Certain breast cancer types, like luminal cancer and those in dense breasts, are more likely to be missed by AI in mammography screening.
Key Details
- 1South Korean researchers reviewed breast images from nearly 1,100 women screened between 2014 and 2020.
- 2AI tools were found to miss cancers with features such as luminal subtype, dense breast tissue, and lesions outside the mammary zone.
- 3The study was published in RSNA's journal Radiology.
- 4Experts urge careful assessment of cases at higher risk of AI error.
Why It Matters
Understanding which cancers AI is most likely to miss can help optimize AI integration into breast imaging workflows, ensuring that radiologists remain vigilant in specific high-risk contexts. This research offers guidance to improve both detection and patient outcomes.
Source
Radiology Business
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.