A new artificially intelligent computer can diagnose skin cancer more accurately than doctors, according to researchers.
Researchers from Germany, the United States and France trained a deep learning convolutional neural network (CNN) to identify skin cancer by showing it over 100,000 images of malignant melanomas and benign moles. The deep learning convolutional neural network, or CNN, was then pitted against 58 dermatologists from 17 countries.
"The CNN missed fewer melanomas, meaning it had a higher sensitivity than the dermatologists", said Holger Haenssle, the first author of the researcher's paper and an academic at the University of Heidelberg, noted The Guardian. It is capable of machine learning, or teaching itself from what it has "seen", so it can keep improving its performance.
To see who would emerge victorious between the doctors and the CNN, the team presented each with 100 skin lesion images and instructed them to make a diagnosis and recommended a follow-up action. "Before doing so, 100 of the most hard lesions were selected to test real dermatologists in comparison to the results of the CNN", explained lead author Holger Haenssle, MD, PhD, from Heidelberg University in Germany, in a prepared statement. They also believe there are 232,000 new cases of skin cancer and 55,500 deaths are reported each year. 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. This would suggest that human dermatologists tend to over-diagnose malignant melanomas, playing it safe rather than risk passing of a risky mole as benign.
From just dermoscopic images, the clinicians were asked first to diagnose either a benign or malignant condition and asked to assign a care plan (level 1).
The CNN was trained on over 100,000 dermoscopic images.
Health officials say the incidence of both non-melanoma and melanoma skin cancers has been increasing in recent years.
The laptop was extra correct even in comparison with essentially the most skilled medical doctors, the research, printed within the Annals of Oncology, discovered. "This CNN may serve physicians involved in skin cancer screening as an aid in their decision whether to biopsy a lesion or not", Haenssle said.
"Today, nothing can replace a thorough clinical examination", stated Victoria Mar and Peter Soyer, two renowned Australian dermatology professors, in the report that accompanied the study.
After training the neural network, the researchers made two test sets of images from the library of Heidelberg that were never used in any training, making it unknown to the CNN. However, the CNN outperformed the dermatologists by detecting 95 percent of melanomas. However, before such an artificial intelligence system finds broad clinical application, some technical problems, such as the difficulty of correctly depicting certain melanomas in areas such as the fingers and toes or the skull, system to "read" the images.
Will Artificial Intelligence Take Over The World?