Hologic, Inc. (Nasdaq: HOLX) presented new research at the 110th Scientific Assembly and Annual Meeting of the Radiological Society of North America (RSNA), showcasing the performance of its Genius AI® Detection 2.0 software across diverse patient populations.
Artificial intelligence (AI) is playing an increasingly important role in breast cancer diagnosis, as well as in assessing a patient’s risk and breast density. The development of AI algorithms begins with the collection of large, high-quality patient data and images, which are used to train and test these algorithms. It is crucial that these data sets reflect the racial and ethnic diversity found across the United States. This ensures that the algorithms minimize biases and avoid creating disparities that could negatively impact specific patient groups.
“Clinicians across the United States have been using AI in breast cancer screening for many years to enhance clinical outcomes and improve efficiency. However, it’s well recognized that AI algorithms can sometimes exhibit racial disparities,” said Dr. Sarah M. Friedewald, Vice Chair for Women’s Imaging at Northwestern Feinberg School of Medicine. “This research is a key step in building confidence in this AI solution’s ability to produce results that are not significantly affected by racial bias.”
The research, titled “Performance of a Digital Breast Tomosynthesis AI Detection Algorithm in Common U.S. Racial/Ethnic Groups,” focused on Hologic’s Genius AI Detection 2.0 software. The study evaluated its performance in over 7,500 digital breast tomosynthesis (DBT) cases from women of different racial and ethnic backgrounds, including Asian, Black, Hispanic, and White groups. The findings showed that the algorithm performed similarly across all groups, ensuring its effectiveness for a wide range of patients.
Erik Anderson, President of Breast and Skeletal Health Solutions at Hologic, emphasized the importance of addressing racial disparities in breast cancer care. “Racial disparities in breast cancer screening and treatment are well-documented. For instance, Black women in the U.S. face a 40% higher death rate from breast cancer compared to White women,” Anderson said. “As a leader in women’s health, Hologic is committed to providing solutions that help clinicians detect breast cancer more effectively and equitably, ensuring our technology works for all patients, regardless of their race or ethnicity.”
In addition to its advancements with Genius AI Detection 2.0, Hologic is introducing the next-generation Genius AI Detection PRO solution. This upgraded AI technology builds on the capabilities of its predecessor, offering enhanced accuracy and efficiency. The new solution is designed to reduce false positives and provide radiologists with greater confidence in their findings. Key features include:
- A deep-learning algorithm that improves specificity by analyzing a patient’s prior exams alongside the current one.
- Intuitive case and lesion scoring, as well as pre-populated exam reports, to help streamline the image review process.
- An integrated interface that includes breast density scoring and essential patient information, enhancing the overall workflow for radiologists.
Hologic remains dedicated to improving breast cancer screening worldwide and advancing technologies that support clinicians in their efforts to deliver better care for all patients.
For more information about Hologic’s presence at RSNA 2024, visit Hologic.com/RSNA.
About Hologic, Inc.
Hologic, Inc. is a global leader in women’s health, dedicated to developing innovative technologies that detect, diagnose, and treat health conditions, raising the standard of care worldwide.
