AI promising on breast cancer

Google says it has developed an artificial intelligence system that can detect the presence of breast cancer more accurately than doctors can.

An international team designed and trained a computer model on X-ray images from thousands of women in the UK and the US. They then compared the system's performance with the actual results from 25,856 mammograms in the UK and 3,097 from the US.

The program was trained to detect cancer using tens of thousands of mammograms from women in the United Kingdom and the United States, and early research shows it can produce more accurate detection than human radiologists can.

The algorithm outperformed six radiologists in reading mammograms, according to a study published Wednesday in the scientific journal Nature. AI was still as good as two doctors working together.

The AI program was developed through a collaboration of Google Health, Cancer Research UK Imperial Centre, Northwestern University and Royal Surrey County Hospital.

According to the study, using the AI technology resulted in fewer false positives, where test results suggest cancer is present when it isn't, and false negatives, where an existing cancer goes undetected.

Compared with human experts, the program reduced false positives by 5.7 percent for US subjects and 1.2 percent for UK subjects. It reduced false negatives by 9.4 percent for US subjects and 2.7 percent for UK subjects.

The AI system was more accurate despite it having less information to work with than human experts did, such as patient histories and prior mammograms.

Breast cancer affects 1 in 8 women globally. It is the second-leading cause of death from cancer in women, surpassed only by lung cancer in its deadliness and overall prevalence.

Despite large-scale breast cancer screening programs in developed countries, screening mammograms don't find about 1 in 5 breast cancers, according to the American Cancer Society.

"This is one of those transformational discoveries you have in your hand, which could disrupt the way we deliver screening in terms of improving accuracy and productivity," Professor Ara Darzi, one of the authors of the paper and the director of the Cancer Research UK Imperial Centre, told CNN Business.

"The performance of even the best clinicians leaves room for improvement," the study's authors wrote in Nature. "AI may be uniquely poised to help with this challenge."

The technology also could be used to address shortages in radiologists, they say.

A 2018 report by the Royal College of Radiologists found that 75 percent of UK radiology department directors believed there were insufficient clinical radiologists to deliver a safe and effective level of patient care.

Reuters contributed to this story.