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
Machine Learning Model Enhances Risk Stratification for Prostate MRI
Researchers developed machine learning models that outperform PSA testing in predicting abnormal prostate MRI findings for suspected prostate cancer.
•AuntMinnie
AI's Evolving Role in Tackling Radiology Workforce Shortages
AI technologies are emerging as key tools to alleviate radiology workforce shortages by improving efficiency and supporting clinical workflows.
•Radiology Business
Multimodal LLMs Struggle with Radiology Board Image Questions
Latest multimodal large language models show limitations on image-based radiology exam questions.