Artificial intelligence shows better results in detecting skin cancer than experienced dermatologists, researchers said Tuesday. A study published in the Annals of Oncology found that a form of artificial intelligence or machine learning known as deep learning convolutional neural network (CNN) is better than human dermatologists at detecting skin cancer.
CNN is a class of deep artificial neural networks inspired by biological processes in that the neurons in the brain are connected to each other and respond to what the eye sees.
A team of researchers from Germany, the United States, and France trained an artificial intelligence system to discover dangerous skin cancer by showing it more than 100,000 images of malignant melanomas and benign nevi.
They compared CNN’s performance with the performance of 58 international dermatologists. They found that CNN missed fewer melanomas and misdiagnosed benign moles as malignant less often than the dermatologists.
The CNN has the ability to learn fast by seeing images and teaching itself in order to improve its performance considering what it has learned (a process is known as machine learning).
“When dermatologists received more clinical information and images at level II, their diagnostic performance improved. However, the CNN, which was still working solely from the dermoscopic images with no additional clinical information, continued to outperform the physicians’ diagnostic abilities,” said professor Holger Haenssle, author of the study and senior managing physician of the Department of Dermatology at the University of Heidelberg in Germany.
The results show that CNN surpassed the dermatologists as well as well-trained experts in detecting melanomas.