{"ID":5551737,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T11:27:09.201833898Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00798","arxiv_id":"2607.00798","title":"ClinRAG-GRAPH: Clinical-prior Retrieval-Augmented Graph Model with Domain Adversarial Learning for Breast pCR Prediction","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.","short_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-groun...","url_abs":"https://arxiv.org/abs/2607.00798","url_pdf":"https://arxiv.org/pdf/2607.00798v1","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\"]","published":"2026-07-01T11:28:01Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"RAG\",\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":613835,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-02T01:54:51.863792489Z","DeletedAt":null,"paper_id":5551737,"paper_url":"https://arxiv.org/abs/2607.00798","paper_title":"ClinRAG-GRAPH: Clinical-prior Retrieval-Augmented Graph Model with Domain Adversarial Learning for Breast pCR Prediction","repo_url":"https://github.com/miccai26-1181/ClinRAG-GRAPH","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}