AI Reads Multiple Mammograms to Help Predict Breast Cancer Risk

FRIDAY, Dec. 6, 2024 (HealthDay News) — A new AI can help identify women at higher risk for developing breast cancer by tracking changes in breast tissue, a new study shows.

The AI compares women’s own mammograms over time, looking for early signs of breast cancer that are tough to see even by a well-trained specialist, researchers said.

“Our new method is able to detect subtle changes over time in repeated mammogram images that are not visible to the eye,” said lead researcher Shu (Joy) Jiang, an associate professor of surgery at Washington University School of Medicine in St. Louis.

The AI identified women at high risk of breast cancer 2.3 times more accurately than standard screening methods, researchers reported Dec. 5 in the journal JCO Clinical Cancer Informatics.

“We are seeking ways to improve early detection, since that increases the chances of successful treatment,” said senior researcher Dr. Graham Colditz, associate director of the Siteman Cancer Center at Barnes-Jewish Hospital with Washington University in St. Louis. 

“This improved prediction of risk also may help research surrounding prevention, so that we can find better ways for women who fall into the high-risk category to lower their five-year risk of developing breast cancer,” Colditz added in a university news release.

For the study, researchers built an AI that discerns subtle differences in mammograms, including changes in density, texture, calcification and asymmetry within the breasts.

The team trained the AI on mammograms taken of more than 100,000 women who received breast cancer screening at Siteman Cancer Center between 2008 and 2012. Those women were followed through 2020, and nearly 500 subsequently developed breast cancer.

The researchers then tested the AI on a separate set of more than 18,000 women who got mammograms at Emory University in Atlanta between 2013 and 2020. The group included 332 women diagnosed with breast cancer.

Women judged to be high-risk by the AI were 21 times more likely to be diagnosed with breast cancer within five years, compared to those at lowest risk, researchers found.

About 53 out of every 1,000 women in the high-risk group developed breast cancer, compared to fewer than 3 out of every 1,000 women in the low-risk group, results showed.

Researchers now are testing the AI in women of diverse racial and ethnic backgrounds, to make sure it is equally accurate for everyone.

The research team has a patent pending on their AI.

More information

The U.S. Centers for Disease Control and Prevention has more on breast cancer screening.

SOURCE: Washington University, news release, Dec. 5, 2024