AI shows promise in telling types of breast cancer apart

The power of artificial intelligence is challenging pathologists in their ability to detect and diagnose some forms of breast cancer.

Researchers in the US have been testing how machine learning could help to read biopsies thanks to its ability to recognise complex patterns that can be a challenge for humans.

“Medical images of breast biopsies contain a great deal of complex data and interpreting them can be very subjective,” said Dr Joann Elmore, lead author of the study published in the JAMA Network Open journal.

“Distinguishing breast atypia from ductal carcinoma in situ (DCIS) is important clinically but very challenging for pathologists.

“Sometimes, doctors do not even agree with their previous diagnosis when they are shown the same case a year later.”

The team supplied its artificial intelligence system with 240 breast biopsy images linked to several types of breast lesions, with its readings compared against diagnoses made by 87 practicing pathologists.

It found that AI came close to performing as well as human doctors in differentiating cancer from non-cancer cases, but the machine managed to outperform doctors when differentiating DCIS from atypical hyperplasia.

“These results are very encouraging,” added Dr Elmore, a professor at the University of California, Los Angeles.

“It is critical to get a correct diagnosis from the beginning so that we can guide patients to the most effective treatments.”

With further improvements, researchers hope AI could be a vital tool in aiding pathologists, and are looking at how it could be used to diagnose melanoma next.

Earlier this week, the Department of Health announced that the NHS will receive a £250 million boost to build artificial intelligence that could help treat conditions including cancer.

The money will be invested in a new National Artificial Intelligence Lab which could help tackle some of the biggest challenges facing the NHS, including improving cancer screening, identifying patients most at risk of dementia or heart disease, and automating admin tasks, giving medical professionals more time with patients.