AI algorithm is as good as radiologists at identifying breast cancer

The National Institute for Health Research (NIHR) has recently announced that an artificial intelligence (AI) algorithm can identify breast cancer from x-ray images as accurate as expert radiologists.

The algorithm, developed by researchers from DeepMind, Google Health, the NHS, Northwestern University in Chicago and Imperial College London, was trained using the x-ray images of almost thirty-thousand women’s breasts from the US and UK, and then was tested to see if it could recognise breast cancer in mammograms of women who either had no cancer or had breast cancer proven by biopsy.

The researchers distributed their discoveries in ‘Nature’, which revealed that the AI algorithm was able to identify breast cancer from the x-ray images to a similar degree of precision to expert radiologists. In addition, the algorithm also significantly decreased the quantity of screening errors where cancer may have been missed or was recognised inaccurately by a radiologist .

Professor the Lord Ara Darzi of Denham, director of the Cancer Research UK Imperial Centre and one of the authors of the paper, stated: “Screening programmes remain one of the best tools at our disposal for catching cancer early and improving outcomes for patients but many challenges remain, not least the current volume of images radiologists must review. While these findings are not directly from the clinic, they are very encouraging and they offer clear insights into how this valuable technology could be used in real life. There will of course a number of challenges to address before artificial intelligence could be implemented in mammography screening programmes around the world, but the potential for improving healthcare and helping patients is enormous.”