A deep convolutional neural network trained on a relatively small dataset in order to classify skin cancer. Researchers found the technology to be more accurate than board-certified dermatologists in their tests. Researchers suggest that this technology, which uses only a single image, can be used for screening purposes.
Creator
Information
Pediatrics or Adult
Adult
Speciality
Dermatology
Modality
Clinical Images
Training
Used 4867 clinical images obtained from 1842 patients diagnosed with skin tumours at the University of Tsukuba Hospital from 2003 to 2016