AI systems detect twice as many incidental breast lesions on routine CT scans as radiologists.
Key Details
- 1AI algorithms identified twice the number of incidental breast lesions compared to radiologists.
- 2Incidental breast lesions are detected on up to 8% of CT scans including the chest, potentially higher.
- 3Up to 70% of these incidental lesions turn out to be cancerous, highlighting the importance of early detection.
- 4Challenges for radiologists include lower spatial and contrast resolution of CT compared to mammography and MRI, and lesion location or incidental nature.
- 5Findings are from a new paper published in Current Problems in Diagnostic Radiology.
Why It Matters
Early and more frequent detection of incidental breast cancers on routine CT has significant potential to improve patient outcomes. Increasing AI support in imaging workflows could address current blind spots and enhance secondary cancer detection, reducing missed diagnoses.
Source
Health Imaging
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.