Melanoma Updates: Epidemiology, Diagnostics, and Treatment

Melanoma has the highest overall mortality of all dermatologic neoplasms.¹ With depth of invasion standing as the strongest prognostic factor, early detection is critical for improving patient outcomes.² While melanoma incidence continues to increase, advances in diagnostic technologies, therapeutics, and public awareness may have contributed to a recent declining trend in mortality rate.¹ In this article, we review the latest changes in melanoma incidence and mortality, highlight key disparities among minority populations, and summarize emerging trends in technology and treatment that are reshaping the future of melanoma care.

Trends in Incidence and Mortality

According to the US Surveillance, Epidemiology, and End Results (SEER) Program, melanoma incidence has continued to rise since the 1970s. However, the average annual percent increase in incidence has decreased from 3.3% annually from 2000-2005 to 1.1% from 2005-2021 (Figure 1).¹ This suggests that the rate of rise in melanoma incidence has slowed, possibly reflecting the impact of prevention and awareness efforts.

Figure 1. Melanoma incidence in the U.S., 2005-2021.

For reasons that not completely understood and are not explainable by behavior patterns alone, melanoma incidence in men is higher than in women.¹ In 2021, melanoma incidence in men was 28.3 per 100,000 compared to 18.2 per 100,000 in women. The annual percent increase in incidence from 2000 to 2005 was 3.3% in men and 2.8% in women; from 2005 to 2021 the annual percent increase in incidence was 1.0% in men and 1.2% in women.¹ While the rate of increase in incidence slowed for both men and women, the rate of increase in women now slightly surpasses that of men.

Melanoma affects all races and ethnicities but occurs most frequently in non-Hispanic whites (NHW), followed by American Indian/Alaska Natives (AI/AN), and Hispanics. In 2021, the incidence rate was 31.3 cases per 100,000 in NHWs, compared to 0.9 per 100,000 in non-Hispanic blacks, 1.2 per 100,000 in Asian/Pacific Islanders (API), 9 per 100,000 in AI/AN, and 4.5 per 100,000 in Hispanics. Despite the lower incidence observed in darker-skinned populations, concerning trends for AI/AN and Hispanic populations show a 60% and 20% increase in melanoma incidence rates, respectively, over the past 20 years.¹ Although incidence rates in AI/AN and Hispanic populations remain lower than in NHWs, recent increases are concerning and may be driven by factors such as regional UV exposure, European admixture, limited dermatological care access, and low melanoma awareness.³ These populations also experience disproportionately higher mortality risk, possibly attributable to a lack of awareness regarding melanoma by both patients and clinicians. These trends underscore the urgent need to reduce racial disparities in melanoma-specific survival (MSS).³

Diagnostic Advances

Excisional biopsies and histopathologic evaluation of tissue specimens remains the gold standard for melanoma diagnosis. Melanoma surveillance observational studies have shown that digital monitoring technologies, such as total body photography (TBP) and sequential digital dermoscopy imaging (SDDI), increase the detection of thin melanomas and may improve early detection through photographic monitoring, but do not significantly increase melanoma detection.⁴ Reflectance confocal microscopy (RCM) and high-definition optical coherence tomography (OCT) have proven to be valuable adjuncts when clinical dermoscopy alone is insufficient for determining the need to biopsy.⁵ Both RCM and OCT are non-invasive imaging methods for visualization of lesional architecture up to depths of 300 microns and 2 mm, respectively.⁷ One study found that benign nevi and melanoma can be differentiated with 97% sensitivity and 98% specificity using this technology.⁶ However, clinical utility is limited due to the need for skilled and standardized interpretation of images.⁷

Recent advances in artificial intelligence (AI) models, such as machine learning, deep learning, and convolutional neural networks (CNNs), have demonstrated considerable potential in aiding clinicians’ diagnostic decision-making. One study utilized machine learning for detecting melanoma from vibrational OCT data and achieved 95% mean accuracy in detecting malignancy; other studies have utilized machine learning to detect melanoma using RCM data, achieving a mean accuracy of 82.72%. In direct comparisons with dermatologists, AI algorithms analyzing dermoscopic images achieved a higher area under the receiver operating curve (ROC ) (ROC > 80%) which suggests strong discriminatory ability in correctly identifying melanoma with a mean sensitivity of 83.01% and a mean specificity of 85.58%.⁷ Moreover, machine learning algorithms incorporating OCT imaging have shown diagnostic accuracies as high as 95%, while RCM-based models have achieved an average accuracy of 82.72%.⁷ In the primary care setting, AI models have shown an accuracy of 89.3% with dermoscopic images and 84.7% for clinical images, with corresponding sensitivities of 0.91 and 0.89 and specificities of 0.89 and 0.83, respectively.⁸ While AI models have performed at or above the level of dermatologist for early melanoma detection, their accuracy remains variable across minority populations. This variability is largely attributed to underrepresentation in AI training datasets, emphasizing the critical need for more diverse and inclusive algorithm development.⁹

AI is rapidly evolving beyond diagnosis, with applications expanding to predictive modeling for patient-specific treatment response in melanoma. Several studies exploring machine learning models have shown promising predictive capabilities for treatment outcomes and survival.^10,11 As AI tools become integrated into clinical practice, they may offer a powerful means of individualizing therapy and further improving survival outcomes. 

Overall, AI technologies have the potential to complement traditional diagnostic and therapeutic while also serving as an efficient and supportive tool for clinicians.¹²

Treatment Updates

Wide local excision is the standard of care for localized melanoma lesions. However, additional therapy is often required for more advanced disease. The introduction of immune checkpoint blockade and BRAF/MEK inhibitors as mainstays in melanoma treatment has significantly improved survival in patients with metastatic and nodal disease.^13-19 Significant advances have been made in adjuvant and neoadjuvant therapy for melanoma. Adjuvant nivolumab and pembrolizumab, both immune checkpoint inhibitors, have demonstrated to offer superior relapse-free survival in patients with resected stage III or stage IV melanoma, with long term data showing sustained relapse-free outcomes.^19,20 More recently, adjuvant pembrolizumab has shown efficacy in reducing the risk of recurrence in high-risk stage IIB or C disease.^21,22 As neoadjuvant therapy, immune check point inhibitors have improved disease free survival in patients with resectable advanced stage melanoma while maintaining a promising safety profile.^23,24 Relatlimab, an immune check point inhibitor against the lymphocyte-activation gene 3, has also shown potential to serve as a neoadjuvant melanoma therapy.²⁵ While neoadjuvant immune checkpoint blockade therapies for advanced melanoma have demonstrated promising results, additional data is needed to fully elucidate their impact and optimize treatment regimens in this setting.

BRAF/MEK inhibitors have also been shown to provide sustained relapse-free survival in patients with stage III melanoma.^26,27 These inhibitors have demonstrated success as neoadjuvant agents as well.^28-30 A meta-analysis of randomized clinical trial data comparing BRAF inhibitors, MEK inhibitors, and immune checkpoint inhibitors for metastatic melanoma found that, compared to vemurafenib monotherapy, combination therapy with vemurafenib/cobimetinib/ipilimumab was associated with improved overall survival (OR 6.95; 95% CI: 4.25–9.64, P < .00001) and progression-free survival (OR 2.49; 95% CI: 1.42–3.56). Additionally, combination therapy was linked to a lower risk of rash compared to vemurafenib monotherapy (OR 2.09; 95% CI: 1.64–2.67), particularly in patients with lactate dehydrogenase levels below twice the upper limit of normal (OR 1.43; 95% CI: 0.99–2.05). However, risks of side effects such as photosensitivity and pyrexia were elevated with combination therapy.³¹

Oncolytic virus therapy represents an innovative approach to targeted cancer treatment. Intralesional talimogene laherparpvec (T-VEC) is an oncolytic viral therapy engineered from herpes simplex virus type 1 (HSV-1) modified to induce host cells to express granulocyte-macrophage colony-stimulating factor. Administered intralesionally, the virus generates both local and systemic antitumor immune responses.^32,33,34,35  T-VEC is currently the only FDA-approved oncolytic virus therapy for advanced-stage melanoma. Its safety profile is favorable, with flu-like symptoms as the most common side effect.³⁵ Neoadjuvant T-VEC has demonstrated promising survival outcomes and sustained disease-free survival,^36,37,38  though further research is needed to refine treatment strategies, overcome resistance, and enhance therapeutic efficacy.

Despite these advances, a substantial proportion of patients do not respond to current therapies. Between 50%–70% of patients are unresponsive to immune checkpoint inhibitor monotherapy, and 40%–50% do not respond to combination therapy.^39,40 Additionally, up to 60% of patients may experience severe adverse effects from advanced melanoma treatments.⁴¹

Challenges and Gaps

Despite significant advances in therapeutics and the associated decrease in mortality rates, the overall incidence of melanoma continues to rise, leading to an increase in the absolute number of melanoma-related deaths. These trends are especially concerning for patients with skin of color (SOC), among whom MSS has continued to worsen over time.⁴² Several factors contribute to this disparity, including delayed diagnosis, lower rates of health insurance coverage, limited access to dermatologic care, and insufficient targeted melanoma education. ^3,42,43 Representation of SOC in dermatology education remains limited, with curricula and clinical training largely focused on NHW patients; greater efforts are needed to diversify teaching materials and patient exposure.⁴⁴ 

These educational and structural gaps contribute to challenges in recognizing melanoma in SOC populations, where clinical presentations often differ significantly from those seen in NHWs. For instance, SOC patients have the highest incidence of acral lentiginous and mucosal melanomas—subtypes that typically occur on less sun-exposed areas such as the palms, soles, nail beds, and mucosal surfaces.⁴² Furthermore, primary lesions in SOC individuals are more likely to appear on the hips, in contrast to the trunk and upper extremities in NHWs.¹ These differences in anatomic distribution and subtype can delay diagnosis.

AI has shown high accuracy in distinguishing benign from malignant pigmented lesions; however, most AI algorithms are trained on image datasets composed predominantly of NHW patients.⁹ As a result, melanoma in SOC is underrepresented, which limits the performance of these tools in a diverse setting. The lack of representative data risks further delaying diagnosis and appropriate management in SOC patients, thereby perpetuating existing disparities in MSS.

Disparities in outcomes extend beyond diagnosis to treatment access. Although therapeutic innovations like immune checkpoint inhibitors have improved survival in advanced melanoma, not all populations benefit equally. Ramirez et al. found that Hispanic patients with cutaneous melanoma in Texas were more likely to be uninsured, live in poverty, and present with metastatic disease compared to NHWs. Moreover, those without insurance were significantly less likely to receive immunotherapy than privately insured patients.⁴⁵ Similarly, Rosenthal et al. reported that while race/ethnicity was not independently associated with worse survival, lower socioeconomic status was significantly linked to increased melanoma-related mortality.⁴³ These studies highlight the potential impact of race and socioeconomic status in determining melanoma outcomes.

Conclusion

While melanoma incidence continues to rise, recent advances in diagnostics, therapeutics, and surveillance technologies have contributed to declining mortality rates. However, disparities in outcomes persist, particularly among patients with skin of color, who experience worse melanoma-specific survival despite lower incidence. These disparities are driven by a complex interplay of diagnostic delays, limited access to care, and underrepresentation in educational resources, clinical datasets, and treatment trials. As AI and personalized medicine continue to reshape melanoma care, prioritizing diversity in research and training is essential. Future efforts should focus on equitable access to care, inclusive AI model development, and targeted interventions in high-risk populations to ensure that the benefits of modern melanoma management are broadly and fairly distributed. 

The authors report no relevant financial disclosures.

References

1. Shah M, Schur N, Rosenberg A, et al. Trends in melanoma incidence and mortality. Dermatol Clin. 2025;43(2):145-154. doi:10.1016/j.det.2025.03.005

2. Diaz-Ramón JL, Gardeazabal J, Izu RM, et al. Melanoma clinical decision support system: an artificial Intelligence-based tool to diagnose and predict disease outcome in early-stage melanoma patients. Cancers. 2023;15(7):2174. doi:10.3390/cancers15072174

3. Townsend JS, Melkonian SC, Jim MA, Holman DM, Buffalo M, Julian AK. Melanoma incidence rates among non-Hispanic American Indian/Alaska Native individuals, 1999-2019. JAMA dermatology (Chicago, Ill). 2024;160(2):148-155. doi:10.1001/jamadermatol.2023.5226

4. Soyer HP, Jayasinghe D, Rodriguez-Acevedo AJ, et al. 3D Total-body photography in patients at high risk for melanoma: a randomized clinical trial. JAMA dermatology (Chicago, Ill). 2025;doi:10.1001/jamadermatol.2025.0211

5. Boone MALM, Suppa M, Dhaenens F, et al. In vivo assessment of optical properties of melanocytic skin lesions and differentiation of melanoma from non-malignant lesions by high-definition optical coherence tomography. Archives of Dermatological Research. 2016;308(1):7-20. doi:10.1007/s00403-015-1608-5

6. Turani Z, Fatemizadeh E, Blumetti T, et al. Optical radiomic signatures derived from optical coherence tomography images improve identification of melanoma. Cancer research (Chicago, Ill). 2019;79(8):2021-2030. doi:10.1158/0008-5472.CAN-18-2791

7. Patel RH, Foltz EA, Witkowski A, Ludzik J. Analysis of Artificial Intelligence-Based Approaches Applied to Non-Invasive Imaging for Early Detection of Melanoma: A Systematic Review. Cancers. 2023;15(19):4694. doi:10.3390/cancers15194694

8. Giavina-Bianchi M, de Sousa RM, Paciello VZdA, et al. Implementation of artificial intelligence algorithms for melanoma screening in a primary care setting. PloS one. 2021;16(9):e0257006. doi:10.1371/journal.pone.0257006

9. Fliorent R, Fardman B, Podwojniak A, et al. Artificial intelligence in dermatology: advancements and challenges in skin of color. International journal of dermatology. 2024;63(4):455-461. doi:10.1111/ijd.17076

10. Li J, Dan K, Ai J. Machine learning in the prediction of immunotherapy response and prognosis of melanoma: a systematic review and meta-analysis. Front Immunol. 2024;15:1281940. doi:10.3389/fimmu.2024.1281940

11. Wang R, Shao X, Zheng J, et al. A Machine-Learning Approach to Identify a Prognostic Cytokine Signature That Is Associated With Nivolumab Clearance in Patients With Advanced Melanoma. Clin Pharmacol Ther. Apr 2020;107(4):978-987. doi:10.1002/cpt.1724

12. Yee J, Rosendahl C, Aoude LG. The role of artificial intelligence and convolutional neural networks in the management of melanoma: a clinical, pathological, and radiological perspective. Melanoma research. 2024;34(2):96-104. doi:10.1097/CMR.0000000000000951

13. Hodi FS, O’Day SJ, McDermott DF, et al. Improved survival with ipilimumab in patients with metastatic melanoma. N Engl J Med. Aug 19 2010;363(8):711-23. doi:10.1056/NEJMoa1003466

14. Robert C, Thomas L, Bondarenko I, et al. Ipilimumab plus dacarbazine for previously untreated metastatic melanoma. N Engl J Med. Jun 30 2011;364(26):2517-26. doi:10.1056/NEJMoa1104621

15. Robert C, Schachter J, Long GV, et al. Pembrolizumab versus Ipilimumab in Advanced Melanoma. N Engl J Med. Jun 25 2015;372(26):2521-32. doi:10.1056/NEJMoa1503093

16. Chapman PB, Hauschild A, Robert C, et al. Improved survival with vemurafenib in melanoma with BRAF V600E mutation. N Engl J Med. Jun 30 2011;364(26):2507-16. doi:10.1056/NEJMoa1103782

17. Sierra-Davidson K, Boland GM. Advances in Adjuvant and Neoadjuvant Therapy for Melanoma. Hematol Oncol Clin North Am. Oct 2024;38(5):953-971. doi:10.1016/j.hoc.2024.05.007

18. Hauschild A, Grob JJ, Demidov LV, et al. Dabrafenib in BRAF-mutated metastatic melanoma: a multicentre, open-label, phase 3 randomised controlled trial. Lancet. Jul 28 2012;380(9839):358-65. doi:10.1016/s0140-6736(12)60868-x

19. Weber J, Mandala M, Del Vecchio M, et al. Adjuvant Nivolumab versus Ipilimumab in Resected Stage III or IV Melanoma. N Engl J Med. Nov 9 2017;377(19):1824-1835. doi:10.1056/NEJMoa1709030

20. Eggermont AMM, Blank CU, Mandala M, et al. Adjuvant Pembrolizumab versus Placebo in Resected Stage III Melanoma. N Engl J Med. May 10 2018;378(19):1789-1801. doi:10.1056/NEJMoa1802357

21. Luke JJ, Rutkowski P, Queirolo P, et al. Pembrolizumab versus placebo as adjuvant therapy in completely resected stage IIB or IIC melanoma (KEYNOTE-716): a randomised, double-blind, phase 3 trial. Lancet. Apr 30 2022;399(10336):1718-1729. doi:10.1016/s0140-6736(22)00562-1

22. Long GV, Luke JJ, Khattak MA, et al. Pembrolizumab versus placebo as adjuvant therapy in resected stage IIB or IIC melanoma (KEYNOTE-716): distant metastasis-free survival results of a multicentre, double-blind, randomised, phase 3 trial. Lancet Oncol. 2022;23(11):1378-1388. doi:10.1016/s1470-2045(22)00559-9

23. Patel SP, Othus M, Chen Y, et al. Neoadjuvant-Adjuvant or Adjuvant-Only Pembrolizumab in Advanced Melanoma. N Engl J Med. 2023;388(9):813-823. doi:10.1056/NEJMoa2211437

24. Witt RG, Erstad DJ, Wargo JA. Neoadjuvant therapy for melanoma: rationale for neoadjuvant therapy and pivotal clinical trials. Ther Adv Med Oncol. 2022;14:17588359221083052. doi:10.1177/17588359221083052

25. Amaria RN, Postow M, Burton EM, et al. Neoadjuvant relatlimab and nivolumab in resectable melanoma. Nature. Nov 2022;611(7934):155-160. doi:10.1038/s41586-022-05368-8

26. Long GV, Hauschild A, Santinami M, et al. Adjuvant Dabrafenib plus Trametinib in Stage III BRAF-Mutated Melanoma. N Engl J Med. Nov 9 2017;377(19):1813-1823. doi:10.1056/NEJMoa1708539

27. Dummer R, Hauschild A, Santinami M, et al. Five-Year Analysis of Adjuvant Dabrafenib plus Trametinib in Stage III Melanoma. N Engl J Med. Sep 17 2020;383(12):1139-1148. doi:10.1056/NEJMoa2005493

28. Amaria RN, Prieto PA, Tetzlaff MT, et al. Neoadjuvant plus adjuvant dabrafenib and trametinib versus standard of care in patients with high-risk, surgically resectable melanoma: a single-centre, open-label, randomised, phase 2 trial. Lancet Oncol. Feb 2018;19(2):181-193. doi:10.1016/s1470-2045(18)30015-9

29. Long GV, Saw RPM, Lo S, et al. Neoadjuvant dabrafenib combined with trametinib for resectable, stage IIIB-C, BRAF(V600) mutation-positive melanoma (NeoCombi): a single-arm, open-label, single-centre, phase 2 trial. Lancet Oncol. Jul 2019;20(7):961-971. doi:10.1016/s1470-2045(19)30331-6

30. Blankenstein SA, Rohaan MW, Klop WMC, et al. Neoadjuvant Cytoreductive Treatment With BRAF/MEK Inhibition of Prior Unresectable Regionally Advanced Melanoma to Allow Complete Surgical Resection, REDUCTOR: A Prospective, Single-arm, Open-label Phase II Trial. Ann Surg. Aug 1 2021;274(2):383-389. doi:10.1097/sla.0000000000004893

31. Jarab AS, Al-Qerem WA, Khdour LM, Mimi YA, Khdour MR. New emerging treatment options for metastatic melanoma: a systematic review and meta-analysis of skin cancer therapies. Arch Dermatol Res. Nov 1 2024;316(10):735. doi:10.1007/s00403-024-03467-2

32. Kohlhapp FJ, Kaufman HL. Molecular Pathways: Mechanism of Action for Talimogene Laherparepvec, a New Oncolytic Virus Immunotherapy. Clin Cancer Res. Mar 1 2016;22(5):1048-54. doi:10.1158/1078-0432.Ccr-15-2667

33. Zhang T, Jou TH, Hsin J, et al. Talimogene laherparepvec (T-VEC): A review of the recent advances in cancer therapy. J Clin Med. 2023;12(3):1098. doi:10.3390/jcm12031098

34. Ferrucci PF, Pala L, Conforti F, et al. Talimogene laherparepvec (T-VEC): an intralesional cancer immunotherapy for advanced melanoma. Cancers (Basel). 2021;13(6). doi:10.3390/cancers13061383

35. Gangi A, Zager JS. The safety of talimogene laherparepvec for the treatment of advanced melanoma. Expert Opin Drug Saf. 2017;16(2):265-269. doi:10.1080/14740338.2017.1274729

36. Dummer R, Gyorki DE, Hyngstrom J, et al. Neoadjuvant talimogene laherparepvec plus surgery versus surgery alone for resectable stage IIIB-IVM1a melanoma: a randomized, open-label, phase 2 trial. Nat Med. 2021;27(10):1789-1796. doi:10.1038/s41591-021-01510-7

37. Kaufman HL, Kim DW, DeRaffele G, et al. Local and distant immunity induced by intralesional vaccination with an oncolytic herpes virus encoding GM-CSF in patients with stage IIIc and IV melanoma. Ann Surg Oncol. 2010;17(3):718-730. doi:10.1245/s10434-009-0809-6

38. Dummer R, Gyorki DE, Hyngstrom JR, et al. Final 5-year follow-up results evaluating neoadjuvant talimogene laherparepvec plus surgery in advanced melanoma: a randomized clinical trial. JAMA Oncol. 2023;9(10):1457-1459. doi:10.1001/jamaoncol.2023.2789

39. Lee KA, Thomas AM, Bolte LA, et al. Cross-cohort gut microbiome associations with immune checkpoint inhibitor response in advanced melanoma. Nat Med. 2022;28(3):535-544. doi:10.1038/s41591-022-01695-5

40. Ugurel S, Schadendorf D, Horny K, et al. Elevated baseline serum PD-1 or PD-L1 predicts poor outcome of PD-1 inhibition therapy in metastatic melanoma. Ann Oncol. 2020;31(1):144-152. doi:10.1016/j.annonc.2019.09.005

41. Asher N, Ben-Betzalel G, Lev-Ari S, et al. Real-world outcomes of ipilimumab and nivolumab in patients with metastatic melanoma. Cancers (Basel). 2020;12(8). doi:10.3390/cancers12082329

42. Qian Y, Johannet P, Sawyers A, et al. The ongoing racial disparities in melanoma: an analysis of the Surveillance, Epidemiology, and End Results database (1975–2016). J Am Acad Dermatol. 2021;84(6):1585-1593. doi:10.1016/j.jaad.2020.08.097

43. Rosenthal A, Reddy S, Cooper R, et al. Disparities in melanoma-specific mortality by race/ethnicity, socioeconomic status, and health care systems. J Am Acad Dermatol. 2023;88(3):560-567. doi:10.1016/j.jaad.2022.10.004

44. Syder NC, Omar D, McKenzie S, et al. Gaps in medical education curricula on skin of color in medical school, residency, and beyond: Part 1. J Am Acad Dermatol. 2023;89(5):885-892. doi:10.1016/j.jaad.2022.03.053

45. Ramirez F, Alvarado L, Dwivedi A, et al. Immunotherapy treatment disparities: a Texas Cancer Registry analysis of patients with cutaneous melanoma. J Immigr Minor Health. 2024;26(1):23-33. doi:10.1007/s10903-023-01536-8