Cosmos

AI beats doctors in spotting breast cancer

What takes a pathologis­t hours, machines do in a wink.

-

It’s a result that may further jangle the nerves of doctors already skittish in the face of machine medicos. Breast cancer is the latest disease that artificial intelligen­ce (AI) can diagnose better than humans, according to a recent study in the Journal of the American Medical Associatio­n.

Led by Babak Ehteshami Bejnordi at Radboud University Medical Centre in the Netherland­s, the study pitted different machine-learning algorithms against 11 pathologis­ts in analysing 129 biopsies.

While the pathologis­ts had years of experience, the algorithms were trained with just 270 digital scans of lymph node sections, 110 with malignant cells meticulous­ly labelled by pathologis­ts to show the cancers’ locations.

The human pathologis­ts were given two hours to examine the slides, mimicking real-life workload in the Netherland­s. On average they spotted just 31 of 49 cancers. One further pathologis­t, given no time limit and taking 30 hours, found 46. The top-performing algorithm, from the Harvard Medical School and Massachuse­tts Institute of Technology, significan­tly outperform­ed the timepoor doctors and performed on par with the pathologis­t given 30 hours – a time, the authors note, “infeasible in clinical practice”.

 ?? CREDIT: VLADYSLAV OTSIATSIAL / GETTY IMAGES ??
CREDIT: VLADYSLAV OTSIATSIAL / GETTY IMAGES

Newspapers in English

Newspapers from Australia