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
•AuntMinnie
ChatGPT Demonstrates High Diagnostic Agreement on FDG-PET/CT Reports
ChatGPT-4o and ChatGPT-5 matched or surpassed nuclear medicine experts in diagnosing neurodegenerative diseases using textual FDG-PET/CT scan descriptions.
•Radiology Business
Radiologists Prefer Domain-Specific AI for CT Report Generation
Radiologists show a clear preference for domain-specific AI models in generating accurate and timely CT report impressions.
•AuntMinnie
German Researchers Release Large ICU Chest X-ray Dataset for AI
A German team has released TAIX-Ray, a massive bedside chest x-ray dataset supporting AI development for pathology detection in ICU settings.