Castle Biosciences Inc Aktie

Good afternoon, and welcome to Castle Biosciences First Quarter 2026 Conference Call. As a reminder, today's call is being recorded. We will begin today's call with opening remarks and introductions, followed by a question-and-answer session.

I would like to turn the call over to Camilla Zuckero, Vice President, Investor Relations and Corporate Affairs. Please go ahead.

Thank you, operator. Good afternoon, everyone. Welcome to Castle Biosciences First Quarter 2026 Results Conference Call. Joining me today are Castle's Founder, President and Chief Executive Officer, Derek Maetzold; and Chief Financial Officer, Frank Stokes. Information recorded on this call speaks only as of today, May 6, 2026.

Therefore, if you're listening to the replay or reading the transcript of this call, any time-sensitive information may no longer be accurate. A recording of today's call will be available on the Investor Relations page of the company's website for approximately 3 weeks following the conclusion of the call.

Before we begin, I would like to remind you that some of the statements made today will contain forward-looking statements, including statements about expected addressable markets, statements containing projections regarding future events or our future financial or operational results and performance, including our anticipated 2026 total revenue and the impact of our investments and growth initiatives, including our ability to achieve long-term growth and drive stockholder value.

Forward-looking statements are based upon current expectations and involve inherent risks and uncertainties. There can be no assurances that the results contemplated in these statements will be realized. A number of factors and risks could cause actual results to differ materially from those contained in these forward-looking statements. Please refer to the risk factors in our most recent SEC filings for more information. These forward-looking statements speak only as of today, and we assume no obligation to update or revise these forward-looking statements as circumstances change.

In addition, some of the information discussed today includes non-GAAP financial measures such as adjusted revenue, adjusted gross margin and adjusted EBITDA that have not been calculated in accordance with U.S. GAAP. Reconciliations of these non-GAAP financial measures to the most directly comparable GAAP financial measures are presented in the tables at the end of our earnings release issued earlier today, which has been posted on the Investor Relations page of the company's website.

I will now turn the call over to Derek.

Thank you, Camilla, and good afternoon, everyone. We delivered strong first quarter results, building on our momentum from 2025. Thanks to the strong execution by the entire Castle team, we delivered revenue of $83.7 million. Test report volumes for our core revenue drivers grew 36% compared to the first quarter of 2025.

Excluding DecisionDx-SCC and IDgenetix revenue, our revenue growth for the first quarter of 2026 is approximately 42% compared to the first quarter of 2025, highlighted by double-digit year-over-year test report volume growth for both DecisionDx-Melanoma and TissueCypher. Throughout the first quarter of 2026, our teams remain focused on executing our growth priorities and our strong performance gives us confidence to raise our 2026 revenue outlook to between $345 million to $355 million compared to our previous provided guidance of $340 million to $350 million.

Now I will walk you through business highlights from the first quarter, and then Frank will provide additional financial highlights before we turn to your questions. Let's start with our core revenue drivers and what we see as the bulk of our 2026 top line growth story, DecisionDx-Melanoma and TissueCypher.

For DecisionDx-Melanoma, we delivered 10,021 test reports in the first quarter, representing 16% year-over-year growth. Further, March of 2026 saw an all-time high record month for test reports delivered. We believe DecisionDx-Melanoma remains a durable growth driver and continue to expect mid- to high single-digit volume growth for the full year 2026.

Driving test adoption and sustaining our competitive advantage through robust clinical evidence remains a key priority. We recently presented new data at the 2026 American Academy of Dermatology Annual Meeting, demonstrating that our DecisionDx-Melanoma test can significantly improve risk prediction within the American Joint Committee on Cancer, or AJCC, stages for patients with cutaneous melanoma. These data from 1,868 CE-linked patients showed that DecisionDx-Melanoma significantly stratifies 5-year melanoma-specific survival within AJCC stages and T categories, identifying patients whose mortality risk is substantially higher or lower than staging alone would predict.

What this means is that in this study, DecisionDx-Melanoma provided clinically meaningful differences in risk within the same stage, enabling more personalized risk-aligned management decisions by helping clinicians identify patients who may warrant closer monitoring or early intervention while also recognizing those who may safely be managed less intensively. These great results are in addition to our recently published data from the prospective multicenter study evaluating DecisionDx-Melanoma's i-31 SLNB test result. Data from this prospective U.S.-based study confirmed again that our test identified patients with a less than 5% predicted risk, consistent with the National Comprehensive Cancer Network guideline thresholds while maintaining favorable outcomes and outperforming traditional staging criteria.

Now let's turn to our gastroenterology franchise. During the first quarter of 2026, we delivered 11,745 TissueCypher test reports compared to 7,432 in the first quarter of 2025, which is 58% growth. Consistent with our DecisionDx-Melanoma test in March, March also represented an all-time record month for TissueCypher. Two studies were recently presented at the Digestive Disease Week by researchers at the Mayo Clinic. The findings demonstrated how molecular risk stratification with the TissueCypher test refined risk assessment and directly informed real-world management decisions for patients with Barrett's esophagus with one study showing changes in surveillance intervals in more than half of patients compared to recommendations guided by traditional histopathology alone, supporting more personalized, risk-aligned patient management. Look to our news release from earlier this month for more information on these studies.

Looking to the full year, we expect to add a similar number of tests in 2026 as we did in 2025, indicating year-over-year growth approaching 50%. Let's move on to what we believe are our midterm, which we view as 2027 and 2028 revenue drivers, which includes our AdvanceAD-Tx test in addition to our core revenue drivers. As a reminder, AdvanceAD-Tx is our first-in-class test designed to guide systemic treatment selection for patients 12 years of age and older with moderate-to-severe atopic dermatitis, or AD. You may recall that we released this test under a limited access program mid-fourth quarter of 2025.

Continuing on our limited access during the first quarter, we received approximately 650 orders. Initial responses indicate that clinicians appreciate that AdvanceAD-Tx integrates into their existing AD care pathway, helping them make more informed systemic therapy choices early in the patient treatment journey. Supporting this claim, during the quarter, we published data from a prospective multicenter clinical validation study in the Journal of the American Academy of Dermatology, demonstrating that AdvanceAD-Tx can identify patients with moderate-to-severe atopic dermatitis who are significantly more likely to achieve greater and faster responses when treated with a JAK inhibitor compared to a Th2 biological therapy.

The data showed that AdvanceAD-Tx can stratify patients by molecular profile, identifying those more likely to achieve near-clear skin or EASI-90, faster time to response and meaningful patient-reported benefits when taking a JAK inhibitor, supporting improved outcomes and more biologically informed systemic treatment decisions early in the treatment journey with JAK inhibitor therapy as compared to Th2 targeted biologic therapy.

Based on revenue cycle time lines, we expect to be in a position to provide more detail on reimbursement by the end of the third quarter 2026.

And with that, I will now turn the call over to Frank.

Thank you, Derek, and good afternoon, everyone. As Derek noted, our first quarter financial performance marks a strong start to 2026. Revenue was $83.7 million for the first quarter of 2026, driven by continued strength in our core revenue drivers. For total revenue for 2026, we are raising our revenue guidance to $345 million to $355 million, up from the previously provided range of $340 million to $350 million. This is growth of high-teens to low 20s in 2026 over 2025, excluding revenue from DecisionDx-SCC and IDgenetix from the 2025 and '26 totals.

Our gross margin during the first quarter of 2026 was 72.8% compared to 49.2% in the first quarter of 2025. As a reminder, first quarter of 2025 gross margin reflects the onetime adjustment of an acceleration of amortization expense of approximately $20.1 million. Our adjusted gross margin, which excludes the effects of intangible asset amortization related to our acquisitions and excludes the effects of revenue adjustments in the current period associated with test reports delivered in prior periods, was 75.6% for the quarter compared to 81.2% for the same quarter in 2025.

Turning to expenses. Our total operating expenses, including cost of sales for the first quarter of 2026, were $102.1 million compared to $115.9 million for the first quarter of 2025. Sales and marketing expenses for the quarter were $41 million compared to $36.8 million for the same period in 2025, primarily driven by higher personnel costs and higher sales-related travel expenses. Increases in personnel costs reflect a higher headcount driven by sales force expansion as well as merit and annual inflationary wage adjustment for existing employees. Higher sales-related travel expenses reflect increased field activity to support growing test report volumes.

General and administrative expenses were $23.9 million for the quarter compared to $21.8 million for the same period in 2025, primarily attributable to higher personnel costs, higher information technology-related costs and higher travel costs, partially offset by a decrease in professional fees. Increases in personnel costs reflect headcount expansions in our administrative support functions as well as merit and annual inflationary wage adjustments for existing employees.

Cost of sales expenses were $20.5 million in the first quarter of 2026 compared to $16.4 million in the first quarter of 2025, primarily due to higher expenses for lab supplies, higher lab services costs, higher personnel costs and higher depreciation expense. The increase in expenses for lab supplies and lab services expense was driven by higher test report volumes. Increases in personnel costs reflect a higher headcount due to additions made to support business growth in response to growing test report volumes as well as merit and annual inflationary wage adjustments for existing employees. The higher depreciation expense reflects continued investment in and expansion of our laboratory facilities.

R&D expenses were $14.4 million for the quarter compared to $12.6 million for the same period in 2025, primarily due to higher personnel costs and higher clinical studies costs. The increases in personnel costs reflect a higher headcount to support continued business growth and increases in clinical studies costs reflect investment in our pipeline products.

Total noncash stock-based compensation expense, which is allocated among cost of sales, R&D and SG&A expense, was $9.8 million for the first quarter of 2026 compared to $11.2 million in the first quarter of 2025. Interest income was $2.5 million for the first quarter of 2026 compared to $3.1 million in the first quarter of 2025.

Our net loss for the first quarter of 2026 was $14.5 million compared to a net loss of $25.8 million for the first quarter of 2025. Diluted loss per share for the first quarter was $0.49 compared to a diluted loss per share of $0.90 for the same period in 2025.

Adjusted EBITDA for the first quarter was negative $5.1 million compared to $13 million for the comparable period in 2025. The year-over-year change primarily reflects a onetime noncash amortization expense recognized in 2025 related to the accelerated amortization of our IDgenetix test.

Net cash used in operating activities was $22.1 million for the first quarter of 2026 due in part to annual cash bonus payments and certain health care benefit payments that do not recur through the remaining 3 quarters of the year. Net cash used in investing activities was $25.8 million for the first quarter and consisted primarily of purchases of marketable investment securities of $55.1 million, purchases of property and equipment, partially offset by the maturities of marketable investment securities and the sale of equity securities.

As of March 31, 2026, we had cash, cash equivalents and marketable securities of $261.7 million. As we've discussed, we expect M&A to play a role in our growth story, and we intend to continue to evaluate candidates that fit within our strategic opportunities criteria.

In closing, I'm pleased with our strong first quarter results and increased guidance, which reflect the consistent execution and momentum we are building across the entire business.

I'll now turn the call back over to Derek.

Thank you, Frank. In summary, I am pleased with our strong start to 2026. We remain confident in our ability to execute our growth strategy and drive long-term value to our stockholders. Finally, I want to thank the entire Castle team for their dedication to advancing patient care and improving patients' lives. We're proud of our accomplishments and excited about the path ahead, and we look forward to sharing our continued progress in the coming quarters.

Thank you for your continued interest in Castle Biosciences. Now we will be happy to take your questions. Operator?

[Operator Instructions] Your first question comes from the line of Mason Carrico with Stephens.

I want to start out with TissueCypher volume, 58% growth year-over-year. Obviously, that's great growth. But volumes did decline very modestly quarter-over-quarter. That just hasn't happened since early 2024, I think. So any unique dynamics to call out in the quarter that may have contributed to that weather, seasonality, anything capacity related? Just I guess, any color there would be great.

Yes. Sure, Mason. Thanks. As you noted, we continue to see really strong growth there with 58% year-over-year growth. On the sequential or quarter-to-quarter trend there, I think we finally have hit the penetration level where we are seeing seasonality and seeing and feeling the sense of that.

Based on looking at IQVIA third-party data, historically, the first quarter of the year has fewer GI procedures than the other quarters. But having said that, importantly, March was a record month for TC and that trend continued in April. So I think we're going to add -- we would expect to add a similar number of test reports in '26 as we did in '25, and that gets us something close to a 50% year-over-year growth for the year. And so good performance on the test, and we continue to be pleased with what we're seeing.

Got it. And you guys update -- or would you give us an update on the reimbursement initiatives for your AD-Tx test or the progress you've made on that front? And then I guess as kind of a follow-up to that, on the potential for revenue to become material there in 2027 or 2028, where does that -- where do you expect that revenue to come from? Is it all from appeals? Or could there be some other revenue model contributing next year by 2028?

So we don't -- Mason, Derek here. We think based upon the long revenue cycles from an RCM perspective, we could be in a position probably by the end of the third quarter to provide some good evidence-based clarity in terms of what we're seeing, what we can assume for 2027, 2028 under a traditional reimbursement approach. There are, of course, other avenues as well in terms of interested parties who may be interested in controlling the cost of having patients keep cycling around medications. And of course, there's always an opportunity to potentially partner with some of the pharmaceutical companies who might have interest in having their share shifted.

But for -- right now, I would say if we rely primarily on traditional governmental or private payer reimbursement, probably in the third quarter so we can give some strong clarity based on evidence.

Your next question comes from the line of Thomas Flaten with Lake Street.

Any -- I think you guys were relocating to a new Phoenix lab at some point this year. Any update on what impact that might have on gross margins going forward?

I don't think we'll see much impact on gross margins, Thomas. We haven't made that change yet. We're moving into an expanded facility in the Phoenix area. And that's really towards -- an eye towards -- as you recall from working with us for a while, we try to stay a couple of years ahead of demand in terms of capacity. And so as we look at the expanding derm franchise and the growth in those test volumes, in particular, we're trying to stay ahead of it. So I don't have guidance for you on when we'll make that move, but I don't think you'll see much impact on gross margin at all as we shift from one facility to the other.

Got it. And then on to AdvanceAD, any thoughts on broadening this initial rollout? I think you had 150 accounts targeted as the first group. Will that stay at those 150 for the foreseeable future, at least until you have more visibility into reimbursement?

We opened up access a bit more in this first quarter of this -- late in the first quarter. And we'll kind of look at our volume, look at our early RCM assumptions here, make sure we're on track and then kind of continue to go and release it over time. But that being said, having 650 orders come in the door in the first quarter is very, very nice reinforcement of the opportunity that we have here when the field force is 100% focused on melanoma, and we have such limited access to our customer base. So we are quite pleased with the continued early response of the dermatologic clinicians out there in the field.

Your next question comes from the line of Catherine Schulte with Baird.

Maybe first for the mid- to high single-digit melanoma volume growth for the year after a really strong start there with mid-teens growth in 1Q, should that double-digit growth continue in the second quarter with some conservatism baked into the back half? Or how should we think about the phasing there?

Yes. We did reiterate, Catherine, our 2026 mid- to high single-digit growth expectations. Q1 was a bit of an easier comp than we expect for the rest of the year. So we're pleased with that. I think that's where we see the business trending.

Okay. And then I guess, have you guys been getting any feedback from clinicians regarding some of the moving pieces on NCCN guidelines? And any feedback you've received on the future oncology publication or any other data that you've put out recently?

So we continue to get good feedback on -- I don't quite understand what NCCN sees here. This is a failed study, failed to meet the 5% cut point here. So what's trying to be said, which is good for us. I think, unfortunately, from an NCCN standpoint, there's a belief that this is really more political than we even thought, I guess you would say. We're hearing that from most of our customers. The recent DeCIDE study, which came out in Future Oncology earlier this year was another strong reinforcement that if you use our test to look at accuracy.

Once again, we have one more study showing that we comfortably get way below 5% predicted risk in people who actually underwent an SLNB. And as important in that same publication is that people who used our test to move away from SLNB, meaning you didn't know if you were going to be positive or negative, had extremely strong outcomes. It was 97.8% recurrence-free survival over the time period of the publication. That is a really safe melanoma patient, if you can, I guess, use those 2 words together, right? So that continues to be strong reinforcement that we've got data that they can rely upon that's consistent over time, which is excellent. And I think that's what also led to having our greatest month ever in March of this year.

Your next question comes from the line of Subbu Nambi with Guggenheim.

This is [ Thomas ] on for Subbu. Frank, you mentioned M&A. Is that something you're looking at near term? Can you just walk us through those factors you're considering when evaluating targets that meet your criteria there?

I mean I think we always are open eye to what may be a possibility. We own things as we become aware of them. We don't feel compelled to chase anything. I think we've got a great opportunity with what we own and control today. But we do look at things as they come around or come across us. And as you know, the goldilocks approach is pretty tough. I mean things have to look pretty good, but we do think that could be part of the future.

Great. And then separately on -- maybe on sales force. Can you just give an update today on derm and GI? And then maybe how headcount expansion is expected to look for this year? And how does that translate to selling and marketing spend?

Yes. We -- what we said is we think we can cover for the time being in the near term, both of those verticals with fewer than 100 reps, and that's where we are today.

Your next question comes from the line of Matthew Parisi with KeyBanc Capital Markets.

This is Matthew Parisi on for Paul Knight at KeyBanc Capital Markets. Congrats on the quarter. You previously mentioned in 2025 that melanoma received FDA breakthrough designation. And I was wondering if Castle is still preparing for like an FDA submission in '26 that you mentioned?

We are moving forward with a submission along that same time line sometime in 2026 here, yes.

And then just one other follow-up. Just wondering if there's been an update on SEC. I know you guys had received acceptance of the reconsideration request for both Novitas and MolDx. And if there's just any update or an idea on timing?

No official update, I guess, from either one of the Medicare contractors, Palmetto or Novitas since, I guess, our year-end earnings call a few weeks ago. We still continue to believe that there -- that kind of a year plus review cycle should be plenty of time for a reconsideration request that was accepted in, I guess, July and September accordingly between Novitas and MolDx. So we aren't, at this point in time, thinking that there is a later posting of a draft LCD than sort of the second half of this year. That would be surprising.

Your next question comes from the line of Kyle Mikson with Canaccord.

This has been covered, I apologize. But on the 650 orders for the atopic dermatitis test, could you just talk about recent trends and how you expect that to accelerate going forward? And when you think about that number getting into the thousands, I guess, in the relative near term here, how does that affect the cost structure of the company? I guess I know it's obviously not super material. But as we see gross margin decline sequentially and things like that, I'm just curious how we should be thinking about P&L impact.

Yes. So Kyle, I think that what we see right now the primary hurdle for our AD test is just our -- candidly, our willingness to -- how available do we want to make it. In terms of impacting the overall COGS profile, that's a pretty efficient test. It's PCR-based test. And so even with some growth in volumes from where we were in Q1, we wouldn't expect a material impact on the blended adjusted COGS structure of the company, certainly in the next several quarters anyway.

Okay. Now on that note, I guess the -- how do you guys kind of anticipate expenses, the cadence of expenses throughout this year because it was a little bit surprising to see the net loss and the lower-than-expected EBITDA in the quarter. And as we think about cash flow positivity and that's been this goal for '26, '27 for a while with the SEC, how should we -- what's the updated thoughts on that metric?

Yes. So as you know, we continue to focus growth on sort of 3 windows, Kyle, near, medium and long term. And as we support that, we do expect some growth in operating expenses. I think as we get through Q1 here and we lap the more meaningful change in FCC revenue, we'll get to a more meaningful comparability period going forward. But I think that we continue to grow into the P&L and leverage the cost structure and our intent there is to generate meaningful returns on those operating expenses driving value going forward.

Your next question comes from the line of Puneet Souda with Leerink Partners.

So first one, maybe on the guide itself, you beat by $4 million, raised by $5 million, largely banking the beat. Just wanted to understand how much of the beat was from FCC? And then I have a follow-up on the TissueCypher.

Yes. Most of that beat was driven by TissueCypher.

Okay. Got it. And then can you maybe provide a little bit more color on the TissueCypher ramp throughout the year? I think you called out you had the 2 best quarter -- I didn't mean March and April, 2 best months, March and April, but maybe that was sequentially down. I didn't exactly catch that. Maybe if you can provide some more color there. So how should we think about the ramp from 1Q to 2Q?

I mean it seems it could be larger than what you saw last year, especially given another 18,000 up year-over-year. So maybe just talk to me in terms of the TissueCypher ramp.

Yes. So as we said, Puneet, we continue to think we'll add a similar number of tests reports for '26 as '25. I think we're big enough or penetrated enough now that probably some seasonality is probably to the point where we feel it. And as I referenced, the number of procedures tends to be lower in Q1. So I think we'll see that growth come ratably through the year. I don't see amount of things quarter-to-quarter that should shift that from more of a ratable ramp.

There are no further questions at this time. I will now turn the call back to Derek for closing remarks.

This concludes our first quarter 2026 earnings call. Thank you again for joining us today and for your continued interest in Castle Biosciences.

This concludes today's call. Thank you for attending. You may now disconnect.

Good afternoon, and welcome to Castle Biosciences DecisionDx-Melanoma Webcast. As a reminder, today's webcast is being recorded. Drs. Guenther and Goldberg will begin with a presentation that follows the accompanying slide deck, followed by a brief question-and-answer session. I would now like to turn the call over to Dr. Matthew Goldberg, Senior Vice President of Medical for Castle Biosciences.

Thank you, operator, and good afternoon, everyone. My name is Matt Goldberg. I'm a board-certified dermatologist, dermatopathologist and I serve as Senior Vice President of Medical here at Castle Biosciences. Before we get into the DECIDE publication itself and before Dr. Guenther takes us through the data in detail, I want to spend a few minutes setting the clinical stage for why this study matters. And my goal here is to ground the discussion to questions physicians are actually trying to answer in early-stage melanoma and then to level set that DecisionDx-Melanoma is already a well-validated test with a strong evidentiary foundation. And this foundation includes retrospective and prospective studies along with meaningful real-world evidence. So from this perspective, the DECIDE trial is best viewed not at the beginning of the story, but as an important new prospective multicenter addition to an already strong body of evidence supporting DecisionDx-Melanoma and Stage I through III cutaneous melanoma.

So for my part of the discussion, I'll attempt to do 4 things here. First, I'll briefly frame the key decision points in early-stage melanoma. Second, how DecisionDx-Melanoma was designed to answer 2 important clinical questions. Third, walk through the validation work that's already existed for the DecisionDx-Melanoma test and introduce the DECIDE study here before handing things over to Dr. Guenther, who will review the publication in more detail that was just published in future oncology. So with that, on to the next slide, I wanted to start with the practical decisions physicians are making when they see a patient with newly diagnosed cutaneous melanoma. And this is really the right place to begin because if we don't frame the clinical problem correctly, it's hard to identify the value of the test for the clinicians and patients who receive the test results. In melanoma, these decisions are very concrete.

They affect surgery, surveillance intensity and who can remain primarily in a dermatology-led clinical care pathway and those who move into more intensive and multidisciplinary oncology pathways. And traditionally, staging and clinical pathologic factors are used to answer 2 central questions after diagnosis of cutaneous melanoma. First, what is my patient's risk of sentinel lymph node positivity? And second, what is my patient's risk of recurrence? And those are the 2 questions that really drive patient management. The patient is thought to be at lower risk for poor outcomes. The treatment path is generally of lower intensity, and that usually means treatment with a wide local excision with appropriate margins, lower frequency follow-up, often primarily with dermatology and no advanced imaging. If a patient is thought to be at higher risk, the management plan becomes more intensive, and that can include wide local excision plus a sentinel lymph node biopsy, closer clinical follow-up, involvement with surgical oncology, potentially medical oncology and in some cases, baseline and surveillance imaging.

So the key point here is that these are not theoretical questions. The risk of poor outcomes directly influences which patients stay on lower intensity management paths and which patients move into a more intensive staging and surveillance pathway. Next slide. And so DecisionDx-Melanoma was designed to help answer both of these clinical questions using tumor biology from the primary melanoma. This is a 31 gene expression profile test used in patients with Stage I to III melanoma. It measures expression of 31 genes from the primary tumor and applies a validated algorithm to generate clinically useful risk information to inform clinician decision-making. First, the test provides a class result ranging from Class 1A, which is the lowest biologic risk to Class 2B, which is the highest biologic risk of recurrence or metastasis within 5 years. It's important to highlight that this class result is independent of the clinical and pathologic information available to clinicians to improve the accuracy of risk prediction for their cutaneous melanoma.

It also provides 2 individual outputs seen here on the right side of the slide. One is the i31-SLNB result, which estimates the patient's individual risk of sentinel lymph node positivity. And the other is the i31-ROR result, which estimates the patient's individual risk of recurrence. And this is another important point to emphasize clearly. Predicting sentinel lymph node positivity and predicting recurrence are related, but they're not the same clinical question. Sentinel lymph node biopsy is about nodal or the lymphatic spread of the melanoma to the draining lymph node basin. Recurrence risk is broader. It's asking about the risk of relapse more generally, whether that ultimately presents regionally or distantly as well as including melanoma-specific survival. And so it's entirely appropriate and really what we would expect that the clinical pathologic inputs used for the i31-SLNB and i31 are not identical. For the i31-SLNB result, the model incorporates the gene expression profile score along with ulceration, Breslow thickness, age and mitotic rate.

For the i31-ROR, again, it uses the gene expression profile score and incorporates ulceration, age, Breslow thickness, mitotic rate, sentinel node status as well as tumor location. And this is really a strength of the test. It's really what clinically intelligent model should do here. The model should bring in the specific independent prognostic factors, clinical, pathologic and gene expression profiling that provide the most clinically impactful results to refine risk prediction and inform specific clinical management decisions for patients with cutaneous melanoma. As it relates to the i31-SLNB and as shown on this slide, the 31 gene expression profile score was the most significant variable in predicting sentinel lymph node positivity and is an independent and significant variable in recurrence outcomes as well. So the take-home message here is that DecisionDx-Melanoma was built to answer the actual questions physicians and patients face after a diagnosis of cutaneous melanoma with outputs aligned to the specific clinical endpoint being predicted.

On the next slide here, it's important to level set that DecisionDx-Melanoma is already a well-validated gene expression profile test. What you're seeing on this slide is a representation of the broader evidentiary foundation for DecisionDx-Melanoma. The study shown here span both retrospective and prospective validation cohorts and they consistently show that DecisionDx-Melanoma provides meaningful risk stratification across survival-related endpoints, and the pattern is consistent. Patients with lower risk results, specifically Class 1A results, have markedly better outcomes than patients with a high-risk class result, specifically here in dark red, the Class 2B result. And this robust separation has been demonstrated repeatedly across independent study cohorts. And when we think about the DECIDE trial, it fits this overall evidence foundation. And it's important to say plainly that it builds on a strong body of evidence that exists before the DECIDE trial even begins.

On the next slide here. It's important also to highlight that the evidence is not stopped with just retrospective and prospective validation studies, but also includes substantial real-world data from prospectively tested patients who received the DecisionDx-Melanoma test as part of their ongoing clinical care. And this is what's on this slide here is the Castle's collaboration with the NCI and SEER cancer registry that's really a key part of this story. Because the DecisionDx-Melanoma test is already being used in clinical care for patients with Stage I to III cutaneous melanoma, this collaboration makes it possible to examine outcomes in a large real-world population of patients who actually received the test as part of their melanoma management. This is really what makes this analysis so meaningful. It reflects real patients, real ordering behavior and outcomes after the diagnosis of cutaneous melanoma and clinical practice here in the United States.

First, in this large real-world cohort of clinically tested Stage I to III melanoma patients, the 31 gene expression profile test effectively stratified mortality risk within AJCC substage groups. Second, the 31-GEP test demonstrated significant prognostic value for melanoma-specific survival beyond the traditional clinical pathologic factors, providing independent prognostic information from the information that is known already at the time of diagnosis. And third, the 31-GEP test, DecisionDx-Melanoma test is the only GEP test in melanoma has shown to be associated with improved survival with clinically tested patients showing a 32% lower 3-year melanoma-specific mortality rate than untested patients in this study. So again, before we dive into the DI data here with Dr. Guenther, it's important to level set that DecisionDx-Melanoma has substantial evidentiary basis behind it. And this slide highlights that the story extends beyond validation studies and into real-world patient outcome data derived from clinically ordered tests and used as part of patients' ongoing melanoma care.

Again, these are patients for whom testing was integrated into their actual clinical management after diagnosis. And then the DECIDE study, in this sense, adds more prospective multicenter evidence to this already strong foundation. On to the next slide here. I want -- as we transition into the DECIDE study, it's important to ground the discussion on how sentinel lymph node biopsy decisions and the sentinel lymph node biopsy procedure itself is used in clinical practice. In routine care, physicians start with clinical pathologic factors to estimate a patient's risk of sentinel node positivity. And the key threshold here that matters is the 5%. Current guidelines support avoiding the sentinel lymph node biopsy procedure where the expected risk of sentinel lymph node positivity is predicted to be less than 5% However, once the patient moves above that letter level, the conversation changes. In the 5% to 10% range, sentinel lymph node biopsies to be discussed and considered. And above 10%, this is the group in whom sentinel lymph node biopsy is discussed and offered is seen here in the table on the left.

So I really want to highlight that this 5% threshold is the critical clinical decision-making line. And for an advanced molecular test to be clinically useful in the setting of sentinel lymph node biopsy decision-making, it has to do more than add general prognostic information that has to refine risk in a way that can actually guide clinical decision-making by identifying patients whose predicted risk falls below 5% where clinicians may feel more comfortable deferring sentinel lymph node biopsy. And similarly, it has to move patients whose risk is above 10%, where sentinel lymph node biopsy should clearly be part of the conversation. And this is really the evidentiary bar and why the DECIDE trial matters so much. It's evaluating whether the i31-SLNB result can prospectively identify patients who truly fall on either side of these established clinically meaningful thresholds of 5% and 10%, respectively. So on to the DECIDE study here on this next slide. This is, again, a prospective multicenter clinical utility study designed around a very practical question.

Can the i31-SLNB result prospectively inform sentinel lymph node biopsy decisions in a clinically meaningful way? And the study had 3 primary objectives: first, to prospectively confirm the performance of the i31-SLNB result in predicting sentinel lymph node positivity. Second, to evaluate real-world use of the i31-SLNB result in guiding sentinel lymph node biopsy decisions; and third, to assess recurrence outcomes among patients with less than 5% predicted risk of sentinel node positivity, including patients who did not undergo the sentinel lymph node biopsy procedure. The study enrolled patients diagnosed within 2 months who are being considered for sentinel lymph node biopsy and whose clinicians were ordering the 31-GEP to help guide this specific clinical decision. Testing was performed, results were returned and the patient and physician made the sentinel lymph node biopsy decision in the model of shared decision-making in a real-world clinical setting, evaluating both the Class result and the i31-SLNB result.

Clinical outcomes were then tracked, including sentinel node positivity rates and recurrence-related outcomes in the low risk -- including in the low-risk patients who did not undergo a sentinel lymph node biopsy procedure. And this is the way to really frame the decide data that Dr. Guenther will walk us through here shortly. And it's not trying to collapse every biologic question to just one endpoint. It prospectively evaluates the output that was built for nodal risk, namely the i31-SLNB against the nodal endpoint that matters of sentinel node positivity. And then it follows recurrence outcomes in the patients identified as low risk and managed without the sentinel lymph node biopsy. So in my view, the design study here should be seen as a prospective study that adds both clinical validity and clinical utility evidence to an already well-validated DecisionDx-Melanoma test, specifically around one of the most consequential decisions in early-stage melanoma management of the sentinel lymph node biopsy.

And really, at this point, it's my pleasure to turn the conversation over here to Dr. Michael Guenther. Dr. Guenther is a board-certified surgical oncologist with more than 3 decades of experience in the multidisciplinary surgical management of cancer, including melanoma, breast cancer and other solid tumors. He had his medical degree from the University of Michigan Medical School, completed general surgery residency at the University of Cincinnati Medical Center and then completed advanced Surgical Oncology fellowship training at the John Wayne Cancer Institute affiliated with UCLA. He is certified by the American Board of Surgery. He has served in high-volume oncology practices, most recently with St. Elizabeth's physicians in Edgewood, Kentucky, where he applies evidence-based surgical approaches to cancer diagnosis, staging and therapy. Importantly, he has also been a lead author and investigator on multiple clinical studies, including as lead author on the multicenter DECIDE trial that we'll discuss here shortly. Dr. Guenther, thank you again for being here with us today, and I'll hand the microphone over to you.

Thank you, Dr. Goldberg. And again, I appreciate the opportunity to do this. Slide 13, please. I had the privilege of presenting the first iteration of this DECIDE study back in 2024 at the Society for Surgical Oncology Annual Meeting. We had 322 patients that followed this algorithm, which essentially, as Dr. Goldberg mentioned, began with the diagnosis of melanoma within the last 2 months, a patient over 18 years of age considering a sentinel node biopsy in whom we might use this 31-GEP to guide a sentinel lymph node biopsy decision. At the second visit, we ordered the test and then we decided whether or not to perform a node biopsy. That was a mutual decision. There were times when I made a recommendation. There were times when the patient had a strong feeling and ultimately, we honored what the patient wished to have performed. We then either did or did not do a sentinel node biopsy with a tumor excision, and then track the clinical outcomes of sentinel lymph node positivity, recurrence-free survival, distant metastasis-free survival and melanoma-specific outcomes in those with a less than 5% risk of nodal metastasis.

Next slide, please. The demographics of this study, there were 912 patients. We had an average or median age of 65 years of age between 20 and 90. So we had a nice broad group. The Breslow depth median was 0.8 millimeters and ranged from 0.1 to 12 millimeters. This reflects typical suburban dermatology practices. Interestingly enough, 42% of the patients had a transected base. This also reflects the pattern of shave biopsies in clinical practice and is quite reassuring to clinicians that the assay still applies and functions properly even in that setting. Overall, 47% of the patients had a sentinel node biopsy, of which 10.2% were positive. For those not undergoing a sentinel node biopsy, which was 52.9% of the group, nearly 90% were either T1a, T1b or T2a primaries. We did have 10% of the group that had deeper lesions, which reassuringly did not have node biopsies performed in some instances. Ulceration was present in 9% of the cases. Mitosis was not a frequent finding. Overall, we had a 52% yield of less than 5% nodal predicted risk.

In that discuss and consider group from 5% to 10%, it was 32.2% and 15.8% of the patients had a predicted node positivity rate of greater than 10%. Slide 15, please. In this subset of Stage IB patients, which consists of T1b and T2a lesions, for the non-clinicians in the room, a T1b lesion is a lesion less than 0.8 millimeters with ulceration or high-risk features and a T2a lesion is a lesion between 0.8 and 1 millimeter with or without ulceration. So Stage B, the population of most concern, the sentinel node positivity rate, if you had a low predicted node positivity was 1.4%. In contrast, if you had a high-risk GEP prediction, the sentinel node positivity rate was 18.5%. That's a 13.2x magnifier risk between low risk and high risk. That is a substantial amount of stratification within the same stage, and that is very valid for clinicians. So we reached our threshold well below 5% in the low-risk lesions and had a much higher yield in high-risk lesions.

Next slide, please. Again, in looking at this Stage IB, the most interesting and if we say controversial group, we had that 1.4% yield for low-risk lesions and an 18.5% risk for high-risk lesions from the DecisionDx i31-SLNB. Last year, the MERLIN_001 study was presented and unfortunately, had a 6.5% node positivity rate in the low-risk group and the high-risk group was 2.8x higher. It was 18.3%. So the low-risk i31SLNB was more than 4x lower than the CP-GEP assay was, while the assay only separated risk 2.8x higher in the CP-GEP group. So we were well below that 5% threshold with one assay, but not so with the other and high-risk lesions were 13x more likely to have a positive node. Next slide, please. When broken down by the entire group, a T1 to T4 primary all comers, if you had a less than 5% prediction, the yield was only 2.6%. In the 5% to 10% range, the discuss and consider range, it was 7%. And if it was greater than 10%, it was 21.4%. That's an eightfold magnifier between less than 5% and greater than 10%.

On the other hand, in the group of most concerned, T1b and T2a, only a 1.4% node positivity rate, which then went from 7.4 to 18.5%, a 13-fold magnifier as the risk went up. We had an extremely successful assay at predicting who had low risks of node positivity. On the other hand, every 5 to 10 is a discuss and consider and most of those patients were going to get recommended to undergo a node biopsy and especially with a greater than 10% risk. Next slide, please. Another way of displaying this, the AJCC staging never gives us in this T1b or T2a group, Stage IB, a circumstance where there is a avoid sentinel node biopsy. The MERLIN GEP assay, again, never reaches the threshold of 5% and then also demonstrates a high-risk lesion. The DECIDE study has confirmed for us a very successful prediction of low-risk node positivity as well as the 5% to 10% discussed and the greater than 10%. This stratification is very important because we can precisely identify those high-risk patients who need node biopsies as well as those truly low-risk patients who could safely consider foregoing a node biopsy rather than being in the discuss and consider range.

Next slide, please. This can't be emphasized enough. This discrimination in the same stage between a low-risk lesion and a high-risk lesion is like wiping fog off the windshield. We can see that 13-fold difference between low risk and high risk. This is clinically very actionable, and this is an important assay quality. Next slide, please. The NCCN guideline of 5% is important to discuss. We typically do not perform sentinel node biopsies for lesions under 0.8 millimeters without high-risk features because a very important clinical study called MSLT-I was performed in the 1990s. It randomized patients to a wide local excision or a wide local excision and sentinel node biopsy. A lymphoscintigram was performed preoperatively. The surgeon removed node or nodes from the basin or basins at risk. Those were read as clean by the pathologist and yet the node failed in that basin at a 1% per year risk, which came up to be 5%. So it made no sense to look for something with a less than 5% incidence when the error rate of the test was 5%.

In that setting, a pathology report on a 0.6 or 0.7 millimeter primary with no adverse features would estimate a 1 in 20 chance of a node being positive. If no nodes were biopsied at all, 1 in 20 patients would have a recurrence. That was set up as the guideline by the NCCN. Last year, Dr. Prieto presented accumulation of studies, the CP-GEPs for T1 and T2 lesions had a false negative rate of 6.2% and a true negative to false negative rate of 15:1. That did not yield even equivalents with the NCCN guidelines. The GEP -- the i31-SLNB study from his pooled results showed a 2.8% false negative rate and a 34:1 true negative to false negative ratio, again, exceeding the NCCN guidelines. I'm happy to report that the current DECIDE data was only 2.6% false negative rate for all comers and again, a 37:1 true negative to false negative ratio. But for the group of most significance, T1 and T2as, was only a 1.8% false negative rate and a 55:1 true negative to false negative ratio.

This was very specific and outperformed not only the NCCN guidelines, but substantially outperformed the CP-GEP test, which did not appear to function as well as a simple pathology report. Next slide, please. What happened to those patients with a low-risk lesion who did not have a sentinel node biopsy. They had a 97.8 3-year recurrence-free survival. They did extremely well. If they had a high-risk lesion, they had a 7% -- nearly 7% difference in recurrence-free survival at 3 years. So this was one of the main pillars of the study was to demonstrate that low-risk patients could forgo a node biopsy without jeopardizing their risks, and they were in this study able to do so. Next slide, please. The identification of high-risk patients in a traditionally "low-risk" cohort is incredibly important and is one of my real passions. There is a false consensus or belief that shallow lesions rarely, if ever, spread. That is not true.

Next slide, please. For a simple T1a lesion, last year in a large study in Europe, the CP-GEP assay did not identify a single high-risk patient among 714 patients. In contrast, a large JAAD study performed last year using DecisionDx found an 8% yield of non-1A lesions, Class 1B, 2A or 2B lesions. That was an 8% cohort within there that had an almost 6% higher risk of death. As a clinician, these are patients who are incredibly important to find because they have shallow disease with bad biology. Next slide, please. An example of this is a patient of mine. This is a 45-year-old man who presented with a 0.4 millimeter lesion on his back. Ulceration was present as was regression, no mitosis. This is Stage IB. If you ask a group of dermatologists or primary care physicians what they would do with this, most of them would do a narrow excision in the office, and that would be it. If you follow NCCN guidelines, this is Stage b. It's in the 5% to 10% yield, so we should discuss and consider sentinel node biopsy.

I did not do that. I ordered a DecisionDx, which had a Class 2B score and the gene expression was 0.91, one of the highest I've ever seen. It had a risk of recurrence at 5 years if the nodes were clean of 88.8%, a node positivity rate of 19%. And if it were Stage 3, the recurrence-free survival drops by another 10% to 78%. In that setting, this person underwent a sentinel node biopsy, which demonstrated 1 out of 6 lymph nodes with "melanophages", it was later interpreted as negative at an outside hospital. No further treatment was rendered, and he returned a year later with a lemon sized mass in his left axilla, which was metastatic melanoma. The CAT scan shows that. He underwent 2 cycles of immunotherapy in a salvage dissection, which demonstrated large positive lymph node. This is a shallow lesion that most clinicians I dare say in the absence of gene expression testing that is reliable would have simply performed a narrow excision and would have missed his life-threatening Stage II disease. This is a really important part of this assay's utility.

Next slide, please. Dr. Goldberg touched on recurrence, which is where this assay has its particular strength. If we look at the distribution of gene expressions from 0 to 1, where 0 is our lowest risk group and one is the highest, thankfully, 2/3 of these were in the lowest risk of metastasis, 96% recurrence-free survival at 5 years. These are people for whom deescalation of therapy and follow-up should be considered. They need to follow up with dermatology for new primaries, but they don't need expensive testing, imaging and anxiety provoking high-risk visits. They need to follow with dermatology. On the other hand, the higher-risk lesions had a 61% 5-year relapse-free survival. Nearly 40% of them recurred, and there is clear evidence that those patients benefit from enhanced surveillance and potentially even life-saving treatments such as surgery or immunotherapy. This ability to separate 35% within the spectrum of outcomes is a significant factor in the management of patients and is not present in other gene expression assays.

Next slide, please. We have strong prospective data now, and there is more coming as the future goes by that we have accurate risk stratification. Low-risk test results are associated with extremely low sentinel node positivity outcomes. This i31-SLNB gives us great confidence in identifying which patients can avoid sentinel node biopsy. And should they choose to do so, we had a 2.2% recurrence rate at 3 years. So the assay performed the way we had hoped for and it validated the initial DECIDE study. With that, I think we'd like to thank the folks for listening to this and be happy to take some questions.

[Operator Instructions] Our first question comes from Catherine Schulte with Baird.

I want to just be clear on kind of the incremental takeaways from this data versus what has previously been published. I mean you guys have put up strong data on the path of meeting this kind of NCCN 5% threshold on sentinel lymph node biopsy guidance decisions. So what is kind of the key incremental from this data? And now that you have this prospective multicenter data showing a strong sentinel lymph node biopsy prediction, what is kind of that missing link for NCCN? And do you think this directly addresses some of the level of evidence concerns that they have raised in prior updates?

Catherine, this is Dr. Goldberg here.

Go ahead, Matt.

No, no, go ahead, Dr. Guenther.

I was going to say that the performance of the assay has never been challenged. The reliability, the validation studies, the enhanced numbers through DECIDE have all pointed at the same thing. There has never been a contrary publication that has questioned the validity of either the assay itself or the interpretations of this. The takeaway from the surgeon's point of view is that we need to do less negative sentinel node biopsies, and this is a huge step in that direction. It is also a conviction that we need to do evaluation of shallow lesions that have bad biology because it affects patient outcomes. The perhaps unsung value to this from the clinician's point of view is the recurrence data, which is truly where we affect patient outcomes.

We have the ability to become efficient, giving patients the treatments they need, but avoiding the treatments and tests that they don't. So as far as the NCCN guidelines go, I don't think that this data or that the outcomes from this in any way were challenged by the NCCN. I think that was a consideration for a very narrow subset of patients who would challenge or take a less than 10% yield of a node biopsy in return for some uncertainty. It doesn't affect the 215,000 assays that have been performed or the 13,000 physicians that use this reliably. That data is as strong as it ever has been, and I believe DECIDE just emphasizes that.

Yes. Catherine, I'll just echo Dr. Guenther here that the incremental value here for the DECIDE trial, I think, to Dr. Guenther's point, is the consistency from the retrospective data that's been published from manuscripts like Whitman et al. on the i31-SLNB experiments and now in this prospective multicenter cohort showing again consistent accuracy of the i31-SLNB, ability to identify patients below the 5% threshold at that clinically actionable threshold that remains the threshold in clinical practice and identifying patients at high risk, so over 10%. So it's that delta between low risk and high risk that the DECIDE trial highlights with the consistency from retrospective to this prospective multicenter data here from DECIDE.

The next question comes from Thomas Flaten with Lake Street.

Dr. Guenther, a couple of questions for you. Did you have patients in your enrollees who had a sentinel lymph node biopsy that turned out to be positive? And what was their 3-year performance on a recurrence-free survival basis?

Most certainly did. I think I've had 145 patients I put on this trial. So I most certainly did have patients that were positive. I can't tell you my exact numbers on my own Stage III, but I can tell you what my high-risk lesions, what happened to them, I published that. And we had 30% and 40% recurrence rates on our node-positive Class 2B lesions. They are a completely different subset than any other melanoma population. So node-positive, high-risk lesions do very poorly, node positive but low-risk lesions with good survival, they do quite well. So my data reflects almost word for word what the Castle database shows.

Got it. And then in kind of real-world clinical practice, when you sit down with a patient who might be in the less than 5% AJCC category and you present them with a Class 1 result from the Castle test, what goes into that? Like can you describe some of those conversations? I'm just curious to hear what tends to sway opinion, what tends to push some patients towards getting a biopsy regardless of what data you show them? Just some of the real-world practice implications of bringing this data to bear with the patient.

What a great question. First off, just as a background, melanoma is a scary word, and most of the patients that I see are convinced that they are going to have a terrible problem. And when I promote or when I bring up a discussion of what we could do with this that we could essentially predict the future on their outcome. I've never had a patient say no. The ones with low-risk lesions were overjoyed, they didn't have to see me again. The high-risk lesions, they always thought they were in trouble anyway, so they were reassured that we took it seriously. But having said that, our risk numbers tell us that we start to see lesions that spread at 0.3. So oftentimes under 0.3 millimeters, we are not aggressive there. However, if this is your partner's wife or this is a nursing student or this is a transplant patient or someone who's incredibly anxious, the value of giving good news to a patient is definitely underrated.

I give so much bad news as a surgical oncologist that giving good news to a patient that they have a survival of a Stage I lesion that would be 99.8% or even a Stage 2 lesion that was in the high 90s is invaluable. It's life altering. So the discussion of how would you like to know what this lesion is likely to do almost every person says yes because it affects the outcomes of their lives so much. And then like I said, there are exceptions to the low-risk rule. I typically don't think of this for people under 0.3 unless there is an extenuating circumstance and anxiety relief is one of those. The husband or wife of 3 kids who's 30 years old with a lesion that comes back as a Class 1A with a recurrence of 97% or 98% and a node positivity rate of 1% or 2% is palpable. So that discussion is real world in the office, and you put your finger right on one of the main uses.

And then just final question. You emphasized the point on one of the slides that in the T1a patients, the competitive test didn't discriminate any patients into a higher-risk category whereas DecisionDx-Melanoma did. I think it was an 8% or something other than Class 1A did you have that experience in the DECIDE study where you had patients that were uprisk?

Absolutely. And it's a critical performance for this. Overall, the Castle data under a millimeter is 15% having metastasizing lesion. And so yes, I did, and that's why I order this in that subgroup, and it is sometimes like pulling teeth to get people to think of that. I've had dermatologists argue with me that shallow lesions don't spread. If you look at the survival, 63% of the deaths from melanoma were in patients who are Stage I or Stage II at diagnosis. Their nodes were clean. That is a big numerator. I know the denominator is big as well, but a lot of deaths, the, I'd say the majority of deaths come from people with unrecognized biologically aggressive disease. And the death is not the only factor that goes into that biological aggressiveness.

[Operator Instructions] The next question comes from Puneet Souda with Leerink Partners.

This is Carlos on for Puneet. Congrats on this publication. So I've got 2 questions. The first one, I know it's still pretty early, just about 1.5 weeks, but if you could give any color on how the sales force is utilizing the study and what reception from the doctors that you're speaking with has been so far, that would be really helpful.

So Carlos, did you want to direct that maybe at Derek or Dr. Goldberg?

Yes. I think that's primarily at Derek.

Okay.

Can you restate that question one more time, Carlos?

Just on how you're utilizing this study so far, and what reception to sales force is hearing from doctors?

Sure. So anecdotal right now, just so we're clear on that fact. So there are sort of 3 elements that this study overall communicates, not only this paper here, but also the early report. One of them is to say your peers are using our tests, I mean, last year, nearly 40,000 times to help make early stage -- early decisions in the treatment of these recently diagnosed patients. And what we find is that just behind the patient's decision to undergo or not undergo this procedure, the very next thing is our test. So that tells you, I think, that clinicians who use the DecisionDx-Melanoma test to make sentinel lymph node biopsy guidance decisions actually are using the test from a clinical practice standpoint. That's a great encouragement to say, I'm not an outlier. I'm actually part of good patient care advances adopting with their technologies.

The second element is, as Dr. Guenther went through, does your test consistently identify people who claims are at a low risk of having a positive sentinel lymph node? Are they actually below that 5% standard that's been around for, I would say, several decades, Dr. Guenther, probably since the late '90s, maybe early '90s. And if that's the case, then I have faith that I should be using the test to help make that decision. So it reinforces earlier data showing that time and again, our test has been able to demonstrate that if we say you have a likelihood of being less than 5%, you actually are below 5%. And the third data element is the -- is what happens to these patients if the physician and the patient actually follow a test result and say, you're predicted to have a similar or biopsy that likelihood of positivity less than 5%.

We're going to have a discussion here and avoid that procedure. How do you do? So are we potentially doing harm by not following through with the similar to biopsy surgical procedure? And the answer is no. These patients do extremely well in terms of a low likelihood of having a metastatic event, which is a great way to wrap around good patient care going forward. So those are the 3 elements that this study, I think, lets us communicate well to clinicians. Now the feedback has been, I think, very similar to Dr. Guenther's commentary on the call so far, which is to say the data is pretty straightforward. It's not unique in that it replicates all prior studies, both in terms of predicting sentinel lymph node positivity plus also demonstration is a low risk, a Class 1A test result or a low chance of recurring actually really low in practice.

And so it reinforces those things. And as Dr. Guenther talked about with his case presentation from his practice there, we're also trying to find patients that look like they have, I wouldn't say nice shallow, I think it was the word Dr. Guenther used, shallow melanomas that are harboring really aggressive biology, and we've shown that as well. So those are the elements that we see. The feedback is pretty consistent in that this is one more piece of data that makes me comfortable that we're doing the right thing by incorporating your test in our clinical practice. And we hear that consistently up and down the chain from surgical oncologists like Dr. Guenther to to nurse practitioners and PAs and in the dermatological community. So that's a great element of support to reinforce. I saw your data before. It's always good to have consistent confirmatory data, and this is just one more study which goes ahead and shows it.

All right. That's really helpful. And I have one more follow-up for you. So I thought one of the more interesting pieces of this data was how you did have head-to-head data versus a competitor. If you could just give an update on the competitive environment and how significant this new study is as another tool in your toolbox to compete against that competitor, that would be really wonderful.

So there have, I guess, in the past been a couple of competitors. There is a U.K. firm that launched a test a couple of years ago. I think they went bankrupt maybe last year, last fall, but the test is no longer on the marketplace in the U.S. There is another potential competitor in Germany called NeraCare. They've made attempts to commercialize in the U.S. that have never done that, that I can see. And then we have Skyline, which is what you're referring to here. They launched their test. I think their press release is back in May of 2020, if I recall correctly, second quarter 2020 during COVID.

And I would say looking at medical claim data, we think they've been able to achieve less than 1%, probably less than 1% market share in the U.S. marketplace over the last, I guess, that would be 5 years, almost 4.5 years or so. So most clinicians that we have a chance to talk to, I think, challenge us by saying, what's the data look like? Is it consistent? Are your "claims" actually what you actually have showed in clinical studies? And we can say, yes, they are. And I think that's a pretty common expectation there. So I think that's the commentary I guess I could offer you.

The following comes from Mark Massaro with BTIG.

This is Vivian on for Mark. I actually just had one for Dr. Guenther. So just wondering what value does DecisionDx-Melanoma add in those borderline cases that you outlined, considering sentinel lymph node biopsy when risk is between 5% and 10%. Just what does the treatment pathway look like for those cases that are more borderline?

Another excellent question. And I think one of the shortcomings would be people who only look at the node positivity rate. The node positivity rate comes on every test, and it's personalized and it's precise. But it has to be taken in the context of what is their recurrence-free survival if the node is negative or if it's positive. So for instance, a 5.2% yield of node positivity when the recurrence-free survival is 95% and 94%, respectively, wouldn't make a very big difference, especially if it was on a head and neck area, in a cosmetic area on a young woman, for instance. So all of those need to be factored in. You can't look at just the node positivity. If someone is not a surgical candidate, I typically don't order the test. If they're on home oxygen at the end of life, then the test, I wouldn't order it because I wouldn't be anticipating a node biopsy. So it's -- all the data and the clinical factors and their own emotional status and family circumstance all get factored into that 5 to 10.

Thankfully, over half the people in this study got clarified down into the less than 5% risk. But you can see our node positivity rate was over 7% in that 5% to 10% range. Those are people who, if they have a positive node are going to be candidates for either close follow-up or immunotherapy. And if they have a negative node, but a high recurrence rate, they're also going to get rolled into close follow-up in a survivorship program. So the way that information is actionable is if the node is negative and they have low risks, then we typically would talk about potentially avoiding it. But in our data hands, 7% is not 5%, it's 7%. So if those people have measurably high recurrences and the node would make a difference, and we oftentimes do offer that to them, especially if it's not going to be a sensitive area or cosmetically disfiguring. So that 5% to 10% area is, as I say, discuss and consider. But most of the time, I recommend considering it because of the therapies available and the close follow-up that we can do, whether the node is positive or negative.

And just to echo to add just slightly here on Dr. Guenther here is just how critically important it is in -- you hear how Dr. Guenther framed the response to have confidence in not only the point prediction of sentinel node positivity, but also have confidence in risk of recurrence information that's part and parcel of clinical decision-making at the bedside. And the data presented here from Beard et al. from the DECIDE study really demonstrates high quality of both endpoints, not only of the point prediction for sentinel node positivity, but also robust risk of recurrence information with the Class 1A result having that outstanding performance in the risk of recurrence data that was just presented as well. So it's critical to have visibility to both endpoints when having clear conversations with patients at the bedside.

[Operator Instructions] The next question comes from Mason Carrico with Stephens.

I appreciate you guys hosting a call here. I guess what do you see as the primary reason DecisionDx-Melanoma hasn't been included in NCCN guidelines despite multiple published studies showing its ability to identify patients below that 5% threshold. I mean, is it study design, patient sample size, the duration of follow-up, I guess? I'm just trying to get an understanding of what you guys view or what they believe or what they're pushing back on just given the body of clinical evidence that you published around this test.

Sure, Mason. Derek here. Camilla?

No, that's what I was going to say. We'll hand that one over to Derek, go ahead.

That's an excellent question there. One can look at our data and the consistency over 53, 54, 55 publications, a couple of which are the focus of systematic reviews and meta-analysis, which is the highest level of evidence, of course, and ask why not? And that's a very excellent question that we would hope when we look at this final -- this last publication here from Dr. Beard and colleagues that they'll look at this data and say, you've got a whole swath of prospective studies of retrospective studies of clinical use studies of studies like this one here showing that if you avoid a sentinel lymph node biopsy procedure because of the low-risk prediction, patients do extremely well, but it's hard to imagine why this would not be in the guidelines in a short order. I agree with you on that one.

Got it. And then maybe a similar question, given the data that you published, the utility you've shown in this test, what objections or misconceptions maybe, if any, do you encounter from dermatologists who are still hesitant to use GEP testing to guide either sentinel lymph node biopsy decisions or incorporate the risk of recurrence?

What are the kind of the questions or pushback that we hear?

Yes. Just given, like I said, similar to the last question, the evidence that you published when you talk to dermatologists, what is the common objection or even misconception that they kind of present the dermatologists specifically who are hesitant or choose not to use this type of testing?

So there's probably a couple of buckets there that I think have pretty clear delineation, and there's probably some squishy areas. So the clear delineation bucket is kind of echoing Dr. Guenther's earlier comment that when you hear the word melanoma, it always must be bad. There are a number of dermatological clinicians who -- if they biopsy a suspicious-looking mold, it comes back invasive melanoma, they are -- that patient is going to a surgical oncologist, a medical oncologist for follow-up and care. It's basically kind of a patient being exited out of their practice. And so those dermatologists have a level of -- have a low level of comfort of treating that form of skin cancer and to them ordering our test when they're sort of graduating their patient to a different care pattern, why I'm ordering your test.

And so I don't know how big that population is, but that was bigger a few years ago. It's less big now, I think. But that's clearly one group of dermatological clinicians. I think the other group is to say, I'm a dermatologist in the Kentucky, Cincinnati area where Dr. Guenther lives. He's a very communicative surgical oncologist. We have a great referral pattern back and forth. I'll let Dr. Guenther make the decision if he wants to order the Castle test when I refer an invasive melanoma to him for a consultation. So therefore, let him make that call. So that represents a certain number of dermatologists, maybe more than the first group, I guess I would call that, Mason. And then I think -- it's interesting, the number of new ordering clinicians that we have come on board every year has been amazing to me, I guess, you would say.

And some of that represents dermatologists who, even though the test has been around a while, maybe they have a sort of no see industry people policy, maybe they're just hard to get to because they just have a very, very, very busy practice, and they're just underinformed or unaware. And so the ability of our sales force of our marketing materials to wrap around them and say, "Hey, I know you're busy, but can we sit down and talk to you about advances in the personalized management of your melanoma patients", and then they raise their hand and say, I have no idea what you're talking about. And so there is still a large pocket of clinicians like that where you would think it's been out there a while, what gives and what gives is that they don't wake up in the morning asking what does Castle have for me today that's new.

They don't even know about us sometimes. And that portion of dermatological community is larger than you might expect, but that's also why we see the new ordering clinician growth every year. Sometimes it's somebody who's been formed for a while, and they've seen maybe a Dr. Guenther using the test clinically and they begin to order in their own patients in their practice. And other times, they just have -- they just had such a low awareness of the value of our test and what will I do differently as a doctor, and it just takes time to overcome that. I think those are probably the 3 or 4 main bucket groups.

Mason, could I just add one thing? I get very little pushback from dermatologists. They're generally nice people. They see the data and they say, yes, this is my reality. But I'm afraid that if I order this and send it to doctor university surgeon that he's going to tell me or she's going to tell me, no, I don't use this. So they're afraid sometimes to send this with their patients. Once they get to the point where they understand that this helps them and that they're in their patient's best interest to have this information and that a dermatopathologist at some university is not better than a gene expression test, then we break through. So that's been my biggest frustration from dermatologists is that they don't get surgeon buy-in because some of them are at universities where they're dominated by different rules or nomograms or things like that. That, to me, is a far bigger issue than the dermatologists who are almost always believing in data when they see it.

I will now pass it back over to Dr. Goldberg for closing remarks.

Thank you, operator. And I just want to say thank you to Dr. Guenther for joining us here on the call and for those also who joined us on the call and for participating in Castle Biosciences DecisionDx-Melanoma webinar. Thank you for your attention and interest.

This concludes today's conference call. Thank you for your participation. You may now disconnect your lines.

Good afternoon, and welcome to Castle Biosciences Fourth Quarter and Full Year 2025 Conference Call. As a reminder, today's call is being recorded. We will begin today's call with opening remarks and introductions, followed by a question-and-answer session.

I would like to turn the call over to Camilla Zuckero, Vice President, Investor Relations and Corporate Affairs.

Thank you, operator. Good afternoon, everyone. Welcome to Castle Biosciences Fourth Quarter and Full Year 2025 Results Conference Call. Joining me today are: Castle's Founder, President and Chief Executive Officer, Derek Maetzold; and Chief Financial Officer, Frank Stokes.

Information recorded on this call speaks only as of today, February 26, 2026. Therefore, if you are listening to the replay or reading the transcript of this call, any time-sensitive information may no longer be accurate. A recording of today's call will be available on the Investor Relations page of the company's website for approximately 3 weeks following the conclusion of the call.

Before we begin, I would like to remind you that some of the statements made today will contain forward-looking statements, including statements about expected addressable markets, statements containing projections regarding future events or our future financial or operational results and performance, including our anticipated 2026 total revenue and the impact of our investments and growth initiatives, including our ability to achieve long-term growth and drive stockholder value.

Forward-looking statements are based upon current expectations and involve inherent risks and uncertainties, and there can be no assurances that the results contemplated in these statements will be realized. A number of factors and risks could cause actual results to differ materially from those contained in these forward-looking statements. Please refer to the risk factors in our most recent SEC filings for more information. These forward-looking statements speak only as of today, and we assume no obligation to update or revise these forward-looking statements as circumstances change.

In addition, some of the information discussed today includes non-GAAP financial measures such as adjusted revenue, adjusted gross margin and adjusted EBITDA that have not been calculated in accordance with U.S. GAAP. Reconciliations of these non-GAAP financial measures to the most directly comparable GAAP financial measures are presented in the tables at the end of our earnings release issued earlier today, which has been posted on the Investor Relations page of the company's website.

I will now turn the call over to Derek.

Thank you, Camilla, and good afternoon, everyone. We closed out a strong fourth quarter and delivered an outstanding year in 2025, driven by continued momentum across our core revenue drivers, disciplined execution and the dedication of our employees. I'm intentional in mentioning the dedication of our employees. It is through their efforts that we were able to deliver clinically actionable results with our current commercial tests today and tomorrow with the addition of future tests.

With fourth quarter revenue of $87.0 million, we delivered revenue of $344.2 million for the full year of 2025. Excluding DecisionDx-SCC and IDgenetix revenue from both 2025 and 2024, our revenue growth for the year would have been approximately 34%. For the full year, we also delivered total test report volume of 105,053 test reports from our core revenue drivers, increasing 37% compared to 2024, highlighted by continued momentum in TissueCypher report volume, which achieved 86% growth over 2024.

As I reflect on our many accomplishments across our growth initiatives, we have succeeded in evolving Castle considerably. Over the course of 2025, we completed the acquisition of Previse, entered into a collaboration and license agreement with SciBase, launched our first-in-class AdvanceAD-Tx test, further strengthened our commercial teams and continue to solidify an already strong balance sheet.

At the same time, DecisionDx-Melanoma reached a significant milestone, surpassing 230,000 test orders since launch, and we continue to build a robust body of clinical evidence across our entire portfolio. And we continue with our unwavering commitment to improving patient care. Everything we do with Castle remains focused on innovative, clinically actionable tests that help clinicians make better informed decisions and improve outcomes for their patients.

We can only accomplish this mission because of the people who call Castle home. I sincerely thank our entire team for their hard work, resilience and commitment throughout the year. None of this progress would be possible without them.

As we review 2025 results, I will also outline how we are thinking about our growth story, starting with the drivers of our near-term performance in 2026, then turning to our midterm opportunities and finally discussing the longer-term pipeline that we believe positions Castle well for sustained growth and value creation. Frank will then provide additional 2025 financial highlights and insight for 2026 before we turn to your questions.

Let's start with our core revenue drivers and what we see as the bulk of our 2026 top line growth story, DecisionDx-Melanoma and TissueCypher. In 2025, for DecisionDx-Melanoma, we delivered 39,083 test reports, representing 9% year-over-year growth, achieving our high single-digit volume growth commitment. Importantly, we continue to see new clinicians ordering DecisionDx-Melanoma for the first time. Specifically in 2025, we had 1,795 clinicians ordered DecisionDx-Melanoma for the very first time. This was consistent with our experience in both 2024 and 2023, reflecting continued strong interest and adoption. Additionally, total ordering clinicians over the lifetime of this test is nearing 17,000.

Our compelling body of evidence for DecisionDx-Melanoma also continues to expand with now 58 peer-reviewed publications supporting the clinical use of the test, which is not only a key driver for test adoption, but also meaningfully differentiates our test from the competition. We saw an approximately 31% patient penetration exiting 2025, and we believe DecisionDx-Melanoma remains a durable growth driver in 2026.

Turning to our gastroenterology franchise. TissueCypher delivered 39,014 test reports in 2025 compared to 20,956 test reports in 2024, representing 86% growth and surpassing 80,000 tests ordered to date. We believe this adoption reflects growing clinical recognition of TissueCypher's value in determining a patient's individual risk of progression from Barrett's esophagus to high-grade dysplasia or esophageal cancer.

Barrett's esophagus is the only known risk factor for the development of esophageal adenocarcinoma, one of the fastest-growing cancers in the U.S. Unfortunately, esophageal adenocarcinoma is also one of the most aggressive and difficult cancers to treat with a 5-year survival rate of less than 20%. In 2024, the American Gastroenterological Association, or AGA, released a clinical practice guideline for Barrett's esophagus, stating that it can be effectively treated with endoscopic procedures like ablation and noting that identifying high-risk patients is crucial.

Importantly, TissueCypher was highlighted as the first prognostic test capable of identifying patients with Barrett's esophagus at risk of progression to high-grade dysplasia or esophageal cancer. We believe this recognition by the AGA reinforces TissueCypher's role in providing personalized and clinically validated risk stratification, which in turn assist clinicians and their patients in making better management decisions with the end goal of extending the lives of high-risk patients with interventions at the precancer state.

For the year ended December 31, 2025, we had 2,082 new ordering clinicians for the TissueCypher test, up from 1,234 in 2024. We remain highly focused on education and building awareness to drive continued adoption. With roughly 11% patient penetration for TissueCypher exiting 2025, an expanded commercial team and the compelling clinical actionability with a high clinical need, we continue to believe TissueCypher is still in the early stages of a long runway for significant growth in 2026 and beyond.

Let's move on to the midterm phase of planned potential growth, which we view as 2027 and 2028. In addition to the continued contribution of our core revenue drivers, let's discuss our recently launched AdvanceAD-Tx test. AdvanceAD-Tx is our first-in-class test designed to guide systemic treatment selection for patients 12 years and older with moderate to severe atopic dermatitis. We clinically launched the test on a limited access model in late November 2025. The launch of AdvanceAD (sic) [ AdvanceAD-Tx ] significantly expanded our total addressable market and reinforced our commitment to the dermatology community. Early results have exceeded our high expectations.

As we announced in early January, we limited access to approximately 150 dermatological accounts in the U.S. Through year-end, we were pleased to see that more than half of these initial accounts had ordered one or more tests in the first 5 weeks of clinical availability. As mentioned in our third quarter 2025 earnings call, our market research suggested a high level of clinical need and adoption. The results of the initial 5 weeks of clinical availability match those expectations.

In fact, through mid-February, we received close to 500 orders, continuing to reinforce our expectations for adoption from our mid-2025 market research studies. We expect to expand clinician access in a phased manner based on a number of internal metrics. We expect revenue contribution from AdvanceAD to be immaterial in 2026 with material revenue contribution expected in 2027 or 2028. Based upon revenue cycle timelines, we would expect to be in a position to communicate more about reimbursement in the second half of 2026.

Lastly, moving on to the next phase of our growth strategy, the longer term, which we view as 2028 and beyond, I'll touch on our pipeline initiatives and strategic investments.

Let's start with our GI pipeline. We acquired a non-endoscopic cell collection device with our acquisition of Previse. We plan to use this collection device to gather samples for development of a pipeline test for differential diagnostic and screening support for GI diseases. We expect to initiate and enroll our first patient for the development study in the second quarter of 2026. This test will be upstream from TissueCypher, and we expect preliminary data before the end of 2026. This collection device requires FDA clearance, and we currently expect to both file our submission and potentially receive clearance in 2026.

Next is our collaboration with SciBase, where we will evaluate their Electrical Impedance Spectroscopy or EIS technology for short. We have U.S. and select country rights to a number of possible indications. The first indication we are studying is the ability of the handheld EIS device or PEN, to predict flares in patients with atopic dermatitis. We believe there are at least 2 additional intended uses in the atopic dermatitis population alone should we see promising results from initial flare prediction study.

Importantly, this approach could offer a nice synergy with our AdvanceAD test by extending the ability to support patients across different points in their disease journey. We expect to initiate the EIS PEN study and enroll our first patient for AD flares in the second quarter of 2026 and have preliminary development data before the end of 2026. And to wrap up our near-, mid- and long-term growth strategy, we continue to expect M&A to play a role. With our strong balance sheet and history of successful execution in this area, we continue to evaluate candidates that fit within our strategic opportunities criteria.

That is, number one, tests near or at market; number two, tests near or at reimbursement; number three, tests that can be promoted within sales teams in the size of our current teams or less, that is around 100 or less; and four, test within or complementary to our current customer verticals as a priority. In summary, we believe our financial strength positions us well to invest across our growth initiatives for continued value creation.

And with that, I will now turn the call over to Frank.

Thank you, Derek, and good afternoon, everyone. As Derek noted, we delivered strong fourth quarter and 2025 financial results, supported by disciplined execution across the business.

In the fourth quarter of 2025, we delivered total revenue of $87 million, resulting in $344.2 million for the full year 2025, exceeding our guidance range. Full year 2025 outperformance was driven predominantly by our core revenue drivers, including significant year-over-year test volume growth for TissueCypher at 86%. For 2026, we anticipate generating total revenue of $340 million to $350 million. This is growth to mid- to high teens over 2025 if you exclude DecisionDx-SCC and IDgenetix revenue from our 2025 and 2026 totals, and we do not disclose revenue by test.

Our revenue guide reflects continued growth in our core dermatologic and gastrointestinal franchises, driven primarily by continued TissueCypher momentum with immaterial revenue expected from our AdvanceAD-Tx test and no revenue included for DecisionDx-SCC. Our gross margin during the fourth quarter was 76.3% compared to 76.2% in the fourth quarter of 2024, and our gross margin for the full year 2025 was 69.2% compared to 78.5% in 2024.

Affecting 2025 gross margin was the loss of revenue from DecisionDx-SCC and the onetime adjustment of an acceleration of amortization expense of approximately $20.1 million during the 3 months ended March 31, 2025. Our adjusted gross margin, which excludes the effects of intangible asset amortization related to our acquisitions and excludes the effects of revenue adjustments in the current period associated with test reports delivered in prior periods, was 77.6% for the quarter and 79.8% for the year compared to 81.1% and 82% for the same periods in 2024.

Turning to expenses. Our total operating expenses, including cost of sales for the quarter were $90.8 million compared to $82.3 million for the prior year and were $387 million for the full year 2025 compared to $323.4 million for 2024. As Derek outlined, our growth plan spans the near, medium and long term. In support of that plan, we expect operating expenses to increase moderately in 2026 as we continue to support and invest in our core franchises, advance our pipeline and support key reimbursement and commercial initiatives.

Sales and marketing expenses were $138.1 million for the full year compared to $123.5 million for 2024. The increase is primarily driven by increased personnel costs due to both expanded headcount and compensation adjustments higher expenses associated with training events and speaker conferences and higher sales-related travel expenses.

General and administrative expenses were $91.2 million for the full year compared to $76.6 million for 2024. The increase is primarily attributable to increased personnel costs from expanded headcount and compensation adjustments and higher information technology-related costs.

Cost of sales expenses were $71 million for the full year compared to $60.2 million for 2024, primarily due to increased personnel costs from expanded headcount and compensation adjustments and higher expenses related to services, supplies and depreciation.

R&D expenses were $51.9 million for the full year compared to $52 million for 2024, primarily due to increased personnel costs from expanded headcount and compensation adjustments, offset by lower clinical studies costs.

Total noncash stock-based compensation expense, which is allocated among cost of sales, R&D expense and SG&A expense was $45.9 million for the full year, down from $50.3 million for 2024. Interest income was $11.8 million for the full year 2025 compared to $12.9 million for 2024. Our net loss for the fourth quarter of 2025 was $2.3 million compared to net income of $9.6 million for the fourth quarter of 2024, and our net loss for the full year 2025 was $24.2 million compared to net income of $18.2 million for 2024.

Diluted loss per share for the fourth quarter was $0.08 compared to diluted earnings per share of $0.32 in the fourth quarter of 2024. Diluted loss per share for the full year 2025 was $0.83 compared to diluted earnings per share of $0.62 for 2024. Adjusted EBITDA for the fourth quarter was $11.5 million compared to $21.3 million for the comparable period in 2024. For the full year 2025, adjusted EBITDA was $44 million compared to $75 million in 2024. Net cash provided by operating activities was $26.9 million for the fourth quarter of 2025 and $64.3 million for the full year.

Looking ahead, historically, in the first quarter of the year, we've seen net operating cash use due in part to annual cash bonus payments and certain health care benefit payments that do not recur during the remaining 3 quarters of the year. Net cash used in investing activities was $60.4 million for the 12 months ended December 31, 2025, and consisted primarily of purchases of marketable investment securities of $188.7 million, purchases of property and equipment, our asset acquisition of pre-buys and purchases of debt securities classified as held to market, partially offset by the maturity of marketable investment securities.

Capital expenditures totaled $36 million in 2025. In 2025, we generated free cash flow, defined as net cash provided by operating activities less capital expenditures of $28.3 million. We expect capital expenditures to decline in 2026. As of December 31, 2025, we had cash, cash equivalents and marketable securities of $299.5 million. In closing, I'm pleased with our strong 2025 financial results, which reflect our continued track record of disciplined execution and focus on driving long-term shareholder value.

I'll now turn the call back over to Derek.

Thank you, Frank. Before concluding, I want to share my sincere gratitude to each and every member of the Castle team who continue to deliver meaningful impact for patients and clinicians every day. I am incredibly proud of our team and grateful for the culture they continue to build here at Castle.

In summary, we are executing on the drivers of our next phase of growth, supported by disciplined capital allocation, operational excellence and relentless innovation, which we believe positions us well for a long-term sustainable growth and value creation.

Thank you for your continued interest in Castle. Now we will be happy to take your questions. Operator?

[Operator Instructions] Our first question will be from the line of Kyle Mikson with Canaccord Genuity. This is Alex Vukasin on for Kyle Mikson.

Congratulations on a strong finish to 2025. When last we spoke in early '26, you noted you've recently submitted new data to NCCN. Recognizing that DecisionDX-Melanoma is unique, and that it's GEP test that has demonstrated improved patient survival and GEP score provides meaningful prognostic information beyond traditional staging alone. Can you just concisely elaborate any takeaways from the recent NCCN update? And what is the level of confidence that DecisionDx-Melanoma could ultimately be included in guidelines? And what does that rank in terms of level of importance?

A lot of questions there, I'll try and answer what I can here. I might miss something. So I think the most important element to think about is that the U.S. standard across all of the sort of organizations that put out guidelines or recommendations for considering to perform or to avoid a sentinel lymph node biopsy surgical procedure has been 5% for several decades. And that was not changed in this update either. So it remains that if a patient and a physician or a health care provider believes a chance of having a positive node is greater than 5%, then one should consider and discuss that or encourage a patient to undergo that procedure.

As you know or may know, our data regarding DecisionDx-Melanoma has shown time and time again in both prospective studies and retrospective studies that a low-risk result from DecisionDx-Melanoma gets you comfortably below 5%, indicating that a patient can have a conversation and hopefully avoid what's an unnecessary surgical procedure.

What the guidelines also showed with this update when they reviewed the MERLIN_001 study is that the MERLIN test fails to achieve this threshold of 5%, which we knew last year when it was published in September, October 2025. So the current guidelines would say there isn't a recommendation to consider DecisionDx-Melanoma, which we'll get to in just a minute. There isn't an acknowledgment or recommendation that the Skyline test actually gets below 5%. And in fact, they also state that it acts similarly to nomograms, which today can't get below 5% from a population basis set. So it's a little head scratching.

Now to answer your question about the outcomes data such as our SEER publication that was not included in the updated guidelines, I think we did a quick count. We have 58 peer-reviewed publications that review our test for both predicting the likelihood of a sentinel lymph node biopsy outcome being below 5% or greater than 5% as well as survival benefits. So talking about recurrence-free survival, distant metastasis-free survival, melanoma-specific survival. We also have clinical use studies showing how doctors have safely used our test results to manage clinical care.

And as you noted, we also have data from the National Cancer Institute, where we map people who received DecisionDx-Melanoma as part of their clinical care with patients in the SEER database who did not receive our test as part of their clinical care and found that when care is guided with the use of our test results, there is an association with improved survival, not just overall survival; but more importantly, melanoma-specific survival. It's a bit of a head scratcher.

It turns out that of those 58 articles, that have been published and easily found by doing a literature search, only 11 are cited in the current guidelines, meaning 47%, including the one you mentioned earlier, the NCI SEER database were not reviewed by the NCCN committee. So that's a good head scratcher about why 47 studies were ignored when what they're looking for is apparently more published evidence to support the use of our test.

That was very helpful. And one last one for me. So one thing we haven't touched upon is the FDA submission for DecisionDx-Melanoma. What is your time line on when we could see FDA approval for this test? And how will this help you in payer discussions, effectively drive higher adoption and potentially reaccelerate test volume growth for this test?

Yes. That's a good question there. So we are preparing our submission as we speak now. we believe that it will be accepted as a de novo 510(k) submission as opposed to PMA submission. And those timelines from the time of submission to time of clearance are pretty well prescripted by the FDA. So that may be something which we would see towards the end of the year or maybe early next year. That's hard to say.

In terms of sort of impact on clinician update since that was the last part of your question, I don't know if there's any evidence that we have seen where you take a lab-developed test and move it over to an IVD cleared device where you would see or expect a sort of substantial change in sort of volume uptake. There are certainly going to be clinicians out there, I think, who may be waiting for sort of an FDA flag of approval. So maybe I'm being a little too conservative there.

I think the bigger impact and the reason why we are going forward on this is looking at the newer state biomarker laws, which, among other things, would indicate that across most of the states who have enacted biomarker laws, if you have an FDA cleared or approved device, then that qualifies for reimbursement or payment from commercial insurance carriers with a few other caveats there.

And so our primary drive, to be honest, about looking to achieve 510(k) clearance was to focus on leveraging state biomarker laws to reduce nonpayments from commercial insurance carriers. So that's the value that we would see. I think the quicker we can get that into the FDA and out of the FDA will then have a subsequent impact, I think, on our overall commercial ASP.

The next question will be from the line of Subbu Nambi with Guggenheim Securities.

This is Thomas on for Subbu. Maybe one on AD-Tx. [ Our checks ] indicated a high level of awareness of the test already in the field and looks like from your prepared comments, that's pretty consistent. Can you just speak a bit to the strategy of your sales team approaching derms with that test and what's led to the rapid KOL awareness?

Let see. I'll try to answer that question. So that's interesting. I wouldn't have guessed we had generated that much awareness depending upon the panel you guys looked at. So that's quite positive, by the way. So thank you for that.

We released the test, as we talked about, I guess, back in January, maybe with a limited access launch and I guess, the last week of November, so kind of 5 weeks of availability to roughly 150 accounts that were dermatological accounts. The majority of those were accounts that were early adopters of gene expression profile testing. So we knew that they had a predilection towards adopting new technologies for patient care. There were also in there a few clinical sites that were not necessarily early adopters of gene expression profile tests, and there were also a small number of KOLs that were not involved in our studies or don't treat skin cancer.

And of those, I think we had noted in January that over half of them had ordered at least one or more tests in the first sort of 5 weeks, and that's a pretty good uptake we thought relative to Thanksgiving being in there, Christmas and Hanukkah from a reduced office use standpoint. So that felt quite positive. And through, I think, mid-February or maybe it was last week, I can't remember the exact date, we had received over 500 orders from the accounts that we've allowed to have initial access to. So I think we would concur that the interest is as high as we thought it would be relative to the market research that we completed last summer, and that continues to be the case here.

As we look forward to the rest of 2026, we look at sort of what's the current split. So currently, we have our field force, which was 100% bonus on DecisionDx-Melanoma test results because that's the one that we have consistency of payment for. And there are some small, I guess you could call them kickers or extra bonus kickers on some group or team-based atopic dermatitis volume growth and test volume growth. But again, given we have controlled this with a limited access perspective, it will remain sort of 100% melanoma focus with some atopic dermatitis sprinkled in.

We'll probably shift that to a 90%/10% here in the second quarter going forward. But again, still trying to control access so we can do 2 things. One of them is -- or 3 things actually. One of them is to maintain our focus and momentum on DecisionDx-Melanoma. Two is to make sure that as we see volume expanding, that our clinical laboratory and the logistics program of having to sort of have kits available with our buffer preservation in doctors' offices at the right time when patients walk in is -- continues to be a seamless process so that we don't have a frustration building up with our customer base in dermatology.

And then third was, of course, making sure that we watch the sort of line of ASP growth. And as we see our ASP growing along our models, then we'll go ahead and release this to more and more customers. But I would concur with you that you're seeing a high level of awareness and enthusiasm among your physician panel that is what we're seeing, too, in terms of enthusiasm.

And our next question today will be from the line of Puneet Souda with Leerink Partners.

This is [ Carlos ] on for Puneet. I've got 2 about TissueCypher. The first one is if you could just give us an update on the sales reps and their activity. I think last we checked, there were 65 reps and then you got a couple more from Previse. Do you see yourself expanding the reps more this year? And just generally how they're contributing to the growth of that account?

So we continue to add to the TissueCypher sales team, and we'll continue to do so over the course of the year as we see territories reaching volume levels that we think is difficult to sort of maintain a balance between maintaining and growing volume within existing customers as well as hunting for new customers.

We think both dermatology and the GI specialties shouldn't require more than 100 sales reps. And so as we sort of see volume come in, we will sort of be marching in a methodical fashion towards trying to get below that number would be higher than before. So that's kind of where we're sitting throughout the -- where we are now and throughout the remainder of 2026, that was the comment, right? Yes.

Okay. And one more on TissueCypher. So you talked a bit last year about an opportunity to penetrate into private equity roll-ups. And it would be helpful to get an update on whether that's something you're executing on that's been driving the, frankly, really incredible growth you've been seeing. Is that still an opportunity that can drive a step-up of growth in the future? Or is it something that after some research, you decided to focus your efforts in other areas?

Great question there. So one, as you look at volume in 2026, including fourth quarter volume, I don't think you or we would be able to discern back the impact on sort of group practices or even PE groups adopting a sort of more formulamatic approach to saying, "Hey, we want to go ahead and treat Barrett's esophagus patients regardless of which GI is treating that patient in a parallel manner." So we have seen some success in some smaller groups that would suggest as we go through 2026 that we would be able to go ahead and tackle and improve efficiency among larger groups. And so that may contribute to some volume expansion in 2026.

But I think the volume expansion, both year-over-year and quarter-over-quarter growth in TissueCypher in 2025 was largely based on just the organic need of individual clinicians seeing the value of this test clinically and deciding to go ahead and try it and then adopt it for their patient care.

Got it. That makes sense. If I could just sneak this in. So this isn't something though that you formally adopted the strategy? Or is it a strategy that you've decided to not formally adopt, focusing on the [indiscernible]

No, I'm -- I'm sorry if I inadvertently ignored your question directly. There is interest in large group models, whether you want to call it PE groups only or just larger practices of gastroenterologists to say, "Hey, we should be treating Barrett's esophagus disease uniformly for quality standards and good patient care as opposed to one-offs."

And so that is an important strategy that we have across the gastroenterology sales force, our strategic accounts team to say, hey, how do we move practices from being individual clinicians or responsible for individual patients to saying, this is a test which has clearly shown it finds people at high risk for disease progression. And we do know that if you go ahead and use interventional tools, be it ablation or ablation with surgical techniques as well that you can basically remove that Barrett's esophagus disease. And if you remove it, it does not progress to esophageal cancer.

So we know we can cure or stop patients from progressing to cancer if we know who to intervene on. And that's a very attractive commentary in terms of why should the survival of me as a patient be any different than Frank Stokes because I see a different doc than he does. So I think we will see the success that we're beginning to go ahead and believe we will feel come to fruition in 2026. So it's definitely a strategy that we're looking to continue to develop, I guess, you would say.

Next question today will be from the line of Matthew Parisi with KeyBanc Capital Markets.

This is Matthew Parisi on for Paul Knight at KeyBanc Capital Markets. First off, congrats on the great quarter. So just a quick question to begin would be around volumes for melanoma. I know you guys did not provide volume guidance, but following 2 consecutive years of high single-digit volume growth for the melanoma test, would it be reasonable to assume continued high single-digit volume growth for '26?

Frank, do you want to handle that?

Yes, yes. Thanks for the question. I think we're going to see mid- to high single digits volume growth in melanoma this year as well. We're in a very nice penetrations level there with 32% maybe of the patients being tested now. And we think something over half the physicians, maybe even 60% of the targetable physicians or clinicians are using the test regularly. So we'll continue to see that same level of growth we would expect this year.

And then just one more would be -- I'm not sure if I missed it earlier, but of the roughly 100 kind of sales force team, could you give some insight into the split between derm and GI? And what would the kind of percentage?

Yes. We do not disclose the number of reps in each sales force. What we've said is that we think each sales force can be well managed at fewer than 100 reps. So we -- I think back in, gosh -- April of '25, we said that the TissueCypher sales force had been expanded to 64. And I think we said last year also the dermatology sales force was in the 70s. So we're still in those vicinities. We will make expansions, as Derek highlighted earlier this year to accommodate our continued growth, but we think we can run both sales forces under 100 for some time here.

Your next question will be from the line of Catherine Schulte with Baird.

This is [ Josh ] on for Catherine. And maybe first, could you share your expectations for TissueCypher volume growth in '26? Do we expect this to come more from further penetration within your existing ordering base or adding new clinicians? And then where are you from a clinician penetration perspective?

Yes. I think last year, we said for '24. Go ahead, Derek.

No, no. You go, you go.

Yes. So I think for '24, we said we had something over 1,000 new ordering physicians in '24 and then for '25, something over 2,000. So those 2 data points together get you to 3,000 clinicians, which is probably, we think, again, similar to derm, which is part of the appeal to the therapeutic area for us. But it looks like there's 12,000 to 14,000 targetable clinicians in the GI space. So we're probably 25%, 30% penetrated in the clinician or HCP level penetration.

And I think if you just take the best numbers we have on a patient basis, we're about 11% penetrated. So clearly, we continue to expect volume growth this year, probably something close nominally to the growth we saw just on a nominal test basis for '24 -- for '25 rather into '26. We are getting into the larger numbers. So the percent growth becomes -- the hurdle becomes a bit higher and you're into the later adopter physicians. But yes, we should see continued volume growth and maybe not quite the percentages we've seen in '24 and '25, just given where we are penetration-wise, but continue to see strong growth from a volume perspective on TissueCypher for the year.

Great. And then I was also wondering if we should expect quarter-over-quarter declines for DecisionDx-Melanoma volumes in 1Q? And then how should we think about the cadence of year-over-year volume growth throughout '26, just given some of the tougher year-over-year comps in the back half?

Yes. melanoma has got just very -- it's very predictable seasonality. And what we see is flattish sequential growth each quarter, except Q1 to Q2. And it's driven -- it's really driven primarily by physician encounters, physician patient encounters. And it's a little different than just business days. Q1, there are a number of -- there are a couple of large derm meetings that take place in Q1 that take physicians out of their practice. So that reduces the patient encounters. And we've talked before, 100 tests one way or the other is still flattish on a basis of 10,000-plus tests.

So that's the pattern we've seen since 2021, coming out of COVID, we've seen that pattern very consistently. And so you kind of have flattish sequential growth until you get Q1 to Q2. That tends to be your step up and then that new level or new stepped-up level is durable through the next several quarters. So we would expect the same flattish performance. You can really look at the volumes we disclosed each year back to '21 and see pretty predictably what volumes look like Q4 to Q1.

The next question will be from the line of Mason Carrico with Stephens.

Derek, could you give us your latest thoughts on the commercial strategy for the derm team if we were to see a positive draft LCD get published midyear for DecisionDx-SCC. I guess how are you thinking about splitting reps time between Melanoma, SCC and your AD test now if that were to play out?

Yes. That will be a very, very nice problem to have, Mason won't it? So I think, there are a couple of variable triggers there, right? So having the reconsideration request resulting in LCD, which kind of covers it the way it was covered before by Novitas, let's just assume that's the base case. I would say that we would begin to go ahead and fold SCC back into the sales bag from a commission standpoint, although we have to watch for timing. It may be up to a year before you would see SCC gain reimbursement. I think, we talked about in previous years that if we see limelight to regaining coverage, then the question will be, do you want the run rate for that test to be $25 million a year? Do you want it to be $100 million a year? So there are some interesting trade-offs to go ahead and think through there.

We think that it's probably difficult to have 3 tests being sold extremely well by the same person, the same customer base. And so if we're faced with that wonderful opportunity or problem, I guess, depending on what you'd say, if we are seeing what we like in terms of the reimbursement growth for the AdvanceAD test, then we could come around and say we can profitably maybe expand our sales forces to go ahead and make sure we can handle all 3 opportunities, DecisionDx-Melanoma, AdvanceAD and the regaining of coverage for DecisionDx-SCC.

So I think we'll have to see kind of how those latter 2 things come out, the SCC draft timing, how confident we are about will that be finalized in 3 months or will it take a year? And then also our sort of climb in AdvanceAD for atopic dermatitis and come to some decisions there. But otherwise, that's been part of our planning about how we approach that, and there's a few different variables there, but it will represent a very, very nice opportunity for patient care and for the company overall.

Got it. That's helpful. And then would you remind us when NCCN typically updates guidelines for SCC? And what new data, I guess, were you able to submit ahead of that panel meeting that maybe previously wasn't submitted or previously wasn't reviewed in last year's update?

Yes, it's a good question. I might be off on the facts here, so I'll send that -- say that caveat here. I believe the submission that would have gone in last spring included our 2 papers for showing the benefit to predicting adjuvant radiation therapy responsiveness. Those papers are published, I think, in mid-2024, the third quarter 2024. So they missed the 2024 cutoffs. Those have been submitted last year. Their annual in-person meeting is usually around the Mohs Surgical Meeting in May of each year. So if they're kind of doing a 1-year cadence of updating guidelines, maybe that comes out between now and call it, late April or May will be the timing I would expect to see.

Thank you. This will conclude the Q&A for today. And I would now like to hand the call back to Derek Maetzold for any closing remarks.

So this does conclude our fourth quarter and full year 2025 earnings call. We do thank you again for joining us today and for your continued interest in Castle Biosciences.

Thank you. This concludes today's conference call, and you may now disconnect your lines.

Good afternoon, and welcome to Castle Biosciences' Third Quarter 2025 Conference Call. As a reminder, today's call is being recorded.

[Operator Instructions] I would like to turn the call over to Camilla Zuckero, Vice President, Investor Relations and Corporate Affairs. Please go ahead.

Thank you, operator. Good afternoon, everyone. Welcome to Castle Biosciences' Third Quarter 2025 Results Conference Call. Joining me today are Castle's Founder, President and Chief Executive Officer, Derek Maetzold; Chief Financial Officer, Frank Stokes; and Senior Vice President, Medical, Dr. Matthew Goldberg, Board-certified dermatologist and dermatopathologist.

Information recorded on this call speaks only as of today, November 3, 2025. Therefore, if you are listening to the replay or reading the transcript of this call, any time-sensitive information may no longer be accurate. A recording of today's call will be available on the Investor Relations page of the company's website for approximately 3 weeks following the conclusion of the call.

Before we begin, I would like to remind you that some of the statements made today will contain forward-looking statements, including statements about expected addressable market, statements containing projections regarding future events or our future financial or operational results and performance, including our anticipated 2025 total revenue and the impact of our investments and growth initiatives, including our ability to achieve long-term growth and drive stockholder value. Forward-looking statements are based upon current expectations and involve inherent risks and uncertainties, and there can be no assurances that the results contemplated in these statements will be realized. A number of factors and risks could cause actual results to differ materially from those contained in these forward-looking statements. Please refer to the risk factors in our most recent SEC filings for more information. These forward-looking statements speak only as of today, and we assume no obligation to update or revise these forward-looking statements as circumstances change. In addition, some of the information discussed today includes non-GAAP financial measures such as adjusted revenue, adjusted gross margin and adjusted EBITDA that have not been calculated in accordance with U.S. GAAP. Reconciliations of these non-GAAP financial measures to the most directly comparable GAAP financial measures are presented in the tables at the end of our earnings release issued earlier today, which has been posted on the Investor Relations page of the company's website.

I will now turn the call over to Derek.

Thank you, Camilla, and good afternoon, everyone. Today, I would like to start with some exciting news. Earlier today, we announced the launch of AdvanceAD-Tx, our first-in-class test designed to guide systemic treatment selection for patients with moderate to severe atopic dermatitis.

Before I get into our test, let me talk about the critical need facing patients with moderate to severe atopic dermatitis. Generally, patients with moderate to severe atopic dermatitis have spent, in many cases, years on topical therapeutics and have reached the point that they are ready to cross the threshold of switching to an advanced systemic therapeutic. There are also patients who are already on an advanced systemic therapeutic but continue to experience significant symptoms.

Today, there are 2 general classes of advanced systemic therapies. Biologic therapies that primarily impact the Th2 pathway are those that broadly inhibit multiple pathways, including the Th2 pathway. This latter class of drugs are known as Janus kinase inhibitors or JAK inhibitors for short. All of these systemic therapies require prior authorization for initiation of a prescription. They are expensive, and they carry -- as do all therapies, the potential for adverse events.

The question facing these patients and their clinicians is which class of therapy is going to be more effective for that individual, that specific patient? We know from longitudinal prescription data that most patients start in a Th2-targeted biologic therapy today. And while these work well on many patients, around 40% to 45% of patients require adding on additional therapies or switching altogether. This lines up with data from studies that have shown anywhere from 20% to 50% of atopic dermatitis disease is driven by both Th2 and additional immune dysregulation pathways, such that a Th2 targeted therapy may not address all of the molecular underpinnings that are driving that patient's unique disease.

We conducted a prospective study across 49 U.S. clinical study sites to see if we could identify a test for use in patients ages 12 and older with moderate to severe atopic dermatitis who may exhibit differential responses to 1 of these 2 therapeutic classes based upon the underlying biology that drives their disease and drives their symptoms. And we were successful. Specifically, we discovered, developed, and validated a gene expression profile test that evaluates the expression of 487 genes that are spread across 12 known immune inflammatory and skin-related pathways that are associated with inflammatory skin conditions, such as atopic dermatitis.

So let's talk about what we found. This initial validation study identified patients with a JAK inhibitor responder profile and those who have a Th2 molecular profile. In patients with a JAK inhibitor responder profile, study data showed that these patients who were treated with a JAK inhibitor were significantly more likely to achieve a 90% improvement in their baseline disease severity, as measured by the Eczema Area and Severity Index scale, also known as EASI, achieved complete clearance on the validated Investigator Global Assessment scale, report no itch and remain flare-free by 3 months, compared to JAK inhibitor responder patients who were treated with a Th2 targeted therapy. What a great step forward in improving patient outcomes.

This is a new opportunity in atopic dermatitis for our dermatologic clinician customers and their patients. I cannot express how grateful I am to our clinical investigators, to our clinical research department, our scientists and bioinformatics colleagues, and all those who are able to bring forward an objective test that will potentially enable for the first time the implementation of precision medicine in the management of atopic dermatitis.

So let's turn to the market size and our approach to clinical availability over the next 6 to 12 months. First, on sizing. Using multiple data sources, focusing on 1-year prevalence, we estimate that there are approximately 13.2 million individuals who are ages 12 and older with moderate to severe atopic dermatitis in the U.S. Using a reasonable ASP at maturity, we estimate that this target patient population represents an approximately $33 billion total addressable market opportunity in the U.S. alone.

With our established leadership in dermatologic testing, we believe that we are well positioned to introduce and scale AdvanceAD-Tx efficiently by leveraging our existing laboratory, logistics and commercial infrastructure. Excitingly, our qualitative market research and physician feedback have been very encouraging. Specifically, approximately 80% of clinicians sampled stated that they would definitely or probably use AdvanceAD-Tx, highlighting the value of matching treatments to immune profiles. Addressing this unmet need, our goal with AdvanceAD-Tx is to enable stronger responses, fewer relapses, faster improvement in symptoms, improved quality of life, and ultimately reduce health care costs.

Finally, let's turn to reimbursement. We are pursuing multiple pathways to accelerate patient access to AdvanceAD-Tx, recognizing that we're effectively building a new market and must evaluate all available options. We expect revenue contribution to be immaterial in 2026, as we build our reimbursement from ground zero. We expect to keep you informed of updates as appropriate. This being said, between models of reimbursement, the large market opportunity and the fact that our dermatology commercial teams will be introducing our AdvanceAD-Tx test to the same customers who use our DecisionDx-Melanoma and DecisionDx-SCC test, we will clinically launch AdvanceAD-Tx on a limited access model this month, November 2025, and expect to expand in a phased manner throughout 2026, in part, so our commercial team can primarily focus on our DecisionDx-Melanoma test.

In summary, the launch of AdvanceAD-Tx marks another important milestone in expanding our commitment to as well as expanding the value that we bring to our dermatological customers.

Now I will walk you through business highlights from the third quarter, and then Frank will provide additional financial highlights before we turn to your questions.

I'm pleased to report that the momentum we established in the first half of the year continued into the third quarter. We believe our outstanding third quarter performance underscores the strength of our operating model, the success of our strategic initiatives and their un-wavered commitment to improving patient care. Revenue reached $83 million. And we delivered total test report volume of 26,841, with tests for our core revenue drivers growing 36% compared to the third quarter of 2024.

For DecisionDx-Melanoma, we delivered 10,459 reports in the quarter, representing a 12% year-over-year increase. Notably, DecisionDx-Melanoma achieved another significant milestone by surpassing 10,000 reports in a single quarter for the first time in the company's history. We reiterate our previously provided expectation to deliver high single-digit volume growth for DecisionDx-Melanoma for the full year 2025 compared to the full year 2024.

Moving on to our DecisionDx-SCC test. We delivered 4,186 test reports in the third quarter of 2025. This high level of volume was achieved without proactive marketing, which we believe underscores the core clinical value and strength of our growing clinical evidence supporting the test. We submitted LCD reconsideration requests early in the third quarter to both Novitas and Palmetto MolDx and received notification from both Medicare contractors that based upon CMS guidelines our reconsideration requests were determined to be valid requests and were accepted as such. I'll remind you that this is not an indication of likelihood of coverage. And there is no specified time line for a final reconsideration decision.

During the quarter, we were pleased to see new peer-reviewed evidence, further validating the clinical utility of our DecisionDx-SCC test. One study expands on the clinical value or utility of our DecisionDx-SCC test by adding a third use predicting local recurrence in NCCN high-risk SCC patients. This use builds on the tests established capabilities of predicting metastatic risk and response to adjuvant radiation therapy, making DecisionDx-SCC an even more comprehensive test for postsurgical management. Additionally, the study showed that DecisionDx-SCC significantly outperformed both the American Joint Committee on Cancer, or AJCC, and the Brigham Women's Hospital, or BWH staging Systems in stratifying risk for local recurrence and metastasis in the NCCN high-risk patient group. This study demonstrates the superior risk stratification power of DecisionDx-SCC compared to traditional staging methods.

A separate study of 244 clinicians was also published in the third quarter. Results from this study showed strong alignment between DecisionDx-SCC risk classes and clinical decision-making. Specifically, Class 2A and 2B results were consistently used by physicians to drive management decisions for use of imaging and adjuvant radiation therapy with use that is similar to clinical and pathologic factors that are deemed very high-risk factors by staging systems and recommended by national guidelines for decisions to use these 2 interventions. Importantly, these findings reinforce the practice-changing impact that DecisionDx-SCC has had on patient care. By enabling risk-aligned escalation or de-escalation of care, DecisionDx-SCC helps clinicians personalize treatment strategies, avoid unnecessary overtreatment, and address the clear limitations of traditional staging systems. Our growing body of evidence underscores DecisionDx-SCC's critical role in improving patient outcomes and guiding treatment pathways for high-risk SCC while supporting smarter, more efficient health care decision-making.

Now let's turn to our gastroenterology franchise. TissueCypher delivered 10,609 test reports in the third quarter compared to 6,073 test reports in the same period of 2024, representing 75% year-over-year growth. TissueCypher, like our DecisionDx-Melanoma test, achieved a significant milestone this quarter by exceeding 10,000 test reports in a single quarter for the first time. And we believe this suggests clinicians are increasingly recognizing its value.

We remain highly focused on building education and awareness to drive continued adoption of our TissueCypher test. As such, we were very encouraged by new data presented at the American Foregut Society's Annual Meeting that reinforced the important role of TissueCypher in Barrett's esophagus management. In a real-world study from 4 surgical practices involving 85 patients with non-dysplastic Barrett's esophagus, TissueCypher identified 15% of patients as intermediate or high risk for progression to high-grade dysplasia or esophageal adenocarcinoma. By definition, these patients with non-dysplastic disease were not identified as high risk by pathology alone. Importantly, the probability of progression for patients receiving intermediate and high-risk TissueCypher scores was similar to or even exceeded the 5-year risk of progression associated with low-grade dysplasia. This is a critical finding because low-grade dysplasia is the threshold at which society guidelines recommend escalating care such as increased surveillance frequency or endoscopic eradication therapy.

These results underscore TissueCypher's ability to deliver clinically meaningful insights. By providing individualized risk stratification, the test enables physicians to escalate care for patients truly at risk while confidently deescalating care for those at low risk. This supports more personalized care strategies, helps to prevent overtreatment and improves the potential to intervene earlier in patients at the highest risk of progression.

Lastly, I want to thank each and every member of the Castle team for their continued hard work and unwavering commitment to improving patient care.

And with that, I will now turn the call over to Frank.

Thank you, Derek, and good afternoon, everyone. Reiterating Derek's sentiment, we're very pleased with our strong third quarter results and the continued positive momentum we are seeing with our business. Net revenues for the 3 months ended September 30, 2025, were $83 million. For total revenue for 2025, we are raising our revenue guidance to $327 million to $335 million, up from the previously provided range of $310 million to $320 million.

Our gross margin during the third quarter of 2025 was 74.7% compared to 79.2% in the third quarter of 2024. Our adjusted gross margin, which excludes the effects of intangible asset amortization related to our acquisitions and excludes the effects of revenue adjustments in the current period associated with test reports delivered in prior periods was 76.8% for the quarter compared to 81.9% for the same period in 2024.

Turning to expenses. Our total operating expenses, including cost of sales for the third quarter of 2025 were $89.8 million compared to $80.7 million for the third quarter of 2024. Sales and marketing expenses for the quarter were $32.8 million compared to $29.8 million for the same period in 2024. This increase is mainly due to higher personnel costs, higher expenses associated with travel and higher marketing expense.

General and administrative expenses were $23.1 million for the quarter compared to $20.7 million for the same period in 2024. This increase is primarily attributable to higher personnel costs and higher information technology-related costs. Higher personnel costs reflects headcount expansions in our administrative support functions as well as merit and annual inflationary wage adjustments for existing employees.

Cost of sales expenses were $18.7 million in the third quarter of 2025 compared to $15.6 million in the third quarter of 2024, primarily due to higher personnel costs, higher expenses for lab supplies and higher lab service expense. Increases in personnel costs reflect a higher headcount due to additions made to support business growth in response to growing test report volumes as well as merit and annual inflationary wage adjustment for existing employees. Higher expense for lab services and lab supplies also reflects higher test report volumes.

R&D expenses were $13 million for the quarter compared to $12.3 million for the same period in 2024, primarily due to higher personnel costs driven by increased headcount to support continued business growth. Total noncash stock-based compensation expense, which is allocated among cost of sales, R&D expense and SG&A expense was $12.1 million for the third quarter of 2025 compared to $13 million in the third quarter of 2024.

Our net loss for the third quarter of 2025 was $0.5 million compared to net income of $2.3 million for the third quarter of 2024. Diluted loss per share was $0.02 compared to diluted earnings per share of $0.08 in the third quarter of 2024. Adjusted EBITDA for the third quarter was $9.2 million compared to $21.6 million for the comparable period in 2024. This further demonstrates our ability to translate strong top line performance into meaningful bottom line results.

Net cash provided by operating activities was $22.6 million for the third quarter of 2025 and $37.4 million for the 9 months ended September 30, 2025. We continue to expect to deliver positive net cash flow from operations for 2025. Net cash used in investing activities was $69.2 million for the 9 months ended September 30, 2025, and consisted primarily of purchases of marketable investment securities of $151.3 million, purchases of property and equipment, our asset acquisition of prebuys and purchases of debt securities classified as held to market, partially offset by the maturity of marketable investment securities. As of September 30, 2025, we had cash, cash equivalents and marketable securities of $287.5 million. Our consistent top line performance, strong margin profile and disciplined expense management all contribute to our healthy cash position.

In conclusion, we delivered another exceptional quarter. And our strong year-to-date performance further reinforces our confidence in the strength of our business and growth opportunities ahead of us.

I'll now turn the call back over to Derek.

Thank you, Frank. In summary, our third quarter performance was strong. The momentum we built reflects our continued focus on strategic priorities, disciplined execution and commitment to delivering value for patients, clinicians and stockholders. Thank you for your continued interest in Castle.

Now we will be happy to take your questions. Operator?

[Operator Instructions] Our first question today will be from the line of Subi Nambi with Guggenheim.

Congratulations on launching the AdvanceAD. Could you provide more color on who would be addressable from the 13.2 million patients? And if it is all of them, how many of these patients are Medicare age?

So good to hear from you. This is Derek. Based on our calculations, the 13 million and change patients are the target marketplace in the U.S. of patients who have moderate to severe atopic dermatitis. That would be the largest denominator.

In terms of the Medicare exposure, we're estimating what, Frank, I think around 10% to 15%, maybe 15%, 20% max could be of Medicare age. So it's really a -- in our case, children above the age of 12 through sort of middle age and then there's another hump later on in life.

A quick follow-up. Could you tell us a little bit more about the multiple reimbursement pathways? What do you mean by that? Is it Novitas and MolDx? Or is it more to do with commercial or something else?

I think that certainly, this is a test that will result in more medically appropriate selections or recommendations by clinicians who are seeing Medicare patients. We have to understand what the commercial payment section might look like. There's also other payer opportunities, but we don't want to provide much more color than that at this point in time until we see how the next spring plays out.

The next question will be from the line of Kyle Mikson with Canaccord.

Congrats on the quarter. First one is going to be on SCC. So kind of a multipart question. The first is on the reconsideration. The requests were approved, I guess. Anything you can kind of share on timing and likelihood and next steps and things like that? I know it's obviously probably tough to get a handle of that.

Then secondly, the SCC volumes seem kind of flattish to down, let's say, quarter-over-quarter. But the gross margin for the company, it seemed to decline sequentially. So maybe what's happening there? I would have thought -- yes, some of the dynamics into gross margin and that kind of like debt cost volume is interested to hear.

I'll take the first couple; and do you want to handle the gross margin, Frank?

Yes.

So on the reconsideration request, the Medicare manual is pretty, I guess, straightforward and direct, which says if there's new -- I can't remember the exact words. But basically, if there's new clinical information that was not reviewed or considered as part of the kind of current LCD, whatever that LC would be in terms of how many years since it was issued or finalized. Then, a reconsideration request should be deemed as being valid if, in fact, there is new information that was not considered as part of the initial LCD.

So that sort of is the threshold there. And as we've talked about, I think, publicly now for quite some time. The fact that the open comment period is closed down in the -- I guess, the fall or 2023 in some cases. We had a significant number of new publications, new data coming out, including, of course, both of the seminal publications regarding the use of our tests or demonstrated our tests could predict responsiveness to adjuvant radiation therapy. So I think the evidence was there to go ahead and say these should be valid considerations. And in fact, they were deemed so by both Medicare -- by both Novitas and MolDx.

As it relates to timing, the Medicare manual or the [indiscernible] manual doesn't have any specific kind of start and stop dates. So that's really up to the working pace of either one of those contractors. So that's an unknown outcome, Kyle.

Regarding SCC volume, keep in mind that until the -- I guess, towards the end of the second quarter, our dermatology commercial teams were being focused or bonus, I guess, whatever you want to call that, roughly 50-50 on melanoma and squamous cell carcinoma. I think that we certainly know that these are promotionally responsive marketplace. That's why we have field forces against them.

We are working on those products. But we also know that these tests and this one in particular, the SCC test provides clinicians who are ordering the test with tremendous information that they realize they can't get elsewhere. So I'm not sure if the -- I mean, flattish to me is actually quite strong in terms of saying, if the volume went down tremendously, you would say, gee, there really wasn't much use of that clinically anyway. So the fact that we actually maintain close to the same volume, I think, is quite important from how our clinicians are using the test and adopting it for ordinary patient care.

Frank, do you want to...?

Yes. And Kyle, we did have some modest revenue in the quarter from some commercial claims on SCC, not really material. But there were some dollars there, which helps the gross margin line.

The next question is from the line of Catherine Schulte with Baird.

This is Tom Peterson on for Catherine. Congrats on a really solid quarter here. I wanted to ask a first question here on the DecisionDx-Melanoma volume outlook. 3Q volumes were up about 5% sequentially versus the guidance of kind of flattish in the back half versus 2Q levels. So I guess, what did you see in the quarter outside of typical seasonality? And then with that in mind, how should we think about the 4Q volume growth for DecisionDx-Melanoma given the reiteration of the high single-digit outlook for the full year?

So we had, I think, signaled or stated, I'm not quite sure what the word is. Early in the year with our guidance back in -- when was that given May or March, that we expected upper single-digit volume growth year-over-year in the melanoma test. And that was met with some head scratching, I guess, in some places in the world. But it looks like that's what's coming in at.

So we are running on our model, which is good for us from the standpoint of modeling accuracy. I don't think there was anything special in terms of third quarter to second quarter this year. We continue to have additional support from a medical communication standpoint at congresses and publications. We also had our dermatology sales force, of course, be switched over to, I think, either 95% or 100% focused on the melanoma test beginning in July of this year. So perhaps that quarter versus quarter lift was due to that complete focus on the melanoma test with the squamous cell test being service, I guess, you would say, versus being educated on.

In terms of fourth quarter, as you may recall, in years past, we typically see the fourth quarter to be flattish or down a bit to the third quarter in terms of normal seasonality. That's due to a combination, we think, of both holidays, both Thanksgiving, Hank and Christmas in the fourth quarter, shorter working days as a result of that, coupling that with people actually wearing pants and long sleeve shirts and hats on. So you sort of pick up less incidental melanoma or looking mold. So I don't think anything would tell us that we would expect something differently in the fourth quarter than what we've seen in the last 2 or 3 years. Is that correct, Frank?

Tom, are you still there, is there another question?

The next question will be from the line of Mason Carrico with Stephens.

So on DecisionDx-Melanoma, good acceleration there. Could you give us a bit more insight into how refocusing the derm team has had an impact? What are you seeing drive the majority of the growth, at least in Q3? Was it new ordering clinicians ramping up? Was it higher utilization among existing docs?

Yes, we see both avenues of growth. I call it same-store new store sales growth. We've seen both. We do continue to have new ordering physicians that convert and then we do try to penetrate deeper into their practices and into their patient base. So both areas were continue to grow for us. And as we said before, it's lots of room to go on that test yet. More physicians to penetrate for sure and then more patients that we'd like to see expand in individual practices.

Frank, any additional insight you can give on the guide update? I think the previous guide may have assumed non-DecisionDx-SCC revenue growing 21% to 26% this year. What does the guide imply now? And could you just clarify what DecisionDx-SCC did contribute in the quarter?

It was a kind of mid-single-digit millions, Mason, on SCC, not material, but we do see some commercial claims coming through on the test. So a modest contributor there. But as we said, we're expecting kind of high single-digit year-over-year growth in volumes on melanoma. I don't really model ASP improvement. We certainly continue to make some progress and hope to continue to make progress. But we really keep ASP advances as upside, just given the difficulty in predicting how and when they may come. And so yes, we're -- I would not assume continued SCC revenue. We're sort of assuming that falls off here just to be conservative.

The next question today is from the line of Puneet Souda with Leerink Partners.

You have Michael Santa on for Puneet. Congrats on the quarter. I just wanted to ask one on TissueCypher. So it looks like you're approaching roughly double-digit market penetration. I was kind of wondering if you could offer some insight on the penetration of physicians in that market? And how you expect the momentum to look, I guess, as you're rounding out the year heading into 2026?

So we haven't necessarily disclosed this quarter, not last quarter, I guess, number of ordering clinicians in the U.S. I would say we are still in the, obviously, early growth phase there, both from a penetration of patients being diagnosed by gastroenterologists plus number of gastroenterologists who are adopting our test across the board. So I think both areas, as Frank said, same-store new store sales is on the upswing for TissueCypher. Keep in mind that based upon third-party data, we think there's what, roughly 420,000 patients diagnosed each year with Barrett's esophagus that could be potentially benefiting from our test. So there is a nice long way to go to get to 105,000 tests a quarter if that was fully penetrated. So I think that reflects upside.

Regarding the other part of your question, Frank, do you want to?

Are you just looking for where we kind of where we think the test is going to go penetration-wise?

Yes. I guess there's any color if you see potential for, I guess, similar market penetration rate into 2026, or if there's anything like a broader awareness or any sort of guideline or coverage wins that you think could potentially drive an acceleration?

I'm not aware of any guideline activity going on that would impact it.

Yes. I'm not sure how much that would drive market share upward. I think it really is more about continuing to educate the marketplace and accessing our customers at the right frequency and new customers at the right level. They appreciate the value of ordering a test like TissueCypher to help guide patient care decisions about do I go ahead and watch and wait and have this patient back every 3 to 5 years or I have to have it back every 6 months or 1 year? Do I go ahead and even intervene and eradicate the Barret's esophagus lesion. So I just think we're seeing early upswing -- from a modeling standpoint, as Frank had said last quarter, I would not go ahead straight-line growth percentage. As our denominator gets bigger, we would expect to go ahead and see the percent growth be lower. But I think that there's a lot of upside, obviously, in getting patients the kind of care they deserve.

The next question is from the line of Mark Massaro with BTIG.

This is Vidyun on for Mark. So I have one on DDM. I think you're pursuing FDA approval there. Could you just educate us on if there's any upside to your current Medicare rate as a result of that FDA approval? And just remind us of the timing of when you're expecting that?

You're talking about our DecisionDx-Melanoma test, correct?

Yes, correct.

Okay. So I thought, want to double check. So we are preparing the application following the achievement of breakthrough designation status earlier this summer. Our intention -- our rationale for doing this, number one, is because it's our option as opposed to be forced to that to provide some benefits to us from a review standpoint.

In terms of upside potential, I don't see this changing our Medicare rate, because as an ADLT through the novelty route as opposed to through the FDA approval route, we sort of already there, I think. So I wouldn't bake that into a benefit. What our hope in pursuing this line, not only with the melanoma test, but looking at our other tests as well is that there are these state biomarker laws that many of us have talked about in the industry for the last couple of years that I think are covering more than 25, maybe less than 30 states so far and more likely going forward. And while those biomarker laws have not proven yet to be the -- to have the impact that they were meant to have by the state legislatures.

Our belief is that over the next couple of years, we're going to see improved enforcement amendments, I guess, to these current laws and regulations such that insurance carriers will be having to follow in Hawaii to do the right thing and follow the intent of these biomarker laws in the first place. And one of the core elements of I guess you would say, coverage under the majority biomarker laws is your test FDA cleared or approved. And so that's our hope is that downstream, not immediately in, call it, '26 or '27, but maybe towards the end of the decade, not only Castle, but others of those who are pursuing an FDA route towards our test will begin to go ahead and reap the benefits of having commercial payers actually stand up and actually reimburse us fairly.

Perfect. Then I just had one follow-up on TissueCypher. Could you just remind us of what your current sales force there stands at? I think it was 65 reps that you may have added since then. And then I'm just curious, you put up a record quarter for TissueCypher. So did you realize any benefit from that prebuys acquisition that you did a couple of quarters ago? I think it was kind of an adjacent technology. Yes, I'll stop there.

Yes. There was no impact on TissueCypher from Prebuys in the quarter. And we have -- on the sales force side, for competitive reasons, we're not giving specific numbers going forward. But what we've said is that we think these therapeutic areas can be targeted with sales forces of under 100 people. And we still think that is the case in NGI.

The next question today is from the line of Thomas Flaten with Lake Street.

A couple of quick questions. One on Advance-Tx. Have you guys just by chance had any engagement on the biopharma side with the manufacturers of JAK inhibitors? I can see there being a strong interest on their part in ensuring that patients get tested appropriately more so than maybe the Th2 therapies.

Yes. We aren't going to comment a whole lot there. I think as you would expect, though, Thomas, that there should be a natural synergies between being able to identify patients who may get a better response versus a less and better response. So we'll see how those kinds of interactions would benefit today. And of course, the initial version, we didn't quite call it version 1.0, but call it 1.0 was really focused on the data that we presented in the press release plus the accompanying corporate presentation on atopic dermatitis.

Going forward, as you know, from Castle, we are continuing to invest in studies and the atopic dermatitis field is no less. We are hopeful. But we don't know, of course, right now that by having 487 genes sort of paper over these 12 different immune or skin-related pathways that we may be able to find signatures even for other classes of therapies or even potentially specific drugs themselves, depending on how unique there kind of action is. So there's opportunities, I think, not just near term, but also midterm to go ahead and improve the utility of our test beyond this initial area, which is personally fantastic to me.

Then finally, I know you get asked this every quarter. But philosophically, on SCC, you're going to continue accepting orders and processing those for the foreseeable future. Is there any trigger that would cause you to no longer accept orders for SCC at this point?

I don't see one right now unless there's some really bad actor playing by the Medicare contractors and even then we'd have to take a really thoughtful internal discussion. We have always believed that if we are developing or acquiring in some cases, a high-complexity assay like our squamous cell carcinoma test. Being in the health care business, we should be offering that test clinically for advancing patient care. And a sort of interim or intermediate blip in sort of the reimbursement landscape would be a terrible way to run a business and say we're going to yank it away from our patients because of a couple of contractors' decisions that we think weren't necessarily in the best interest of patient care. So I don't think there's any short-term trigger like that per se. We're aware of that.

Do you want to add to that, Frank?

I think that's it.

With no further questions in the queue at this time, I'd like to hand the call back to Derek Maetzold to give closing remarks.

Thank you, Harry. This concludes our third quarter 2025 earnings call. Thank you again for joining us today and for your continued interest in Castle Biosciences.

This concludes today's conference call. Thank you all for joining. You may now disconnect your lines.

Good afternoon all, and thank you for joining us for the Castle Biosciences' Q2 2025 Earnings Call. As a reminder, this call is being recorded. We will begin today's call with opening remarks and introductions, followed by a question-and-answer session.

I'd now like to turn the call over to Camilla Zuckero, Vice President, Investor Relations and Corporate Affairs. Camilla, when you're ready.

Thank you, operator. Good afternoon, everyone. Welcome to Castle Biosciences' second quarter 2025 results conference call. Joining me today are Castle's Founder, President and Chief Executive Officer, Derek Maetzold; and Chief Financial Officer, Frank Stokes.

Information recorded on this call speaks only as of today, August 4, 2025. Therefore, if you are listening to the replay or reading the transcript of this call, any time-sensitive information may no longer be accurate. A recording of today's call will be available on the Investor Relations page of the company's website for approximately 3 weeks following the conclusion of the call.

Before we begin, I would like to remind you that some of the statements made today will contain forward-looking statements within the meaning of the Private Securities Litigation Reform Act of 1995. These forward-looking statements include, but are not limited to, statements about our financial outlook, TAM, intended use populations and similar items referenced in our earnings release issued today and statements containing projections regarding future events or our future financial or operational results and performance, including our anticipated 2025 total revenue, our expectations regarding reimbursement for our products, opportunities for growth, the clinical value of our tests, impacts of seasonality and other trends, the timing of targeted milestones, our M&A strategy, our ability to capitalize on strategic opportunities, including our recent SciBase and Previse transactions and the impact of our investments in growth initiatives, including our ability to achieve long-term growth and drive stockholder value.

Forward-looking statements are based upon current expectations and involve inherent risks and uncertainties, and there can be no assurances that the results contemplated in these statements will be realized. A number of factors and risks could cause actual results to differ materially from those contained in these forward-looking statements. These factors and other risks and uncertainties are described in detail in the company's annual report on Form 10-K for the year ended December 31, 2024, and its quarterly report on Form 10-Q for the quarter ended June 30, 2025, under the heading Risk Factors and in the company's other documents and reports filed or to be filed with the Securities and Exchange Commission. These forward-looking statements speak only as of today, and we assume no obligation to update or revise these forward-looking statements as circumstances change.

In addition, some of the information discussed today includes non-GAAP financial measures such as adjusted revenue, adjusted gross margin and adjusted EBITDA that have not been calculated in accordance with generally accepted accounting principles in the United States or GAAP. These non-GAAP items should be used in addition to and not as a substitute for any GAAP results. We believe these metrics provide useful supplemental information in assessing our revenue and operating performance. Reconciliations of these non-GAAP financial measures to the most directly comparable GAAP financial measures are presented in the tables at the end of our earnings release issued earlier today, which has been posted on the Investor Relations page of the company's website. I will now turn the call over to Derek.

Thank you, Camilla, and good afternoon, everyone. Following a strong first quarter, our team closed out a very successful second quarter that was ahead of our expectations. We believe this strength reflects the clinical value our tests provide to clinicians and their patients. Thanks to the strong execution by the entire Castle team, we delivered revenue of $86.2 million and total test report volume of 26,574, with tests for our core revenue drivers growing 33% year-over-year compared to the second quarter of 2024.

Additionally, we are pleased to have maintained strong gross margins and a healthy balance sheet, ending the quarter with $275.9 million in cash, cash equivalents and marketable securities. This financial strength positions us well to continue investing in our near-term growth initiatives, including expanding our body of clinical evidence and commercial team optimization efforts, along with strategic investments and pipeline developments to support longer-term growth.

Today, I will walk you through business highlights from the second quarter, and then Frank will provide additional financial highlights before we turn to your questions.

On to our quarterly highlights. For DecisionDx-Melanoma, we delivered 9,981 test reports during the quarter, which resulted in a sequential increase of approximately 16% compared to the first quarter of 2025 and a year-over-year increase of approximately 4% compared to the second quarter of 2024. On an absolute number basis, this is the largest second quarter over first quarter sequential increase in volume for DecisionDx-Melanoma we have seen since our IPO in 2019.

We expect continued solid growth in the second half of the year. And as a result, we are reiterating our expectations for high single-digit volume growth for DecisionDx-Melanoma for the full year 2025 compared to the full year 2024.

Castle has invested in generating a substantial body of evidence to support the clinical performance and use of our DecisionDx-Melanoma test. We're particularly proud of our ongoing collaboration with the National Cancer Institute's Surveillance, Epidemiology and End Results Program Registries, or NCI SEER for short, which was initiated back in 2021 and continues to evolve. Prior studies have shown that clinicians use DecisionDx-Melanoma to inform both avoiding sentinel lymph node biopsy surgical procedures in low-risk patients and initiation of surveillance imaging and referrals to medical oncology in high-risk patients, which enables early detection of recurrences and earlier initiation of therapy.

Early detection has been shown to improve outcomes to a greater extent when therapy is initiated with a smaller metastatic tumor burden, which improves net health outcomes. In fact, during the second quarter, we presented novel research aimed at enhancing the clinical management of patients with cutaneous melanoma at the 2025 American Society of Clinical Oncology Annual Meeting. This NCI SEER study presented an updated matching of patients who received DecisionDx-Melanoma as part of their clinical care to those who did not. This large real-world cohort included 13,560 patients with cutaneous melanoma whose treatment plan was managed with the results of our DecisionDx-Melanoma test. This represents the largest real-world study of gene expression profile testing to date.

The clinical use of DecisionDx-Melanoma was associated with a 32% reduction in mortality risk compared to untested patients, meaning patients whose treatment plan did not include the use of our DecisionDx-Melanoma test. These results provide further evidence of our test association with improved patient survival.

Moving on to our DecisionDx-SCC test. We are very pleased with our volume performance, delivering 4,762 test reports in the second quarter of 2025. As a reminder, DecisionDx-SCC reimbursement for the second quarter reflects a Novitas Local Coverage Determination policy, or LCD, that went into effect for dates of service on or after April 24, 2025, and included noncoverage language for our DecisionDx-SCC test.

That said, early in the third quarter, we submitted our DecisionDx-SCC reconsideration request for both the Novitas and MolDx LCDs. Under CMS guidelines, MACs have up to 60 days to accept or reject a reconsideration request. Importantly, we have already received notification from Novitas that based upon CMS guidelines, our reconsideration request was determined to be a valid request and was accepted as such. We are still awaiting notification from MolDX. While this is not an indication of the likelihood of coverage, it is a step forward in the process. It's important to note that as is the case for development of a new LCD, there is no specified time line for a final reconsideration decision. We expect to keep you informed of updates as appropriate.

Now let's turn to our gastroenterology franchise. TissueCypher continued its strong momentum in the second quarter, delivering 9,170 test reports compared to 4,782 in the same period of 2024. This represents a 92% year-over-year growth compared to the second quarter of 2024. We continue to believe the growth drivers for TissueCypher in 2025 and beyond include, first and foremost, a recognition of the unmet clinical need; and two, continued commercial optimization, which includes a strong focus on education and awareness.

Lastly, moving on to our pipeline initiatives. In June, we entered into an exciting collaboration and license agreement with SciBase, a Swedish-based public company that focuses on advanced electrical impedance spectroscopy or EIS technology, which includes both desktop and point-of-care instruments. The initial goal of the collaboration is to advance the development of a diagnostic test that predicts flares in patients diagnosed with atopic dermatitis, a U.S. market with an estimated patient population of up to 24 million people. We expect that should our development program be successful, this test will enable us to meet another significant unmet clinical need for many of the clinicians who have already adopted our DecisionDx-Melanoma and SCC test for use in skin cancers.

Staying with this atopic dermatitis theme, I'm pleased to provide an update regarding our internally developed pipeline test. As we have talked about in the past, we have a program underway to see if our novel specimen collection technique, coupled with gene expression profiling would be successful in identifying a genomic signature that could predict treatment responses to patients who are diagnosed with moderate to severe atopic dermatitis and eligible for or seeking systemic therapy, be it an injectable biologic or an oral therapy. Based upon our analysis to date, we believe that our development program has been successful.

Specifically, we've identified a signature, which has been validated in an independent patient cohort that identifies patients who are likely to have strong relief from the atopic dermatitis symptoms, specifically in their response as measured by 3 core indexes: first is an improvement in their eczema area and severity index, or EASI score, as is known; second is improvement in itch symptoms; and third is a reduction in flares. Assuming continued success with our validation assessments, we expect to launch this pipeline test by the end of 2025.

Lastly, our Previse acquisition brings a robust technology pipeline, which has the potential to increase our current GI offerings. Specifically, we believe there is an opportunity to create a multi-omics approach for improved test value in Barrett's esophagus as well as a non-endoscopic sample collection device for pipeline opportunities to potentially expand screening and diagnostic support for patients with Barrett's esophagus and other GI diseases.

And with that, I will now turn the call over to Frank.

Thank you, Derek, and good afternoon, everyone. Reiterating Derek's sentiment, we are pleased to report strong second quarter financial results. Net revenues for the 3 months ended June 30, 2025, decreased by $0.8 million or 1% to $86.2 million compared to the 3 months ended June 30, 2024, due to a $12.5 million decrease in revenue from our dermatological tests, offset by an $11.7 million increase in revenue from our non-derm tests.

The $12.5 million decrease in net revenue for our dermatological test was primarily attributable to our DecisionDx-SCC test and the $11.7 million increase in net revenues from our non-derm test was largely attributable to our TissueCypher test. While we do not typically disclose revenue by test, we estimate that revenue from DecisionDx-SCC for the second quarter of 2025 was just above $15 million. If you exclude DecisionDx-SCC revenue from both the second quarter of 2025 and 2024, our normalized revenue growth for the second quarter of 2025 would be approximately 23%.

We are providing this information for this quarter due to the specific circumstances regarding DecisionDx-SCC noncoverage decision, which went into effect during the second quarter of 2025.

Adjusted revenue, which excludes the effects of revenue adjustments in the current period related to tests delivered in prior periods, was $86.2 million for the second quarter of 2025, a decrease of 1% compared to the second quarter of 2024.

For total revenue for 2025, we are raising our revenue guidance to $310 million to $320 million, up from the previously provided range of $287 million to $297 million, which reflects the DecisionDx-SCC LCD with a date of service effective date of April 24, 2025. Again, we do not disclose revenue by test, but for an apples-to-apples comparison for 2025 revenue growth, if you exclude DecisionDx-SCC revenue from both our '24 and '25 totals, our normalized revenue growth range in 2025 would be approximately 21% to 26%.

Our gross margin during the second quarter of 2025 was 77.3% compared to 80.7% in the second quarter of 2024. Our adjusted gross margin, which excludes the effects of intangible asset amortization related to our acquisitions and excludes the effects of revenue adjustments in the current period associated with test reports delivered in prior periods, was 79.5% for the quarter compared to 83.2% for the same period in 2024.

Turning to expenses. Our total operating expenses, including cost of sales for the second quarter of 2025 were $90.4 million compared to $82 million for the second quarter of 2024.

Sales and marketing expenses for the quarter were $35.1 million compared to $32.7 million for the same period in 2024. The increase is mainly due to higher organizational and business development activities costs and higher sales-related travel expenses.

General and administrative expenses were $22.9 million for the quarter compared to $18.4 million for the same period in 2024. The increase is primarily attributable to higher personnel costs and higher information technology-related costs. Higher personnel costs reflect headcount expansions in our administrative support functions as well as merit and annual inflationary wage adjustment for existing employees.

Cost of sales expenses were $17.6 million in the second quarter of 2025 compared to $14.5 million in the second quarter of 2024, primarily due to higher personnel costs, higher lab services costs and higher expenses for lab supplies. Increases in personnel costs reflect a higher headcount due to additions made to support business growth in response to growing test report volumes as well as merit and annual inflationary wage adjustments for existing employees. Higher expenses for lab services and lab supplies also reflects higher test report volumes.

R&D expenses were $12.8 million for the quarter compared to $14.1 million for the same period in 2024, primarily due to lower expenses for clinical trials.

Total noncash stock-based compensation expense, which is allocated among cost of sales, R&D and SG&A, was $11.2 million for the second quarter of 2025, down from $13.2 million in the second quarter of 2024.

Our net income for the second quarter of 2025 was $4.5 million compared to net income of $8.9 million for the second quarter of 2024. Diluted earnings per share was $0.15 compared to diluted earnings per share of $0.31 in the second quarter of 2024.

Adjusted EBITDA for the second quarter was $10.4 million compared to $21.5 million for the comparable period in 2025.

Net cash provided by operating activities was $20.8 million for the second quarter of 2025 and $14.8 million for the 6 months ended June 30, 2025. We continue to expect to deliver positive net cash flow from operations for 2025.

Net cash used in investing activities was $50.8 million for the 6 months ended June 30, 2025, and consisted primarily of purchases of marketable investment securities of $92.8 million, our asset acquisition of Previse, purchases of property and equipment and purchases of debt securities classified as held to market, partially offset by the maturity of marketable investment securities. As of June 30, 2025, we had cash, cash equivalents and marketable securities of $275.9 million.

As we look beyond prebuys and the license agreement with SciBase, we look to put the strength of our balance sheet to work through a disciplined and strategic approach to capital deployment, focusing on investing our capital for stockholder value. As it relates to M&A, our strategy is centered on complementing our existing portfolio to drive mid- to long-term value creation. In today's dynamic reimbursement environment, we consider diversification, expanding both our test portfolio and payer mix while also maintaining a disciplined approach with an aim to ensure any transaction supports near and midterm profitable growth.

Our key M&A priorities at this time include: one, pursuing opportunities where our test is already on the market and has established reimbursement; two, favoring tests that complement our current portfolio and/or offer high clinical value in adjacent therapeutic areas; finally, exploring areas where we can develop pipeline tests that enhance the value we deliver to existing customers.

In conclusion, I'm pleased with our excellent financial results in the second quarter, continuing our long-standing history of strong execution and performance excellence.

I'll now turn the call back over to Derek.

Thank you, Frank. In summary, we delivered another strong quarter and furthered our position as a leader in both our dermatologic and gastrointestinal testing franchises. We are excited about our performance in the first half of the year and believe our ability to create value for our stockholders in the near and long term remains intact. Thank you for your continued interest in Castle Biosciences.

Now we will be happy to take your questions. Operator?

[Operator Instructions] Our first question comes from Thomas Flaten from Lake Street.

Congrats on a great quarter. Just first, with the breakthrough designation you got for Dx-Melanoma just a few weeks ago, anything you can share with us on your plans to seek FDA approval studies, et cetera, just lay out kind of the bigger strategic thinking there?

Thanks, Thomas. Derek here. Yes, with the breakthrough designation device status approved or authorized, we are marching our efforts to go ahead and push forward towards an FDA submission. Timing of that, I don't think we need to make public at this point in time, but that's part of our expected outcome for that -- for seeking BDD in the first place.

Got it. And then, Frank, with the numbers that you kindly shared around SCC, it seems that kind of on an ASP basis, you may have gotten more than just kind of a 2/3, 1/3 split throughout the quarter. Are you getting paid on any of the volume that isn't Medicare at this point?

We get paid episodically on commercial claims, yes, not in significant percentages, but we do get some payments.

But remove that from our thinking going forward as consistent with prior guidance?

There will be some. It -- one of the challenges you have is just timing, Thomas. A lot of times that comes out of period. So sometimes you'll see that show up in prior period revenue. But yes, we'll have some modest payments. But again, it's not a significant percentage.

Our next question comes from Mason Carrico from Stephens.

I think you've historically talked about 6 months for a sales rep to reach average productivity. Could you give us some insight into how many GI reps had reached that level of tenure maybe at the start of Q2 as well as how many have now hit that threshold as of today?

I think we scaled to the current level of territories, I think, just before year-end. So they would have been certainly in training in the first quarter. So I would think as we're exiting into the third quarter now, and you would assume if our modeling was correct about 6 months to KPI will be up to full speed, we should be hitting that with a fully mature, I guess, you call that sales team in the third and fourth quarter of this year.

Okay. And now that -- well, I guess I'm assuming that the derm sales force is refocused on melanoma. Could you just give us some insight into kind of what you saw in terms of utilization trends once that shift happened and how that's progressed since?

I actually don't think I can from a data standpoint. As you know, with the LCD being effective April 24, however, there are some laboratory orders coming in and reports that were going out with the data service before April 24. So we didn't really make a hard shift until the end of the quarter anyways from sort of a compensation focus standpoint. And also the SCC test is important to our clinicians as well. So I think going forward, we can go ahead and see what the third and fourth quarter looks like from sort of a future modeling standpoint if they're solely focused on the melanoma test.

Our next question comes from Mark Massaro from BTIG.

Congrats on a good quarter, the beat and the raise. I wanted to start with your internal developed product for atopic dermatitis. It's nice to see that the program has reached sort of your internal hurdles. So now that you're planning or still on track to launch it by year-end 2025, can you just give us a sense for what the reimbursement outlook is for atopic dermatitis? Is this something where you're going to pursue an LCD? Or are there reimbursement mechanisms in place that you could benefit from?

So one is we are on track still and believe we'll have this test available clinically as appropriate on a limited launch basis by the end of the year so that I guess, when do we set that expectation, September 21, '22? Yes. So we're on track for that aspect. Reimbursement perspective, we have 3 or 4 areas we're pursuing in parallel. Not sure which will end up being the ones that will be the largest revenue drivers in reality, I'd rather not go into the detail right now until we see a couple of those mature out. But suffice it to say, we think there is substantial clinical value to a patient going from sort of a standard of care approach, which is trial and error sounds negative. It's basically trial and trial to saying, hey, if your symptoms are severe enough where you are looking at going from topicals only and taking that step across the transit to systemic therapies, why wouldn't you want to, given the cost of those therapies in the case of Dupixent, the need for injection versus oral, why wouldn't you want to understand when you make that significant upstep in terms of therapeutic efficacy as well as side effects as well as cost, want to have your patients understand that they can select test -- they can use our test to go and figure out that this patient is more likely to be a very, very strong responder to JAK inhibitors versus not. So that's quite exciting from our standpoint. But because of that, I think reimbursement has a couple of options there to go forward.

From a modeling standpoint, I would say starting out at the end of this year, I think revenue driving impact is immaterial for 2026 because it's just launching. So this is more, I think, smooth the '27, '28, '29 as we see how '26 matures.

Okay. Great. And my second question, your squamous cell carcinoma volume certainly exceeded my expectations. And I recognize that the noncoverage decision went live in April. So I think on the last earnings call, you talked about how you plan to continue to offer the test. And so recognizing that you've submitted your reconsideration request for Novitas and MolDX, should we continue to expect you to continue to offer it perhaps until a time that you hear back from the reconsideration request? Is that the right way to think about it?

Yes. So we are -- we certainly expect over the next couple of quarters to have volume moderate down as we aren't focusing educational sales efforts on that test specifically. We aren't looking to remove the test from the marketplace. I think we built Castle Biosciences to be, first and foremost, focused on developing innovative tests that make a significant clinical difference in the lives of our patients or the patients that our doctors are treating. And this is no exception. I think this LCD process that we've talked about in the past is quite disappointing from a patient care perspective, given that Novitas was quite quick in their turnaround is accepting our reconsideration submission as valid. I think that gives us expectations here to move forward, even though, of course, that's a beginning of a reconsideration process. So I wouldn't see us removing SCC from marketplace in any time in the short-term. I think it's the right patient care decision to keep it available. That will have some moderating impact on COGS, I guess, you would say, gross margin perhaps, but that's -- I think at the end of the day, what we think is right for patients, which means it's right for Castle.

Okay. If I can sneak one last one in. One for you, Frank. It looks like you beat consensus by about $15 million in Q2 on revenue. You raised, I think, the midpoint of the guide by $23 million. Can you just give me a sense for the drivers in the back half of the year and perhaps remind us about any seasonality between Q3 and Q4?

Yes. So on melanoma, as we've said, each quarter, we see seasonal flatness typically from Q2 to Q3 and Q3 to Q4. And so that's been the historical trend, and that data is in our MD&A that you can see there. But other than that, we're seeing good strong drivers across the business and accordingly, we raised our guidance accordingly.

[Operator Instructions] Our next question comes from Puneet Souda from Leerink Partners.

First one on TissueCypher. Strong growth there in the quarter. Just wondering how we ought to think about the cadence of volume growth here, third quarter, fourth quarter. And wondering if you're willing to provide anything in terms of 2026 for that.

We're not going to -- maybe last first.

Not yet. We haven't provided any insight into '26 yet. But yes, we agree, good continued growth in that test volume trends.

Okay. Just -- but in terms of the overall guide for this year, any context you can provide there in terms of the volume growth we ought to think about? [ Purchase appraisal... ]

I'll give a try, Puneet. We -- our guide does assume continued growth in volumes in TC. We expect at some point to hit seasonality with that test. But right now, we're still just very underpenetrated. And so we don't yet see seasonality in it.

Got it. Okay. And then I appreciate the details on the reconsideration request, the 60 days. Could you elaborate when do you expect exactly to hear back from MolDX? And what was submitted this time around in the reconsideration request package? It seems that you have an expectation of positive outcome. Please remind me, I mean, if I'm incorrect on that. But -- and tell us how you're thinking about the sort of the overall timing for MolDX. And then if it was, again, the reconsideration request was turned down, what would be the other avenues at this point in time?

So I'll maybe take a step up and answer the question here. So one is that we submitted a reconsideration request to both Novitas and the MolDX group. Novitas was quite speedy in terms of turning around an acknowledgment or statement that they accepted the reconsideration submission as valid under CMS guidelines, which we expected, by the way. The Palmetto request went in at the same time, I think, maybe the same day, the next day of April, something like that earlier in July. Under CMS guidelines, MACs have up to 60 days to take to acknowledge receipt as being valid or not valid. We haven't heard back anything yet, which is I think what we signaled maybe on the script. So I'd expect to hear back towards sort of within by Labor Day time period, I think, would be the right timing of that. So that's my expectation.

In terms of the package that went in, we certainly aren't going to post it I think the actual package. But if you go and dial back, you may recall that when those draft LCDs posted in the summer of 2023 once the open comment period closed for both Novitas and for Palmetto, neither one of them were under any obligation to cite any published evidence or literature that had a publication date after the close of open comment period. I think it was maybe August and then maybe early September 2023, respectively. So since that time period, we had, I think, 8 or 9 or 7 or 8 peer-reviewed publications come to fruition. I think one set or a couple of them essentially dealt directly with questions or comments that MolDX had asked us about in the draft LCD. So those are -- those were published in the interim. We did send those to MolDX, but they were not reviewed because they don't have to review things after the close of comment period.

We also published 2 studies that were multicenter in nature, demonstrating that our DecisionDx-SCC test can predict responses to patients who are receiving adjuvant radiation therapy. And to our knowledge, there was no other biomarker that has been demonstrated in squamous cell carcinoma to predict adjuvant radiation therapy response. Those 2 publications represented the largest single study ever performed in the FCC population and the other one was the second largest study ever performed. So we think with the robustness of that data and the use of our test that was demonstrated after the comment periods were closed to actually identify patients that will get a response from radiation therapy versus those that will not is an important and significant clinical use, which is the, I guess, you call it the verbalized feedback we've gotten not only from clinicians but also from our Medicare contractors.

So I think within that basket of 8 or 9 publications, there is significant new evidence that goes beyond the LCD and by the CMS program integrity manual, both MACs should go ahead and accept our submissions as valid. I think that covers it maybe.

And just -- yes, I just wanted to clarify, again, if we -- if -- I mean, if there's a decision that was negative, what are the avenues that are left at this point? Or if...

We already have a positive from Novitas.

No, I think he means the reconsideration.

Reconsideration, yes.

That's a good question. I guess if MolDX comes back and says, we don't think your submission is valid, we would request and I don't think it's a posted information, but we would certainly want to understand exactly why they believe that's the case. I would have a very hard time to understand how from a medical regulatory standpoint, they could make such a case, but we would work with both MolDX as well as with central CMS to understand what we would believe would be an incorrect conclusion. I don't know about timing, et cetera, but that's just the MolDx avenue. The Novitas avenues moving forward.

Our next question comes from Kyle Mikson from Canaccord Genuity.

Great quarter. So just on the gross margin in the quarter, beat our model, beat the Street. Could you talk about the impact from the SEC reimbursement kind of roll off in the quarter? It seems like that was much better than we had feared. So could you talk about that? And maybe going forward, what that looks like kind of the next few quarters into '26?

Yes, we did -- it wasn't as low as a normalized gross margin will be because we did have payments for part of the quarter. So I would expect the back half of the year adjusted gross margin doesn't look quite as good as it did Q2. Having said that, it's still one of the better gross margins in the sector, and we work hard to maintain that through disciplined spending in facilities, et cetera.

It would be -- Frank, would the mid-70s make sense for adjusted gross margin for like a 4Q, for example?

Yes. I think we said low to mid-70s, Kyle. I think that's what we said in the past. [ Ajudted gross, yes. ]

Yes, of course. And then, Frank, the cash flow from operations positive for the full year. But when you think about the first half of the year, I think it was like $15 million or so from ops. If you take out SEC, I mean, it seems like it would be just a little bit better than breakeven maybe. When you look at the 2026 outlook, just excluding SEC from the top-line, of course, what's the kind of cash flow progression as you think about TissueCypher kind of ramping, melanoma returning rebounding? Could you be positive next year as well?

We have not guided for operating cash flow for '26, but those trends are -- I concur with your view of those trends. And we don't have significant spending increases that might change that. So I think we would be on trend from the fourth quarter into '26.

All right. And then, Derek, last one for you. On the kind of the GI business, is there any -- there's no cross-selling going on today with the 2 -- with the our test and TissueCypher. But do you anticipate that like the conversations with GIs, for example, is going to be a little more streamlined and could accelerate the growth of that segment, let's say? Or is it just like not the most complementary at this point?

I think where we see the most significant value out of the Previse acquisition is not sort of saying you can pick one or the other doctor. Our TissueCypher test with the work that did is clearly the most validated test that's available today and the accuracy metrics are extremely good, although everything can be better. So it would be a complementary test, I guess, you would say, is probably the way to position that today. But the exciting part of what we see is the potential ability to combine spatialomics with genomics, either be it methylation islands like we have from the Previse acquisition or if it's going to be next-gen sequencing. But if we can get to sort of a spatialomics plus something, which could be methylation technology or sequencing add-ons, we believe that we will be able to get to a more accurate test by using more than one modality or platform versus one alone. So that's the sort of first large focus we have. And clearly, the work coming out of Hopkins coming out of provides will assist us in accelerating how to get there.

And then the next opportunity that we see here is to really take the capsule sponge work that they've spent a few years working on and see how we can accelerate that development as a potential future test, again, mainly for use in gastroenterology offices.

Okay. And just to clarify, you're not expecting any material revenue from Esopredict?

No.

No, not discrete revenue. No.

Our next question comes from [ Susie Neman ] from Guggenheim.

This is Subu Nambi from Guggenheim. For DecisionDx-Melanoma, will you need any further studies to support FDA approval?

We don't believe that will be the case. I think the easy conversation that was had with the FDA regulators regarding our BDD application, I would think that we have plenty of data that would support that approval as is. We won't know that, of course, until we go into that process, but we would have taken it through the breakthrough designation device status if we hadn't felt comfortable with that, Subu. So I think we're -- we feel confident that the level of data that we have out there now would support FDA authorization clearance approval depending on the approach they would take.

And then, Derek, how are you prioritizing internal resources between the assets acquired in the Previse acquisition, the SciBase collaboration and the atopic dermatitis assets that you're developing internally?

How are we prioritizing them?

Yes.

Yes, prioritizing internal resources with all of our initiatives.

So the -- I guess starting with Previse first and maybe repeating a bit talked about with Kyle there. We believe that the ability to go from a single platform spatialomics test to a multi-platform multi-omics approach will yield a more clinically valuable test at the end of the day. So to be quite frank, we have ongoing R&D investments in TissueCypher and folding in an extra platform is actually not adding much resources and just expanding the protocol slightly to capture both opportunities. So that's not really a prioritization issue or that. I think the -- we've been looking for opportunities to look down the road to expand in the future our value to our gastroenterology customers. We believe that the capsule sponge technology that Previse had developed will be one of those sources to get there. So that is an additional R&D project. But again, it fits in within the current TissueCypher budget anyways, largely speaking today and tomorrow.

On the SciBase opportunity, as we talked about, I think we -- on the earnings call plus added a slide to our corporate presentation deck on the data that we see today, our internal test really was focused on or is currently being focused on patients who are taking that step from topicals only, most likely have moderate to severe atopic dermatitis that are taking the step over the transom to get to a systemic therapy. That's really where that test is focused, whereas the initial studies that we're focusing on for SciBase technology are really taking people across the spectrum who are being medically treated with topicals and with systemic therapies to be able to say, if you have an atopic dermatitis condition, you're on a therapy of some sort, but you continue to have flares, which are you could call as breakthroughs, I guess, in symptoms. We hope that our technology will be able to demonstrate that you can use our test or our tool every couple of days, every day, every 3 to 4 days and predict a flare in the future, near-term future, adjust your therapy so that you hopefully either reduce the severity of that flare up, which is a significant burden on patients, that also translates to reduced itch flare-ups as well or you may be able to bid it all together

And so to me, they're quite complementary to the exact same medical dermatologist who is interested in eczema skin management, and it turns out that the majority of those physicians are dermatologists are the same customers treating skin cancer. So we have another opportunity for really a strong overlap and the same customer who hopefully knows about casual skin cancer test uses them. And then we've introduced both our internal atopic dermatitis test for predicting therapy response as well as later on the probe that we have from SciBase, it's a very, very nice way to kind of walk into the same offices that are medically oriented and help them solve more patient problems from the same one company. Does that kind of get to the question?

One quick one, a follow-up to Kyle's question on the margins. Based on the current TissueCypher trajectory, do you expect the mix shift to pull downward on your margins this year just because TissueCypher is a lower-margin test? Or have you made some improvements to not really affect that?

Yes. We have improved the cost structure on TissueCypher a good bit. It is still lower gross margin than GEP testing though. So depending on how volumes grow there, it could be a bit of a dilutive to gross margin. But again, it would be -- we would still have one of the better gross margin in the second [ Audio Gap] still hit those targets we ought to hit.

Our next question comes from Catherine Schulte from Baird.

Maybe first, just as we think about your guide for high single-digit DecisionDx-Melanoma volume growth for the year, and that would imply low double-digit growth in the back half. So as we think about going forward, is that back half growth rate the right go-forward assumption? Or do you think high single digit would be a better baseline?

We've said high single digit for the full year, Catherine. So we continue to have that expectation.

Yes, as a jumping off point for next year was the question.

Is a jumping off point for next year? I don't have guidance yet for next year on the product. But as we said before, we still think that the test has plenty of room to grow and continue to penetrate that patient base.

Okay. And then maybe on TissueCypher, how should we think about how much growth is being driven by adding new clinicians versus further penetrating your ordering base? And maybe just talk to what kind of trends you see in terms of order rate ramps as providers mature?

I don't know if we disclosed that information publicly yet, Catherine, although something we couldn't have in the future. We are so early on in penetration. I can't off the top of my head, to be honest, give you a -- are we seeing more growth from existing customers who are seeing better penetration in their practice? Are we seeing more from new customers? Both are happening. I think in the past, we sort of talked about potential -- the GI office practice brings some different challenges compared to dermatology, where in dermatology, the biopsy for a melanoma or squamous cell carcinoma is being done in the office setting. So you've got the same staff, the same dermatologists or NPPA in the same facility, whereas in gastroenterology, the actual endoscopy is being done in the ambulatory care center, which is typically not brick-and-mortar associated with the actual GI clinics. So there's a different personnel swap over.

So my sense is that what we're seeing here is that we are getting solid growth from new first-time ordering customers because we're still early in the game. And once we get somebody on board who buys in a TissueCypher, then after the first couple of orders, the question really becomes how do you make sure that the endoscopy work going on in the ambulatory care center gets transferred the right personnel in the actual GI clinic so that the test is ordered appropriately at the right time. So both will be ongoing strong for a while is my expectation.

Our next question comes from Sung Ji Nam from Scotiabank.

Maybe on the DecisionDx-Melanoma, I was curious if you could talk about the progress you're making with the private payers there. And given the NCI, the real-world study, the largest of such kind, do you think that's a big enough impetus for you to gain further traction with the commercial payers going forward?

Yes, Sung Ji, thanks. I think like most high-value molecular diagnostic tests, we see a lot of resistance from the payer community on the private side. And that resistance is driven less from data or lack of data and more just from self-interest, frankly. And so we continue to generate data. We continue to generate impressive data. More than half the physicians are using our melanoma test. And so I think the payer community is kind of getting to the point of having a red face test problem. I mean how do they go and say this test is experimental and investigational when 55%, 60% of the doctors are using it regularly in their practice. That doesn't sound investigational or experimental to me, unless you think 2/3 of the physicians are unqualified to practice medicine. And if they want to make that assertion, we would be happy to have that debate with them as well. So I think we continue to see penetration there. Very, very slow progress.

The other challenge we've talked with you about before is the need to work through the lab benefit managers, the third-party lab benefit managers and technical assessment groups and their cycles tend to be -- well, they tend to be long and drawn out, but they also tend to be somewhat regular. And so even when you accomplish a change in policy, that policy may not be rolled out until next year. And then each of the member plans, they have their own time lines. And so there's sort of a long kind of a cascade, if you will, of seeing a policy change actually be -- result in change in coverage policy. So we think we've got more than ample evidence. It's sort of beyond clear, but there's just -- there's a self-interest and a resistance on the part of the commercial payers across the board, as you've seen in all categories of testing in your universe.

Got it. That's super helpful. And then just on, the SciBase collaboration, and apologies if you guys have discussed this previously, but they seem to have a product for melanoma as well. And was curious if there are opportunities for collaboration for melanoma going forward or if that's part of the partnership that you guys have announced earlier in the quarter.

Okay. Thank you, Sung Ji. I think we discussed back when we announced the SciBase collaboration, was that a month ago? A month ago. A couple of areas. One is that SciBase developed 2, I guess, platforms or boxes, you could call it, for the electrical impedance spectroscopy technology. One of them is a sort of a desktop-based unit with a probe that's attached to a flexible wand. The other one is a small pen device. Our focus is really on developing the small portable pen device that would be used by a patient, for example, as opposed to being an office where that desktop unit sits and focusing more on newer indications like atopic dermatitis, flare, et cetera. So we do not fold in the current desktop melanoma test into this initial collaboration, but it's certainly something as we go forward that we'll be jointly evaluating and saying if there is the right time for that to have Castle collaborate with that in the U.S., that's great. If not, we can let it go along from a parallel structure standpoint.

We currently have no further questions. So I'd just like to hand back to Derek for any further remarks.

This concludes our second quarter 2025 earnings call. Thank you again for joining us today and for your continued interest in Castle Biosciences.

As we conclude today's call, we'd like to thank everyone for joining. You may now disconnect your lines.