University of Chicago researchers have written a computer program that uses artificial intelligence to diagnose metastatic cancer.

The researchers say that the software analyses the features of ultrasound images to help doctors predict earlier whether a woman’’s cancer has metastasised, something that can directly affect how her doctors will approach treatment, which may, in turn, influence the outcome of that treatment.

As part of a preliminary pilot study, the researchers reanalysed the diagnostic ultrasounds of 50 women with suspected breast cancer who all had lymph nodes that appeared normal in the ultrasound—suggesting that their cancers had not metastasised.

The team say that all 50 women later underwent surgery to remove their cancers and axillary lymph nodes, and tissue biopsies of the lymph nodes revealed that 20 of them had metastatic cancer and 30 of them had cancer that remained localized at the time of surgery.

According to the researchers, the pilot study aimed to determine whether the computer would have accurately identified the 20 metastatic cases based on analysing the ultrasound images of the tumours.

Medical physicist Karen Drukker, a research associate and assistant professor in the department of radiology at the University of Chicago, said that the program performed promisingly well.

“We discovered that a computer analysis of breast ultrasound could potentially predict with promising accuracy which patients had metastasis and which did not,” says Drukker.

The researchers next plan to start an observer study in which several radiologists will use the computer program to see whether it enhances their ability to diagnose metastasis, once again based on retrospective cases for which the answer can later be revealed.

A presentation on the study’s findings was made at a meeting of the American Association of Physicists in Medicine (AAPM) in Anaheim, California, on Wednesday.