An AI model using mammogram images predicts 5-year breast cancer risk more accurately than traditional breast density assessment.
Key Details
- 1The study is presented at the RSNA annual meeting in Chicago.
- 2Clairity Breast, the first FDA-authorized image-only AI breast cancer risk model, was trained on over 421,000 mammograms.
- 3AI model performance was evaluated on more than 245,000 screening mammograms from the US and Europe.
- 4Women in the AI high-risk group had a >4x higher incidence of cancer (5.9%) than average-risk (1.3%), while density-based separation was modest (3.2% vs. 2.7%).
- 5Findings support integrating image-only AI risk scores with traditional risk factors for more personalized screening strategies.
Why It Matters
This research advances precision screening in breast imaging, offering radiologists a more nuanced, data-driven tool for risk stratification. Early identification of high-risk patients via AI could lead to tailored screening protocols and improved outcomes.
Source
EurekAlert
Related News
•EurekAlert
AI-Powered OCT Enables Rapid 'Optical Biopsy' for Early Endometrial Cancer Detection
A team at Washington University has developed a catheter-based 3D OCT system with AI to quickly and noninvasively detect early endometrial cancers.
•EurekAlert
AI Clinical Reasoning in Diagnostics and Digital Fatigue in Healthcare
Recent JMIR features explore large language models in clinical diagnostics and digital fatigue among healthcare professionals.
•EurekAlert
KAIST, MIT, Microsoft Develop Efficient AI Image Upsampling for Robotics
KAIST, MIT, and Microsoft have created 'Upsample Anything,' a training-free AI method to restore high-resolution visual data from compressed images with up to 16x improved GPU memory efficiency.