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
Stanford Team Introduces Real-Time AI Safety Monitoring for Radiology
Stanford researchers introduced an ensemble monitoring model to provide real-time confidence assessments for FDA-cleared radiology AI tools.
•Radiology Business
Harrison.ai Receives FDA Breakthrough Status for Imaging AI Device
Harrison.ai has been awarded three FDA breakthrough device designations for its imaging AI solutions, including a tool for obstructive hydrocephalus triage.
•AuntMinnie
Head-to-Head Study Evaluates AI Accuracy in Fracture Detection on X-Ray
A prospective study compared three commercial AI tools for fracture detection on x-ray, showing moderate-to-high accuracy for simple cases but weaker performance in complex scenarios.