AI-driven quantification of breast arterial calcification (BAC) on mammograms predicts risk of major cardiovascular events in women, independent of traditional risk scores.
Key Details
- 1Study used a transformer-based segmentation model to quantify BAC on mammograms from 123,762 women across Emory Healthcare and Mayo Clinic Enterprise.
- 2BAC severity (mild, moderate, severe) was associated with incrementally higher hazard ratios for major adverse cardiovascular events (up to HR 3.29 for severe BAC in the Emory cohort).
- 3Incidence of major cardiovascular events increased more than 8-fold from zero to severe BAC category in the Emory cohort.
- 4Dose-response noted: each 1 mm² increase in BAC conferred an additional 2–3% risk for major events (p < 0.001).
- 5AI-derived BAC scores add prognostic value beyond the PREVENT cardiovascular risk calculator, offering a non-invasive risk assessment using existing mammogram data.
Why It Matters
Opportunistically assessing cardiovascular risk in women using routine mammograms through AI enables earlier prevention without extra imaging or radiation, potentially transforming population health strategies and radiology's role in preventive care.
Source
AuntMinnie
Related News
•Radiology Business
AI Tool Dramatically Reduces Breast MRI Scan Time
A new AI-enabled MRI technique significantly speeds up breast imaging while enhancing image quality and tumor detection.
•AuntMinnie
Study: Computer Vision Models Best LLMs in Chest CT Breast Abnormality Detection
Computer vision models (CVMs) surpass large language models (LLMs) in accurately labeling incidental breast abnormalities on chest CT scans.
•AuntMinnie
Deep Learning Models Rival Radiologists for Pancreatic Cancer Detection on CT
Deep-learning models achieved comparable or superior accuracy to experienced radiologists in detecting pancreatic cancer on CT scans, especially for small tumors.