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
Deep Learning AI Outperforms Radiologists in Detecting ENE on CT
A deep learning tool, DeepENE, exceeded radiologist performance in identifying lymph node extranodal extension in head and neck cancers using preoperative CT scans.
•Radiology Business
Patients Favor AI in Imaging Diagnostics, Hesitate on Triage Use
Survey finds most patients support AI in diagnostic imaging but are reluctant about its use in triage decisions.
•AuntMinnie
AI Projected to Reshape Radiologist Workload But Not Eliminate Jobs
Stanford researchers predict AI could reduce radiologist hours by up to 49% over the next five years, though workforce size is likely to remain stable due to rising imaging demand.