According to statistics from the WHO, currently, between 2 and 3 million non-melanoma skin cancers and 132,000 melanoma skin cancers occur each year globally. Digital health technologies, such as smartphone apps like SkinVision, telemedical services as well as A.I. are at the frontlines of fighting the widely prevalent disease.

Although several research groups developed smart algorithms for diagnosing skin cancer already, the one created at Stanford University is likely the most robust system so far. It was trained on more than 1.28 million images and fine-tuned with a set of nearly 130,000 scans of skin lesions from more than 2000 diseases. That’s the most extensive dataset used for automated skin cancer classification as of yet.

Read more…