AI to Diagnose Melanoma More Efficiently than Dermatologist


New study reports ability of AI assisted devices to diagnose skin cancer in various parts of the body

Clinical trial published in Annals of Oncology reported that artificial intelligence detected skin cancer more accurately than a large group of international dermatologists in controlled testing, Agence France Presse reports. As a part of the study, 58 dermatologists from 17 countries were examined against a deep learning Convolutional Neural Network (CNN). Prior to the test, researchers from Germany, France, and the U.S. taught the CNN to differentiate benign skin lesions from dangerous melanomas.

In the process, the team showed more than 100,000 images of correctly identified skin cancers to the neural network, which was designed with Google’s Inception v4 CNN architecture. The 58 dermatologists were divided into three self-identified groups: beginners with less than two years of experience, skilled with two to five years, and experts with more than five years of experience.

Two tests were conducted, in the first test dermatologists were shown 100 dermoscopic images with no other information and they were asked to indicate whether the cancer was a melanoma or benign. In addition, the doctors were asked whether they would recommend excision, short-term follow-up, or no action. Four weeks later the dermatologists were shown the same images again, with additional clinical information about the patients plus close-up images.

The CNN scored higher than the overall group of dermatologists on both tests, with and without extra information. The dermatologists accurately identified an average of 86.5 percent of the skin cancers on the image-only test. In the second test, with more information, the doctors averaged 88.9 percent accuracy.  The CNN, however, correctly detected the types of cancers 95 percent of the time based on images only.


Comments are closed.