ClinRAG-GRAPH: Clinical-prior Retrieval-Augmented Graph Model with Domain Adversarial Learning for Breast pCR Prediction
2026-07-01 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a method called ClinRAG-GRAPH to better predict how well breast cancer patients will respond to chemotherapy before treatment starts. Their approach combines MRI scans, clinical data, and biopsy information into a network that learns important patterns while reducing differences caused by various imaging centers. They also use a language model to find similar past cases, helping to explain their predictions. Tests on data from multiple centers showed their method works reliably across different hospitals.
Neoadjuvant chemotherapyPathological complete responseDCE-MRIGraph convolutional networkDomain-adversarial learningMultimodal representationLarge language modelRetrieval-augmented generationCross-center validation
Authors
Yaofei Duan, Yuhao Huang, Tianyu Zhang, Yuan Gao, Luyi Han, Xin Wang, Xinyu Xie, Xinglong Liang, Chunyao Lu, Muzhen He, Patrick Pang, Yue Sun, Ning Mao, Tao Tan, Ritse Mann
Abstract
Neoadjuvant chemotherapy (NAC) response prediction is clinically important for treatment stratification in breast cancer. However, robust pre-treatment pathological complete response (pCR) prediction remains challenging due to insufficient cross-modal modeling, multicenter imaging heterogeneity, and weak evidence-grounded interpretability. We propose ClinRAG-GRAPH, a Clinically informed Retrieval-Augmented Generation Graph framework, for pre-treatment pCR prediction from DCE-MRI, structured clinical variables, and biopsy-derived pathological biomarkers. ClinRAG-GRAPH constructs an intra-patient clinical-prior graph and applies a prior-guided relation-aware graph convolutional network for structured multimodal representation learning. To improve cross-center robustness, we introduce a dual-branch domain-adversarial learning strategy to suppress protocol-related MRI bias while preserving pCR-relevant features. To enhance interpretability, we further incorporate large language model (LLM)-driven subgraph RAG module that retrieves clinically analogous historical cases and integrates retrieved evidence for pCR inference. We assemble a large-scale multicenter NAC breast cancer cohort for extensive validation, drawing from two public sources and three in-house centers.Results show that ClinRAG-GRAPH achieves AUCs of 0.815 on the internal test set and 0.774/0.712 on two external test sets, demonstrating robust pre-treatment pCR prediction across centers. The code is available at the anonymized https://github.com/miccai26-1181/ClinRAG-GRAPH.