Prior skin image datasets have not addressed patient-level information obtained from multiple skin lesions from the same patient. Though artificial intelligence classification algorithms have achieved expert-level performance in controlled studies examining single images, in practice dermatologists base their judgment holistically from multiple lesions on the same patient. The 2020 SIIM-ISIC Melanoma Classification challenge dataset described herein was constructed to address this discrepancy between prior challenges and clinical practice, providing for each image in the dataset an identifier allowing lesions from the same patient to be mapped to one another. This patient-level contextual information is frequently used by clinicians to diagnose melanoma and is especially useful in ruling out false positives in patients with many atypical nevi. The dataset represents 2,056 patients (20.8% with at least one melanoma, 79.2% with zero melanomas) from three continents with an average of 16 lesions per patient, consisting of 33,126 dermoscopic images and 584 (1.8%) histopathologically confirmed melanomas compared with benign melanoma mimickers.

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.

A Correction to this paper has been published: https://doi.org/10.1038/s41597-021-00879-x.

A great portion of cutaneous melanoma’s diagnoses nowadays is attributed to thin tumors with up to 1 mm in Breslow thickness (hereafter thin CMs), which occasionally metastasize. The objective of this study was to identify thin CM’s metastatic patterns from a topographical and chronological standpoint. A total of 204 cases of metastatic thin CMs from five specialized centers were included in the study, and corresponding data were collected (clinical, epidemiological, histopathological information of primary tumor and the number, anatomical site, and time intervals of their progressions). First progressions occurred locally, in regional lymph nodes, and in a distant site in 24%, 15% and 61% of cases, respectively, with a median time to first progression of 3.10 years (IQR: 1.09–5.24). The median elapsed time between the first and second progression and between the second and third progression was 0.82 (IQR: 0.34–1.97) and 0.49 (IQR: 0.21–2.30) years, respectively, while the median survival time was about 4 years since first progression. Furthermore, the sequences of locations and time intervals of the progressions were associated with the clinicopathological and demographic features of the primary tumors along with the features of the preceding progressions. In conclusion, the findings of this study describe the natural history of thin CMs, thus highlighting the necessity to identify subgroups of thin CMs at a higher risk for metastasis and contributing to the optimization of the management and follow-up of thin CM patients.