Photographs in a 42-year-old asymptomatic lady. Credit score: Radiology (2025). DOI: 10.1148/radiol.242408
A Korean analysis workforce has reported that synthetic intelligence (AI) utilized in mammography missed 14% of invasive breast cancers, the sort the place delayed analysis can instantly influence affected person survival.
Breast most cancers is assessed into ductal carcinoma in situ (stage 0) and invasive most cancers (levels 1–4). Whereas prior research have estimated the general false‑destructive charge of AI‑assisted mammography for all breast cancers at about 19.4%, its efficiency in invasive cancers has remained a essential query.
Researchers from the Breast Middle at Korea College Faculty of Medication—Professor Sungeun Music (Division of Radiology, Korea College Anam Hospital) and Professor Okhee Woo (Division of Radiology, Korea College Guro Hospital)—analyzed 1,097 breast most cancers circumstances recognized between 2014 and 2020 utilizing a commercially obtainable Korean AI program (Lunit Perception MMG).
The AI missed 17.2% of luminal‑sort cancers, 14.5% of triple‑destructive cancers, and 9% of HER2‑optimistic cancers. Missed invasive cancers tended to happen in youthful girls, had tumors 2 cm or smaller, decrease histologic grade, fewer lymph node metastases, low Ki‑67 expression, had been positioned exterior glandular areas, and infrequently fell into BI‑RADS class 4. Dense breast tissue, non‑glandular tumor location, structural distortion, and microcalcifications had been the commonest causes for missed detection. Notably, 61.7% of those cancers had been thought of detectable by radiologists.
“While AI shows strong performance in detecting breast cancer, our findings highlight the need for continuous oversight and complementary work by radiologists,” mentioned Professor Music. “Knowing the features of invasive cancers that AI tends to miss will be key to improving both clinical use and future development of AI tools.”
The research, titled “Invasive Breast Cancers Missed by AI Screening of Mammograms”, seems within the Radiology.
Extra info:
Okay Hee Woo et al, Invasive Breast Cancers Missed by AI Screening of Mammograms, Radiology (2025). DOI: 10.1148/radiol.242408
Offered by
Korea College Faculty of Medication
Quotation:
AI efficient at detecting superior breast most cancers, however misses some circumstances (2025, September 2)
retrieved 2 September 2025
from https://medicalxpress.com/information/2025-09-ai-effective-advanced-breast-cancer.html
This doc is topic to copyright. Other than any honest dealing for the aim of personal research or analysis, no
half could also be reproduced with out the written permission. The content material is offered for info functions solely.
