A deep-learning model combining radiomics and clinicopathologic data with breast DCE-MRI improves prediction of complete pathological response after chemotherapy.
Key Details
- 1Study led by Chaowei Wu, PhD, at Cedars-Sinai Medical Center.
- 2Model integrates clinicopathologic data, shape radiomics, and retrospective pharmacokinetic quantification radiomics.
- 3Included MRI data from 1,073 breast cancer patients (2002–2016).
- 4Model achieved higher AUCs (up to 0.82 on external datasets) vs. conventional methods.
- 5Reported accuracy 69%, sensitivity 95%, specificity 59%.
- 6Early pCR prediction aids personalized treatment planning.
Why It Matters
Improved prediction of chemotherapy response using AI-driven analysis of DCE-MRI could enable more personalized and effective treatment strategies in breast cancer, potentially improving outcomes. The results show better accuracy and generalizability than existing methods across multiple datasets.
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.