OEM News

Research Supports Hologic’s AI-Powered Mammography Tech for Detecting Challenging Cancers

Results highlight AI’s potential to help radiologists identify diverse breast cancer subtypes.

By: Michael Barbella

Managing Editor

Photo: Business Wire.

Hologic is sharing new research demonstrating the efficacy of its artificial intelligence (AI)-driven breast cancer detection technologies. The research includes a study focused on invasive lobular cancer.

“Invasive lobular cancers are more challenging to detect on a mammogram because of their unique characteristics,” said Mark Horvath, president of Breast & Skeletal Health Solutions at Hologic. “In the study, AI maintained high sensitivity for flagging these cancers, including some that had been interpreted as negative at a prior screening. These data add to a growing body of evidence that AI can act as a powerful supportive tool for radiologists as they review the full spectrum of breast cancers.”

In this retrospective, single-center study, researchers at Massachusetts General Hospital in Boston reviewed invasive lobular cancer cases diagnosed over a 10-year period and grouped them into two categories—those detected by a radiologist during a routine screening exam (195 total) and “false negatives” that were diagnosed within a year of a routine screening exam initially interpreted as negative (44 total). Researchers then used Hologic’s Genius AI Detection solution to retrospectively analyze all 239 cases. In this cohort, the technology identified and correctly localized close to 90% of the confirmed invasive lobular cancers.1

According to new research, an average of one in 20 women worldwide will be diagnosed with breast cancer in their lifetime and if current rates continue, 3.2 million new breast cancer cases will be diagnosed and 1.1 million breast cancer-related deaths will occur annually by 2050.2 About 10% to 15% of all breast cancers are invasive lobular cancers,3 while ductal cancers that originate in the milk ducts of the breast—such as invasive ductal carcinoma and ductal carcinoma in situ—occur more commonly. Invasive lobular cancer arises in the milk-producing glands (lobules) of the breast and, because of its unique biology and tendency to grow in a linear pattern, it may be more challenging to see on mammography. This may lead to later detection and a more advanced stage at diagnosis.

The AI algorithm also identified 43% of the invasive lobular cancer cases initially interpreted during routine screening as negative.1 Of note, as a retrospective analysis at a single institution, the study did not evaluate the way(s) use of AI in real-time clinical practice would affect recall rates, biopsy outcomes, or patient management.

The MGH study did not assess false-positive rates, recall rates or biopsy outcomes, and its single-center design may limit generalizability. AI performance was evaluated retrospectively and did not influence real-time radiologist decision-making; therefore, the observed gains represent a theoretical upper bound rather than a measured clinical impact. Additionally, the cohort included only patients with invasive lobular cancer, precluding comparison with other histologic subtypes.

Hologic’s Genius AI Detection solution is a mammography screening technology that locates lesions likely to represent breast cancer. Suspicious areas are highlighted at radiologists’ workstations for concurrent reading to support smart, decisive interpretation. Hologic’s deep learning algorithm is fed by the accumulation of a large, diverse patient base, providing rich insight and intelligence.

Hologic Inc. develops medical technologies that detect, diagnose, and treat health women’s health conditions and raise the standard of care.

References
1 Lamb LR, Kim H, Do S, Bahl M. Artificial intelligence for the detection of invasive lobular carcinoma on screening digital breast tomosynthesis. Oral presentation, Society of Breast Imaging Symposium, Seattle, WA, April 2026.
2 Kim J, Harper A, McCormack V, et al. Global patterns and trends in breast cancer incidence and mortality across 185 countries. Nature Medicine. 2025;31(4). doi:https://doi.org/10.1038/s41591-025-03502-3.
3 DePolo J. Invasive Lobular Carcinoma (ILC). www.breastcancer.org. https://www.breastcancer.org/types/invasive-lobular-carcinoma.

Keep Up With Our Content. Subscribe To Medical Product Outsourcing Newsletters