融合临床先验与多模态数据，提升乳腺癌新辅助化疗疗效预测准确率。
ClinRAG-GRAPH: Clinical-prior Retrieval-Augmented Graph Model with Domain Adversarial Learning for Breast pCR Prediction
- 构建患者内临床先验图，结合图神经网络学习多模态特征
- 跨中心AUC达0.712~0.815，显著提升模型鲁棒性
- 引入LLM检索相似病例增强可解释性，适合临床决策支持
新辅助化疗（NAC）疗效预测对乳腺癌治疗分层具有重要临床意义。然而，由于跨模态建模不足、多中心影像异质性以及证据驱动的可解释性弱，术前病理完全缓解（pCR）预测仍具挑战。本文提出ClinRAG-GRAPH，一个基于临床先验的检索增强生成图模型，用于从DCE-MRI、结构化临床变量和活检病理生物标志物中预测术前pCR。该模型构建患者内临床先验图，并采用先验引导的关系感知图卷积网络进行结构化多模态表征学习。为提升跨中心鲁棒性，引入双分支域对抗学习策略，抑制协议相关MRI偏差的同时保留与pCR相关的特征。为进一步增强可解释性，集成大语言模型（LLM）驱动的子图RAG模块，检索临床相似历史病例并整合证据进行pCR推断。我们构建了大规模多中心NAC乳腺癌队列用于验证，涵盖两个公开来源及三个院内中心。结果表明，ClinRAG-GRAPH在内部测试集上达到AUC 0.815，外部测试集分别为0.774和0.712，展现出跨中心稳健的术前pCR预测能力。代码已开源：https://github.com/miccai26-1181/ClinRAG-GRAPH。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。