Hologic Presents New Breast Imaging AI Research and Solutions

Hologic, Inc. presented new research demonstrating the performance of its Genius AI Detection 2.0 software across diverse patient populations at RSNA 2024.

“Clinicians across the United States have been leveraging AI solutions in breast cancer screening for many years to drive both clinical and efficiency improvements; however, it’s widely understood that AI algorithms can exhibit racial disparities in a variety of applications,” said Sarah M. Friedewald, MD, Vice Chair for Women’s Imaging, Department of Radiology, Northwestern Feinberg School of Medicine. “This research was a critical step in increasing clinical confidence in this particular AI solution’s ability to deliver results that are not materially impacted by racial bias.”

The research, titled “Performance of a Digital Breast Tomosynthesis AI Detection Algorithm in Common U.S. Racial/Ethnic Groups,” evaluated the performance of Hologic’s Genius AI Detection 2.0 solution in more than 7,500 digital breast tomosynthesis (DBT) cases from women who identified as Asian, Black, Hispanic or white. Researchers found that the measured performance of the algorithm was similar across all evaluated cohorts.

“We know that significant racial disparities exist in breast cancer screening and treatment; for example, studies have shown that alarmingly, Black women in the US have a 40% higher death rate from breast cancer compared with white women,” said Erik Anderson, President, Breast and Skeletal Health Solutions, Hologic. “As a leader in women’s health, we are deeply committed to providing clinicians with effective, equitable solutions to advance the detection of breast cancer globally. A key part of that is ensuring that our customers can rely on our technology to perform effectively for all patients regardless of race, ethnicity or background.”

Further demonstrating its leadership in breast imaging AI, Hologic is also introducing its next-generation Genius AI Detection PRO solution for use in the US. This advanced cancer screening technology expands on Hologic’s Genius AI Detection 2.0 solution by providing even greater accuracy and efficiency, giving radiologists more confidence and helping to reduce false positives. This new AI assistant provides:

• A deep-learning 2D and 3D algorithm that improves specificity by using a patient’s prior exam in the current exam’s analysis.
• Intuitive 1-10 case and lesion scoring and pre-populated exam reports designed to accelerate image review and save radiologists’ valuable time.
• An all-in-one interface that conveniently includes deep-learning breast density scoring along with key patient and mammogram quality information, designed to support radiologists at every step of the reading workflow.

Also, Hologic showcased the Envision Mammography Platform, which offers patients a high-speed Hologic 3D™ mammogram with a 2.5-second scan time. This next-generation technology provides a more comfortable exam with tilt positioning, adapting to patients rather than the other way around. The Envision platform enhances the detection of subtle objects, minimizes focal spot blur and improves 3D image sharpness.

“There is tremendous excitement surrounding our latest breast health innovations, and our team is looking forward to showcasing the many ways we’re advancing solutions across the breast health continuum at this year’s RSNA,” said Anderson. “Through strong customer relationships, continuous improvement and the latest research, we continue to take our leading technologies to the next level to support healthcare providers in improving the patient experience and providing excellent care.”