Sept. 26, 2025 — Data from two groundbreaking studies evaluating the performance of Hologic’s artificial intelligence (AI)-powered mammography technology was presented recently at the European Society of Breast Imaging (EUSOBI) Annual Scientific Meeting in Aberdeen, Scotland.
“These results underscore AI’s ability to make breast cancer screening more accurate and efficient, and its potential to provide valuable insights about each patient’s unique tumor biology,” said Mark Horvath, President, Breast and Skeletal Health Solutions at Hologic. “We’re proud to work with top researchers around the world to continue to advance this technology and improve care for women everywhere.”
The first study, conducted at Massachusetts General Hospital in the U.S., aimed to evaluate whether AI scores on 3D mammography (digital breast tomosynthesis) screening exams are associated with tumor characteristics, including histologic grade and lymph node status. Researchers retrospectively analyzed approximately 600 exams performed between 2016 and 2019 using Hologic’s Genius AI® Detection 2.0 mammography solution. All cases were biopsy-proven cancers; 80% were invasive and 20% were ductal carcinoma in situ (DCIS).
To indicate the likelihood that breast cancer is present, the Genius AI Detection technology assigns a score to each suspicious lesion on an exam and then takes all the scores together to create an overall “case score.” A score between 51% and 75% corresponds to a 1 in 61 likelihood of cancer, while a case score between 76% and 100% corresponds to a 1 in 27 likelihood. In the study, AI case scores were higher for higher-grade tumors and node-positive cancers — features associated with more aggressive disease.
“AI is quickly becoming a valuable second set of eyes for radiologists, helping to flag cancers sooner, and our study suggests an added benefit of identifying those that are more likely to be aggressive,” said Dr. Manisha Bahl, M.D., MPH, FSBI, Associate Medical Director of Quality at Mass General Brigham and Associate Professor of Radiology at Harvard Medical School, who will be presenting the results at EUSOBI. “These findings are noteworthy because, for patients with more aggressive cancers, earlier detection allows treatment to begin sooner, which can improve clinical outcomes.”
The second study, presented by Professor Yan Chen, Ph.D., Chair of Digital Screening and Head of the Digital Cancer Screening Research Group at the University of Nottingham, UK, tested how well Hologic’s Genius AI Detection solution performed compared with radiologists. In this study, 108 radiologists from the UK and U.S. reviewed 75 clinically challenging breast cancer cases. The AI system also read the same cases.
The AI technology demonstrated similar performance to radiologists in finding cancers, with higher sensitivity but lower specificity. While the study is ongoing, these early results suggest AI could be a useful tool in helping radiologists diagnose breast cancer early. In many countries, each mammogram is checked by two radiologists and workforce shortages can make this difficult. These findings show AI’s potential to help fill this gap.
In addition to its AI-powered technologies, Hologicshowcased its latest breast surgery innovations at EUSOBI, including the next-generation Sentimag Gen 3 device for tumor localization and breast cancer staging. The product was developed by UK-based acquisition Endomag and was launched in Europe earlier this year.
Hologic will host multiple education sessions and workshops throughout the congress.
To learn more, visit www.hologic.com.
November 17, 2025 
