Combining AI with radiologists substantially improves detection of pulmonary embolism (PE) on CT pulmonary angiography (CTPA) scans, new research shows.
Key Details
- 1Researchers retrospectively analyzed 32,500 CTPA exams from over 29,000 adults (2021-2023).
- 2AI and radiologists agreed on PE diagnosis in 97.8% of cases.
- 385% of positive PE cases were flagged by AI and confirmed by radiologists; 15% were found only by radiologists.
- 4Radiologists were correct in 88.7% of the disagreements; AI in 11.3%.
- 5AI-informed radiologists achieved 99.2% sensitivity for PE detection.
- 6Concordance was highest for acute and central emboli, which have the most clinical urgency.
Why It Matters
This study demonstrates that integrating AI with radiologist expertise can improve both the efficiency and accuracy of PE detection, especially for urgent cases. It highlights the necessity of human oversight, illustrating the best results stem from collaborative use rather than AI or radiologist alone.
Source
Radiology Business
Related News
•AuntMinnie
Study: Computer Vision Models Best LLMs in Chest CT Breast Abnormality Detection
Computer vision models (CVMs) surpass large language models (LLMs) in accurately labeling incidental breast abnormalities on chest CT scans.
•Cardiovascular Business
Radiology Maintains Lead in FDA-Cleared AI Algorithms, Cardiology Follows
Radiology remains the top specialty for FDA-cleared AI, with cardiology as a strong second, particularly in cardiovascular imaging.
•AuntMinnie
Deep Learning Models Rival Radiologists for Pancreatic Cancer Detection on CT
Deep-learning models achieved comparable or superior accuracy to experienced radiologists in detecting pancreatic cancer on CT scans, especially for small tumors.