AI is now better at detecting skin cancer than expert dermatologists
With every development in AI, it’s becoming clear that the most promising areas where the tech could improve lives is in the detection of cancer.
A recent study found that artificial intelligence is not just faster at detecting skin cancer than experts, it’s more accurate, too.
Researchers from Germany, the US 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. It’s an AI system that works similarly to nerve cells in the brain, learning from images it sees and continuously improving its performance.
After training the CNN to recognise the differing forms of skin cancer, the researchers pitted it against that of 58 international dermatologists. Overall, the CNN misdiagnosed benign moles less often and also missed fewer melanomas.
The majority of these dermatologists weren’t new to the industry, either: 17% had less than two years’ experience in dermatoscopy, while 19% had two to five years and 52% of the dermatologists had more than five years’ experience.
The dermatologists accurately detected melanomas in 86.6% of the cases and could correctly identify non-malignant lesions 71% of the time. The CNN was able to detect 95% of the malignant melanomas.
The dermatologists were able to detect more melanomas when they had context about the patients’ background – 88.9% of malignant melanomas and 75% of non-malignant lesions – yet, this still wasn’t as accurate as the CNN.
“These findings show that deep learning convolutional neural networks are capable of out-performing dermatologists, including extensively trained experts, in the task of detecting melanomas,” Holger Haenssle of the University of Heidelberg and first author of the study, explained.
AI has been making huge inroads into the NHS, and in the detection of cancer in recent years. Last year, Stanford University created an AI that spots the warning signs of skin cancer with 91% accuracy. Then in October, an AI created in Japan was able to identify cancer just through a colonoscopy.
The study is a major milestone for the detection of skin cancer. An estimated 232,000 people are diagnosed with having a malignant melanoma worldwide every year, with 55,500 of these dying from the cancer. If detected early, the cancer can be stopped.