Artificial intelligence beat doctors in a recent study in finding skin cancer on humans as researchers worked to develop a way to faster detect the dangerous skin lesions from benign ones, The Guardian reported.
German, French, and American researchers made up a team that taught an artificial intelligence system to distinguish cancerous lesions compared to those that were not, the newspaper said. The deep learning convolutional neural network, or CNN, was then pitted against 58 dermatologists from 17 countries.
"The CNN works like the brain of a child," Holger Haenssle, senior managing physician at the University of Heidelberg, Germany, and lead author of the study said in a statement from the European Society for Medical Oncology. "To train it, we showed the CNN more than 100,000 images of malignant and benign skin cancers and moles and indicated the diagnosis for each image.
"Only dermoscopic images were used, that is lesions that were imaged at a 10-fold magnification. With each training image, the CNN improved its ability to differentiate between benign and malignant lesions."
The machine and doctors were shown images of malignant melanomas and benign moles, the newspaper said. Doctors correctly found skin cancer and benign moles 86.6 percent of the time, but CNN was correct 95 percent of the time.
"One set of 300 images was built to solely test the performance of the CNN, Haenssle said in the statement. "Before doing so, 100 of the most difficult lesions were selected to test real dermatologists in comparison to the results of the CNN," Haenssle continued.
"… The CNN missed fewer melanomas, meaning it had a higher sensitivity than the dermatologists, and it misdiagnosed fewer benign moles as malignant melanoma, which means it had a higher specificity; this would result in less unnecessary surgery," he said.
Researchers said CNN would be a useful tool for dermatologists in diagnosing skin cancers, but not take over for them. Doctors were in an "artificial setting," the test set did not include the full range of skin lesions; and there were fewer images from non-Caucasian skin types and genetic backgrounds to examine.
"Currently, there is no substitute for a thorough clinical examination," Dr. Victoria Mar, of Monash University in Melbourne, Australia, and H. Peter Soyer of The University of Queensland in Brisbane, Australia, said in an editorial that accompanied a study in the Annals of Oncology, according to a European Society for Medical Oncology statement.
"However, 2D and 3D total body photography is able to capture about 90 to 95 percent of the skin surface and given exponential development of imaging technology we envisage that sooner than later, automated diagnosis will change the diagnostic paradigm in dermatology. Still, there is much more work to be done to implement this exciting technology safely into routine clinical care," they continued.
© 2026 Newsmax. All rights reserved.