An AI algorithm enhanced radiologists' detection of incidental pulmonary emboli (IPE) on routine contrast-enhanced CT studies.
Key Details
- 1Study assessed 14,453 contrast-enhanced outpatient CT chest/abdomen/pelvis exams for IPEs using Aidoc's AI algorithm.
- 2AI detected 224 IPE cases, 36 of which radiologists missed; these were mostly small and distal emboli.
- 3AI missed 30 IPEs that radiologists found, most being small, with one large central embolus missed.
- 4Radiologist re-review of 1,400 negative cases found 8 additional IPEs missed initially.
- 5Specificity for identifying IPE: 65.1% for radiologists, 66.9% for AI, and 75.8% when combined.
- 6AI showed similar sensitivity as radiologists but a lower positive predictive value; false positive rate noted.
Why It Matters
Automated AI second reads can improve detection of incidental findings on routine CT exams, suggesting a synergistic workflow where AI and human expertise together outperform either alone. This has potential clinical impact for patient outcomes and radiology practice, though current AI tools require continued human oversight.
Source
AuntMinnie
Related News
•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.
•Radiology Business
AI Model Uses CT Scans to Reveal Biomarker for Chronic Stress
Researchers developed an AI model to measure chronic stress using adrenal gland volume on routine CT scans.