Artificial intelligence better than doctors at diagnosing skin cancer, study shows
When it comes to diagnosing some cancers, artificial intelligence is better than doctors, research suggests.
The results pitted AI against dermatologists to diagnose signs of skin cancer by looking at images of malignant melanomas and benign moles.
It found that the machines correctly diagnosed the malignant growths in 95% of cases while the human doctors identified 87%.
The artificial intelligence also misdiagnosed fewer benign moles as malignant.
The team of international researchers used a form of AI known as a convolutional neural network (CNN), which mimics the way the brain works, learning as it works.
Prof Holger Haenssle, who led the study – published in the Annals of Oncology – said: “The CNN works like the brain of a child. 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.
“With each training image, the CNN improved its ability to differentiate between benign and malignant lesions.”
MOST POPULAR TODAY ON YAHOO
Father of dangling boy saved from balcony by Mali ‘Spider-Man’ was ‘out playing Pokemon Go’
Parachute sabotage wife says she doesn’t believe husband Emile Cilliers meant to kill her
Teen, 17, arrested over murder of 87-year-old man beaten in his own home
In pictures: Skies above the UK lit up overnight during the ‘mother of all thunderstorms’
The machines were then tested against 58 dermatologists.
“The CNN missed fewer melanomas, meaning it had a higher sensitivity than the dermatologists,” added Prof Haenssle. “And it misdiagnosed fewer benign moles as malignant melanoma, which means it had a higher specificity. This would result in less unnecessary surgery.”
The study’s results comes after Health Secretary Jeremy Hunt said extra funds for the NHS must be used to expand the use of artificial intelligence to diagnose patients.