Adding MRI to a multimodal AI model significantly improves breast cancer detection and risk prediction.
Key Details
- 1NYU Langone researchers evaluated a transformer AI model using mammography, DBT, ultrasound, breast MRI, and clinical variables.
- 2The training set included 1.3 million exams from 274,388 women (2010–2022).
- 3A separate test cohort comprised 1,944 women with 18,201 exams.
- 4Without MRI input, the AUROC for 5-year cancer risk prediction was 0.899; with MRI, it increased to 0.94.
- 5Improved model performance allows better identification of high-risk women for screening and prevention.
Why It Matters
This work demonstrates that integrating MRI with other imaging modalities in AI models can meaningfully enhance risk stratification and detection accuracy for breast cancer. Such advances support precision medicine, enabling more targeted screening and preventive interventions in clinical radiology.
Source
AuntMinnie
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.