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
Machine Learning Model Enhances Risk Stratification for Prostate MRI
Researchers developed machine learning models that outperform PSA testing in predicting abnormal prostate MRI findings for suspected prostate cancer.
•AuntMinnie
AI's Evolving Role in Tackling Radiology Workforce Shortages
AI technologies are emerging as key tools to alleviate radiology workforce shortages by improving efficiency and supporting clinical workflows.
•Radiology Business
Multimodal LLMs Struggle with Radiology Board Image Questions
Latest multimodal large language models show limitations on image-based radiology exam questions.