AI and radiologists differ in the types and patient characteristics of false-positive findings in digital breast tomosynthesis breast cancer screening.
Key Details
- 1Study included 2,977 women (average age 58) and 3,183 DBT exams (2013–2017) from UCLA.
- 2AI-only false positives mostly flagged benign calcifications (40%), while radiologists mostly flagged masses (47%).
- 3AI and radiologists had nearly identical false-positive rates: 9.7% (AI) vs. 9.5% (radiologists).
- 4Of 541 false-positive exams, 43% were AI-only, 44% were radiologist-only, and 13% were flagged by both.
- 5AI-only false positives occurred in older women (average 60 years), less often with dense breasts (24%), and more often with prior surgical history (37%).
- 6Concordant (AI-radiologist) flagged findings needing biopsy were high-risk in 44% of cases.
Why It Matters
Identifying how AI and radiologists differ in false-positive findings can inform the design of AI tools to improve screening specificity and reduce unnecessary recalls, directly impacting efficiency and patient care in breast imaging.
Source
AuntMinnie
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.
•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.
•Radiology Business
Radiology AI Devices at Elevated Risk for FDA Recalls, Study Finds
Radiology AI devices are more likely to face FDA recalls, largely due to deviations from intended use and incomplete clinical data.