AI-powered mammography finds cancer cases not initially detected by radiologists

Hologic has announced data form a study of of its AI-driven mammography technology, which found that the technology was able to identify cancer cases that were not initially identified by radiologists.

In a retrospective study conducted at Massachusetts General Hospital, researchers analysed 5,000 digital breast tomosynthesis (3D mammography) screening exams performed between 2016 and 2019 using Hologic’s Genius AI Detection 2.0 mammography solution.

Among the 5,000 exams, there were 100 cancer cases that were not initially detected by radiologists but were later confirmed to be malignant. The study looked at whether Genius AI Detection 2.0 was able to identify any of these previously missed cancers, as well as its ability to detect and correctly localise the 500 cancers that were initially identified by radiologists.

“As AI continues to evolve, I believe it will become an increasingly vital tool for radiologists, helping to transform breast cancer detection and ultimately reduce the burden of this disease for patients,” said Manisha Bahl, Breast Imaging Division quality director and co-service chief at Massachusetts General Hospital and associate professor of radiology at Harvard Medical School.

Hologic will present the research at the Society of Breast Imaging (SBI) Annual Symposium in Colorado Springs, Colorado.

Hologic will also highlight its contrast-enhanced mammography technology, the Envision Mammography Platform, and the new Genius AI Detection PRO solution, which offers advanced cancer detection by analysing prior exams and an AI assistant with automated reporting and other workflow features.

Genius AI Detection PRO also includes a red-yellow-green colour-coded system, where green cases signify that the AI is confident there is no breast cancer present while red means the AI is confident there is cancer present. Designed to simplify the entire reading workflow, Genius AI Detection PRO solution has been shown to reduce radiologists’ overall reading time up to 24 per cent.

“It’s an exciting time for breast health innovation, and we’re proud to showcase our latest advancements at this year’s SBI event,” said Mark Horvath, president of Breast and Skeletal Health Solutions.

“From AI-driven solutions to breast surgery technologies, Hologic continues to lead the way in redefining the breast health continuum and improving the standard of care for women everywhere.”