A deep learning algorithm accurately quantifies coronary artery calcium (CAC) on routine nongated chest CT scans, offering significant potential for opportunistic cardiovascular risk assessment.
Key Details
- 1The AI-CAC algorithm analyzes noncontrast, nongated chest CTs, typically not used for CAC scoring.
- 2Study used data from 98 VA medical centers, comparing results from 795 patients with paired gated CTs.
- 3AI-CAC had 89.4% accuracy at detecting CAC and 87.3% accuracy at categorizing CAC above or below the score of 100.
- 4CAC scores above 400 indicated a 3.49-fold higher risk of 10-year all-cause mortality compared to a score of 0.
- 5Nearly all patients flagged by the model for high CAC would benefit from lipid-lowering therapy per cardiologist review.
- 6Opportunistic screening tested on 8,052 low-dose CT scans and highlights value for population health.
Why It Matters
This research paves the way for leveraging existing routine CT scans to opportunistically assess heart disease risk, enabling earlier intervention and proactive patient management. Broad AI adoption could convert millions of non-dedicated chest CT exams into valuable tools for cardiovascular prevention.
Source
AuntMinnie
Related News
•AuntMinnie
Paul Chang Discusses Foundation Models and Agentic AI at RSNA 2025
Dr. Paul Chang shares his insights on the role of foundation models and agentic AI in radiology at RSNA 2025.
•AuntMinnie
Toronto Study: LLMs Must Cite Sources for Radiology Decision Support
University of Toronto researchers found that large language models (LLMs) such as DeepSeek V3 and GPT-4o offer promising support for radiology decision-making in pancreatic cancer when their recommendations cite guideline sources.
•AuntMinnie
AI Model Using Mammograms Enhances Five-Year Breast Cancer Risk Assessment
A new image-only AI model more accurately predicts five-year breast cancer risk than breast density alone, according to multinational research presented at RSNA 2025.