These Scientists Are Training AI To Spot Cancer Risks

BERKELEY, CA — Scientists from UC Berkeley and a cancer research and treatment organization have developed a new microfluidic platform using AI that can assess women's breast cancer risks.

Lydia Sohn, the Almy C. Maynard and Agnes Offield Maynard Chair in Mechanical Engineering at UC Berkeley, along with Mark LaBarge, professor in the Department of Population Sciences at City of Hope, developed the AI-based platform called MechanoAge.

"In my view, this is what happens when you have a real collaboration that develops over a long time," LaBarge said. "This result is not what we imagined at the beginning."

MechanoAge squeezes breast epithelial cells to see how they behave and recover under stress. Through the algorithm, researchers can identify cells' "mechanical age" and see whether they show signs of accelerated aging, which can signal cancer risks.

"For women with a known genetic risk factor for breast cancer, there are things you can do, like follow a higher-risk screening protocol," LaBarge said. "For everybody else, you’re left wondering, ‘Am I at high risk?’"

By creating quantifiable data from translating the physical changes in the cell, LaBarge says, woman have real evidence drawn from their own cells to discuss with their doctors.

During the research, scientists put the algorithm to the test by testing it on different cells from older and younger women. The analysis showed that cells from older women took longer to bounce and were stiffer.

Another subset group of young women who already had genetic mutations that put them at higher risk of breast cancer was also found to have cells that were stiffer and bounced less, according to the study.

"We learned that the older the mechanical age, as determined by how cells respond to being squeezed through our microfluidic device, the higher the risk for breast cancer," Sohn said.

Sohn added that while their team isn't the first to measure mechanical properties of cells, their platform was built to be affordable.

"Other approaches require advanced imaging technology that’s expensive, cumbersome and has limited availability," Sohn said. "In contrast, MechanoAge uses computer chips that are simpler than an Apple Watch and Radio Shack parts that are cheap and easy to assemble, potentially making the device highly scalable."

The study by LaBarge and Sohn was published in April in Lancet’s eBioMedicine.