Skin-cancer screening is important for early diagnosis and treatment. Visual examination by dermatologists is the first step to identify abnormal skin lesions that need to be further biopsied. In a pioneering report, “Dermatologist-level classification of skin cancer with deep neural networks,” Andre Esteva et al. used 129,450 clinical images of skin disease to train a deep convolutional neural network to classify skin lesions according to established criteria. The result is an algorithm that can classify lesions from photographic images similar to those taken with a mobile phone. The accuracy of the system in detecting malignant melanomas and carcinomas matched that of trained dermatologists. This technique could be used outside the clinic as a visual screen for cancer, potentially reducing healthcare costs and expanding and simplifying screening.
By Victoria Aranda, Nature