AI triaging halved breast MRI scan times while preserving diagnostic performance, enabling efficient, adaptive imaging workflows.
Key Details
- 1Simulation study analyzed retrospective data from 863 women (1,423 MRI exams); 51 breast cancers diagnosed within 12 months.
- 2AI-directed triaging assigned about 50% of exams to an abbreviated protocol based on real-time suspicion scoring.
- 3Diagnostic performance: Sensitivity (AI triage 88.2%, conventional 86.3%); specificity (AI triage 80.8%, conventional 81.4%).
- 4Cancer detection rates were nearly identical (31.6 vs 30.9 per 1,000 exams); interval cancer rates slightly improved with AI triaging (4.2 vs 4.9 per 1,000).
- 5No cases were missed by abbreviated MRI that would have been detected by the full protocol.
- 6Study highlights potential for workflow efficiency and personalized MRI acquisition.
Why It Matters
This approach could make high-volume breast MRI screenings more efficient, reducing scan and patient time without sacrificing cancer detection. It marks a step toward adaptive, AI-driven imaging protocols and improved resource utilization in breast imaging.
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.