New research presented at the European Congress of Radiology (ECR) conference highlights the significant role of image-based artificial intelligence (AI) models in mammography screening for assessing short-term breast cancer risk. The findings demonstrate AI’s potential to enhance precision screening and provide critical insights into broader health risks, such as cardiovascular disease.
AI Models Improve Breast Cancer Risk Prediction
A study involving over 8,000 women, including 780 diagnosed with incident breast cancer, evaluated AI-based risk models for digital mammography and digital breast tomosynthesis (DBT). The results showed that these models, namely ProFound AI Risk (iCAD), predicted 40% and 48% of future breast cancer cases in high-risk women, respectively.
According to lead study author Emily Conant, M.D., professor emeritus in the Department of Radiology at the Hospital of the University of Pennsylvania, the research focuses on short-term risk assessment, which is crucial for guiding precision screening strategies.
“Who needs what? How often? … How can we really use this information, this risk based on the image qualities, to drive precision screening better than we’re doing it right now?” Dr. Conant emphasized.
Breast Arterial Calcification Detection and Its Broader Health Implications
In addition to risk assessment, researchers also explored the use of AI algorithms to detect breast arterial calcification (BAC) in mammograms. The study found that the AI algorithm achieved a 98% case-level AUC for BAC detection, demonstrating its high accuracy.
Dr. Conant highlighted the importance of this finding, noting that mammograms can provide more than just breast cancer risk assessments.
“I think the fact that the mammogram shows more than just, you know, breast cancer and risk for future breast cancer, short-term risk, long-term risk, but can also help sort of triage women who are at higher cardiac risk. That’s really huge,” she stated.
While the study results are promising, Dr. Conant emphasized the need for further research, including prospective studies, to validate these findings and refine AI’s role in mammographic screening.
The Future of AI in Mammography
The rapid advancements in AI-powered mammography underscore its potential to revolutionize breast cancer detection and expand its use in broader health screenings. With ongoing studies and increasing adoption of AI technologies, precision screening can become more effective, benefiting both early cancer detection and cardiovascular risk assessment.
The research aligns with previous findings that show AI’s effectiveness in improving breast cancer detection rates and enhancing recall decision-making. As AI continues to evolve, its integration into mammographic screening is expected to offer more refined and personalized healthcare solutions.
