{"url":"/dataset/isic-2020-challenge-dataset","name":"ISIC 2020 Challenge Dataset","full_name":"Official dataset of the SIIM-ISIC Melanoma Classification Challenge 2020","description_markdown":"The dataset contains 33,126 dermoscopic training images of unique benign and malignant skin lesions from over 2,000 patients. Each image is associated with one of these individuals using a unique patient identifier. All malignant diagnoses have been confirmed via histopathology, and benign diagnoses have been confirmed using either expert agreement, longitudinal follow-up, or histopathology. A thorough publication describing all features of this dataset is available in the form of a pre-print that has not yet undergone peer review.\r\n\r\nThe dataset was generated by the International Skin Imaging Collaboration (ISIC) and images are from the following sources: Hospital Clínic de Barcelona, Medical University of Vienna, Memorial Sloan Kettering Cancer Center, Melanoma Institute Australia, University of Queensland, and the University of Athens Medical School.\r\n\r\nThe dataset was curated for the SIIM-ISIC Melanoma Classification Challenge hosted on Kaggle during the Summer of 2020.\r\n\r\nDOI: https://doi.org/10.34970/2020-ds01","description_withheld":null,"homepage":"https://challenge2020.isic-archive.com/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":{"name":"Creative Commons Attribution-Non Commercial 4.0 International License.","url":"https://creativecommons.org/licenses/by-nc/4.0/legalcode.txt"},"modalities":[],"tasks":[{"name":"Medical Image Classification","url":"/task/medical-image-classification","datasets_with_task":"/datasets/task/medical-image-classification"},{"name":"Skin Lesion Classification","url":"/task/skin-lesion-classification","datasets_with_task":"/datasets/task/skin-lesion-classification"},{"name":"Skin Cancer Segmentation","url":"/task/skin-cancer-segmentation","datasets_with_task":"/datasets/task/skin-cancer-segmentation"},{"name":"Skin Cancer Classification","url":"/task/skin-cancer-classification","datasets_with_task":"/datasets/task/skin-cancer-classification"}],"languages":[],"variants":["ISIC 2020 Challenge Dataset"],"data_loaders":[],"num_papers_in_archive":6,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/medical-image-classification-on-isic-2020","task":"Medical Image Classification","dataset_variant":"ISIC 2020 Challenge Dataset","rows":1,"metrics":["AUC"],"first_row_in_archive_order":{"model":"EfficientNet Ensemble","paper":"/paper/identifying-melanoma-images-using","metrics":{"AUC":"0.9490"},"code_links":[{"title":"haqishen/SIIM-ISIC-Melanoma-Classification-1st-Place-Solution","url":"https://github.com/haqishen/SIIM-ISIC-Melanoma-Classification-1st-Place-Solution"},{"title":"Tirth27/Skin-Cancer-Classification-using-Deep-Learning","url":"https://github.com/Tirth27/Skin-Cancer-Classification-using-Deep-Learning"},{"title":"stanleyjzheng/masseyhacksvii","url":"https://github.com/stanleyjzheng/masseyhacksvii"},{"title":"Ramstein/MelanomaClassification","url":"https://github.com/Ramstein/MelanomaClassification"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/identifying-melanoma-images-using","title":"Identifying Melanoma Images using EfficientNet Ensemble: Winning Solution to the SIIM-ISIC Melanoma Classification Challenge","date":"2020-10-11","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":1,"samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}