Artificial intelligence (AI) systems have been shown to help dermatologists diagnose melanoma more accurately, however they lack transparency, hindering user acceptance. Explainable AI (XAI) methods can help to increase transparency, yet often lack precise, domain-specific explanations. Moreover, the impact of XAI methods on dermatologists’ decisions has not yet been evaluated. Building upon previous research, we introduce an XAI system that provides precise and domain-specific explanations alongside its differential diagnoses of melanomas and nevi. Through a three-phase study, we assess its impact on dermatologists’ diagnostic accuracy, diagnostic confidence, and trust in the XAI-support. Our results show strong alignment between XAI and dermatologist explanations. We also show that dermatologists’ confidence in their diagnoses, and their trust in the support system significantly increase with XAI compared to conventional AI. This study highlights dermatologists’ willingness to adopt such XAI systems, promoting future use in the clinic.

Due to their ability to solve complex problems, deep neural networks (DNNs) are becoming increasingly popular in medical applications. However, decision-making by such algorithms is essentially a black-box process that renders it difficult for physicians to judge whether the decisions are reliable. The use of explainable artificial intelligence (XAI) is often suggested as a solution to this problem. We investigate how XAI is used for skin cancer detection: how is it used during the development of new DNNs? What kinds of visualisations are commonly used? Are there systematic evaluations of XAI with dermatologists or dermatopathologists? Google Scholar, PubMed, IEEE Explore, Science Direct and Scopus were searched for peer-reviewed studies published between January 2017 and October 2021 applying XAI to dermatological images: the search terms histopathological image, whole-slide image, clinical image, dermoscopic image, skin, dermatology, explainable, interpretable and XAI were used in various combinations. Only studies concerned with skin cancer were included. 37 publications fulfilled our inclusion criteria. Most studies (19/37) simply applied existing XAI methods to their classifier to interpret its decision-making. Some studies (4/37) proposed new XAI methods or improved upon existing techniques. 14/37 studies addressed specific questions such as bias detection and impact of XAI on man-machine-interactions. However, only three of them evaluated the performance and confidence of humans using CAD systems with XAI. XAI is commonly applied during the development of DNNs for skin cancer detection. However, a systematic and rigorous evaluation of its usefulness in this scenario is lacking.

Background. Reports on long-term (≥10 years) effects of cancer vaccines are missing. Therefore, in 2002, we initiated a phase I/II trial in cutaneous melanoma patients to further explore the immunogenicity of our DC vaccine and to establish its long-term toxicity and clinical benefit after a planned 10-year followup. Methods. Monocyte-derived DCs matured by TNFα, IL-1β, IL-6, and PGE ₂ and then loaded with 4 HLA class I and 6 class II–restricted tumor peptides were injected intradermally in high doses over 2 years. We performed serial immunomonitoring in all 53 evaluable patients. Results. Vaccine-specific immune responses including high-affinity, IFNγ-producing CD4 ⁺ and lytic polyfunctional CD8 ⁺ T cells were de novo induced or boosted in most patients. Exposure of mature DCs to trimeric soluble CD40 ligand, unexpectedly, did not further enhance such immune responses, while keyhole limpet hemocyanin (KLH) pulsing to provide unspecific CD4 ⁺ help promoted CD8 ⁺ T cell responses — notably, their longevity. An unexpected 19% of nonresectable metastatic melanoma patients are still alive after 11 years, a survival rate similar to that observed in ipilimumab-treated patients and achieved without any major (>grade 2) toxicity. Survival correlated significantly with the development of intense vaccine injection site reactions, and with blood eosinophilia after the first series of vaccinations, suggesting that prolonged survival was a consequence of DC vaccination. Conclusions. Long-term survival in advanced melanoma patients undergoing DC vaccination is similar to ipilimumab-treated patients and occurs upon induction of tumor-specific T cells, blood eosinophilia, and strong vaccine injection site reactions occurring after the initial vaccinations. TRIAL REGISTRATION. ClinicalTrials.gov NCT00053391. FUNDING. European Community, Sixth Framework Programme (Cancerimmunotherapy LSHC-CT-2006-518234; DC-THERA LSHB-CT-2004-512074), and German Research Foundation (CRC 643, C1, Z2).

Uveal melanoma (UM) represents the most common intraocular malignancy in adults and accounts for about 5% of all melanomas. Primary disease can be effectively controlled by several local therapy options, but UM has a high potential for metastatic spread, especially to the liver. Despite its clinical and genetic heterogeneity, therapy of metastatic UM has largely been adopted from cutaneous melanoma (CM) with discouraging results until now. The introduction of antibodies targeting CTLA-4 and PD-1 for immune checkpoint blockade (ICB) has revolutionized the field of cancer therapy and has achieved pioneering results in metastatic CM. Thus, expectations were high that patients with metastatic UM would also benefit from these new therapy options. This review provides a comprehensive and up-to-date overview on the role of ICB in UM. We give a summary of UM biology, its clinical features, and how it differs from CM. The results of several studies that have been investigating ICB in metastatic UM are presented. We discuss possible reasons for the lack of efficacy of ICB in UM compared to CM, highlight the pitfalls of ICB in this cancer entity, and explain why other immune-modulating therapies could still be an option for future UM therapies.

Early detection of melanoma is critical to reduce the mortality and morbidity rates of this tumor. Total body photography (TBP) may aid in the early detection of melanoma. To summarize the current evidence on TBP for the early detection of melanoma, we performed a systematic literature search in Medline, Embase, and the Cochrane Central Register of Controlled Trials (CENTRAL) for eligible records up to 6th August 2020. Outcomes of interest included melanoma incidence, incisional and excisional biopsy rates, as well as the Breslow’s index of detected tumors. Results from individual studies were described qualitatively. The risks of bias and applicability of the included studies was assessed using the QUADAS-2 checklist. In total, 14 studies published between 1997 and 2020 with an overall sample size of n = 12,082 (range 100–4692) were included in the qualitative analysis. Individuals undergoing TBP showed a trend towards a lower Breslow’s thickness and a higher proportion of in situ melanomas compared to those without TBP. The number needed to excise one melanoma varied from 3:1 to 14.3:1 and was better for lesions that arose de novo than for tracked ones. The included studies were judged to be of unclear methodological concern with specific deficiencies in the domains “flow and timing” and “reference standard”. The use of TBP can improve the early detection of melanoma in high-risk populations. Future studies are warranted to reduce the heterogeneity of phenotypic risk factor definition and the technical implementation of TBP. Artificial intelligence-assisted analysis of images derived from 3-D TBP systems and digital dermoscopy may further improve the early detection of melanoma.