AI Technology Helping Diagnose Breast Cancer Even Earlier

A study by breast radiologists at Lynn Women’s Health & Wellness Institute at Baptist Health Boca Raton Regional Hospital reveals that adding artificial intelligence (AI) technology to existing 3D mammography for breast cancer screening helps catch cancers before they can be detected by the human eye on images. The Institute is the only site in South Florida that offers this particular AI-enhanced digital breast imaging.

“With AI, we are finding cancers years before we would find them without AI,” says investigator Kathy Schilling, M.D., medical director of Lynn Women’s Health & Wellness Institute. “This technology is having a significant impact. We are seeing that less therapy is needed for our patients. They may not require chemotherapy or radiation therapy.”

Breast cancer is the most common cancer found in women in the U.S., and nearly 300,000 new cases are expected to be diagnosed in 2023, according to the American Cancer Society.

Kathy Schilling, M.D., medical director of Baptist Health Lynn Women’s Health & Wellness Institute at Boca Raton Regional Hospital

An early adopter of AI, Dr. Schilling’s curiosity drove her to conduct a retrospective evaluation of the Institute’s experience. She presented those results, “Real-World Breast Cancer Screening Performance with Digital Breast Tomosynthesis Before and After Implementation of an Artificial Intelligence Detection System,” at the European Congress of Radiology meeting in Vienna on March 3.

The Institute began using AI in 2020 in the hopes that its dedicated breast radiologists would find more cancers in their early stage, when they are most treatable. “We were already outperforming expected detection rate benchmarks from the American College of Radiology,” Dr. Schilling says, “but as volumes increased, we wanted to ensure quality and increase our confidence.”

Her findings were even more dramatic than expected. Cancer detection rates rose from 5.77 per 1000 women screened to 7.8 per 1000, a 23 percent increase in detection, according to Dr. Schilling. Each of the radiologists improved in accuracy and there was no change in recall rates, meaning that there were no more false positives than usual, she adds.

Improvements in imaging technology have led to increased demands on radiologists, Dr. Schilling says. “When we read 2D mammograms, there were two images per breast so I would have been seeing about 400 images a day, 2,000 a week and 80,000 images a year,” she explains. “With 3D, we are seeing 1 mm slices, so up to 280 images per exam, 28,000 a day and 5.6 million images a year. You get very fatigued and mesmerized scrolling through each exam, but you don’t want to miss a cancer.”

AI will never replace radiologists, whose rapport with patients is important, Dr. Schilling says, but the technology and deep-learning abilities make it possible to flag suspicious areas for a more thorough look by the physician.

Dr. Schilling’s study is moving to the next phase, where she will investigate the size and stage of cancers upon diagnosis at Lynn Women’s Health & Wellness Institute pre- and post-AI implementation.

In addition, Dr. Schilling is the local principal investigator for “Contrast-Enhanced Mammography Imaging Screening Trial (CMIST),” a multicenter national trial supported by GE Healthcare and the American College of Radiology. That study is looking at contrast-enhanced mammography in patients with dense breasts. Some 40 percent of women have dense breasts, she says, making it more difficult to detect breast cancer using mammography alone.