Researchers developed an explainable AI model to improve breast cancer detection in MRI with lower false positive rates.
Key Details
- 1AI model was trained on over 10,000 contrast-enhanced breast MRI exams from 2005 to 2022.
- 2The dataset included diverse cases and varying categories of breast density for robust training.
- 3Unlike prior models, this AI was evaluated on both low- and high-prevalence cancer cohorts, improving clinical relevance.
- 4The model features explainability to provide evidence-backed decisions, critical for clinical adoption.
- 5A key aim is to reduce false positive rates, a common issue in breast MRI diagnostics.
Why It Matters
False positives in breast MRI can lead to unnecessary anxiety and follow-up tests. Explainable, robust AI models like this can aid radiologists in accurate cancer detection and support clinical integration through transparency.
Source
Health Imaging
Related News
•AuntMinnie
Paul Chang Discusses Foundation Models and Agentic AI at RSNA 2025
Dr. Paul Chang shares his insights on the role of foundation models and agentic AI in radiology at RSNA 2025.
•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.