BCN20000: Dermoscopic Lesions in the Wild
This dataset enables research on automated skin cancer diagnosis from dermoscopic images, particularly for incremental improvements in handling diverse and difficult lesion types.
The authors introduced the BCN20000 dataset of 19,424 dermoscopic skin lesion images to address unconstrained classification of skin cancer, including challenging cases like lesions in hard-to-diagnose locations, large lesions, and hypo-pigmented lesions, for use in the ISIC Challenge 2019.
This article summarizes the BCN20000 dataset, composed of 19424 dermoscopic images of skin lesions captured from 2010 to 2016 in the facilities of the Hospital Clínic in Barcelona. With this dataset, we aim to study the problem of unconstrained classification of dermoscopic images of skin cancer, including lesions found in hard-to-diagnose locations (nails and mucosa), large lesions which do not fit in the aperture of the dermoscopy device, and hypo-pigmented lesions. The BCN20000 will be provided to the participants of the ISIC Challenge 2019, where they will be asked to train algorithms to classify dermoscopic images of skin cancer automatically.