AI misses 14% of invasive breast cancers on mammography, with luminal cancers and dense tissue posing significant challenges.
Key Details
- 1Study analyzed 1,097 breast cancers from 1,082 women using Lunit Insight MMG AI between 2014–2020.
- 2AI missed 154 cancers (14%), often in younger women with smaller (<2 cm), lower-grade tumors and dense breasts.
- 3Missed cancers were more likely luminal subtype (false-negative rate 17.2%), compared to HER2-enriched (9%) and triple-negative (14.5%).
- 4Major reasons for AI misses included dense breast tissue (n=56), nonmammary zone location (n=22), architectural distortion (n=12), and amorphous calcifications (n=5).
- 561.7% of AI-missed cancers were deemed 'actionable' on further review by radiologists.
Why It Matters
Understanding which cancer features are often overlooked by AI tools enables radiologists to better interpret AI results, reducing missed diagnoses. These insights highlight the continued importance of human expertise in mammography, especially for high-risk groups like women with dense breast tissue.
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.