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
Toronto Study: LLMs Must Cite Sources for Radiology Decision Support
University of Toronto researchers found that large language models (LLMs) such as DeepSeek V3 and GPT-4o offer promising support for radiology decision-making in pancreatic cancer when their recommendations cite guideline sources.
•AuntMinnie
AI Model Using Mammograms Enhances Five-Year Breast Cancer Risk Assessment
A new image-only AI model more accurately predicts five-year breast cancer risk than breast density alone, according to multinational research presented at RSNA 2025.
•Radiology Business
AI Model Uses CT Scans to Reveal Biomarker for Chronic Stress
Researchers developed an AI model to measure chronic stress using adrenal gland volume on routine CT scans.