The integration of convolutional neural networks into dermatology practices, especially those with fewer than 5 years of experience, may increase diagnostic accuracy of skin cancer, according to a ...

On the most basic level of classification—benign, malignant, or a type called "non-neoplastic"—the accuracy of the neural network was over 70 percent while the doctors were in the 60s.

In an international study that compared dermatologists and A.I. neural networks in their ability to correctly diagnose skin cancers based on images, A.I. was accurate more often than the doctors ...