Artificial Intelligence For Skin-Cancer Screening

An algorithm that can classify skin lesions from images could improve skin-cancer screening.

Upvote 0 Comment

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 

Source: https://rdcu.be/Od7J; News and Views https://rdcu.be/Od7M 


No comments yet.