MSK stands for Memorial Sloan-Kettering Cancer Center. It is a lesion recognition image dataset from the Memorial Sloan-Kettering Cancer Center. It can be used to research and develop algorithms for automatic detection of melanoma. Melanoma is the most deadly skin cancer.

The dataset was used as part of the Lesion Analysis Challenge for Melanoma Detection at the 2017 International Symposium on Medical Imaging (ISBI) organized by the International Skin Imaging Collaboration (ISIC). The challenge had three tasks: Lesion Segmentation, Feature Detection, and Lesion Analysis. The competition had 593 registrations, 81 pre-submissions, and 46 final submissions (each participant had a 4-page arXiv paper).