Artificial Intelligence can detect skin cancer better than dermatologists

Adjust Comment Print

A new artificially intelligent computer can diagnose skin cancer more accurately than doctors, according to researchers. A CNN is an artificial neural network inspired by the biological processes at work when nerve cells (neurons) in the brain are connected to each other and respond to what the eye sees. It is a deep learning convolutional neural network, trained to detect cancer, previously fed with more than 100,000 images of malignant melanomas, as well as - for comparison purposes - images of harmless moles.

The computer's performance was then compared to that of 58 specialist doctors from 17 countries. In a technique known as machine learning, the device was able to quickly evaluate information researchers presented it, and improve its ability to pinpoint skin cancers.

The performance of the dermatologists showed an improvement when they were provided more details of the patients and their skin cancer.

More news: Ukraine admits faking death of anti-Kremlin journalist

"Most dermatologists were outperformed by the CNN", the research team wrote in a paper published in the journal Annals of Oncology.

It also "misdiagnosed fewer benign moles as malignant melanoma... this would result in less unneccessary surgery".

Melanoma incidents are constantly increasing, with about 232,000 new diagnoses and 55,500 deaths each year worldwide.

More news: Singapore Airlines announces 19-hour ultra-marathon to NY

In a series of field tests, the Heidelberg team pitted the CNN against dermatologists from all over Europe. But even so, the CNN, which was still working only with the images and was given no additional information, still outperformed the humans. More than half of the clinicians had more than 5 years of experience. Melanoma can be cured if diagnosed early, but unfortunately often the diagnosis is delayed when the cancer progresses.

More research needs to be carried out ensure the CNN is accurate when diagnosing areas hard to image such as the fingers, toes and scalp, and to train it to pick up unusual melanomas, as well as lesions that patients haven't yet found.

It's not likely that AI will replace the efforts of dermatologists any time soon, as a thorough clinical examination is a safer bet than a clever system adept at image recognition. "Still, there is much more work to be done to implement this exciting technology safely into routine clinical care", they continued.

More news: IPL 2018: List of all the Winners

The authors conclude the results of their study "demonstrate that an adequately trained deep learning CNN is capable of a highly accurate diagnostic classification of dermoscopic images of melanocytic origin" and that "physicians of all different levels of training and experience may benefit from assistance by a CNN's image classification".