A Patient-Centric Dataset of Images and Metadata for Identifying Melanomas Using Clinical Context
Abstract
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 from three continents with an average of 16 lesions per patient, consisting of 33,126 dermoscopic images and 584 histopathologically confirmed melanomas compared with benign melanoma mimickers.
Keywords
Cite
@article{arxiv.2008.07360,
title = {A Patient-Centric Dataset of Images and Metadata for Identifying Melanomas Using Clinical Context},
author = {Veronica Rotemberg and Nicholas Kurtansky and Brigid Betz-Stablein and Liam Caffery and Emmanouil Chousakos and Noel Codella and Marc Combalia and Stephen Dusza and Pascale Guitera and David Gutman and Allan Halpern and Harald Kittler and Kivanc Kose and Steve Langer and Konstantinos Lioprys and Josep Malvehy and Shenara Musthaq and Jabpani Nanda and Ofer Reiter and George Shih and Alexander Stratigos and Philipp Tschandl and Jochen Weber and H. Peter Soyer},
journal= {arXiv preprint arXiv:2008.07360},
year = {2020}
}
Comments
Figures: 3, Tables: 2, Pages: 12