English(EN) ClinRAG-GRAPH: Clinical-prior Retrieval-Augmented Graph Model with Domain Adversarial Learning for Breast pCR Prediction

AI模型ClinRAG-GRAPH改进乳腺癌pCR预测

作者 PulseAugur 编辑部 · [2 个来源] · 2026-07-01 11:28

研究人员开发了ClinRAG-GRAPH，一个用于预测接受新辅助化疗的乳腺癌患者病理完全缓解（pCR）的新型框架。该模型使用图卷积网络整合了包括DCE-MRI、临床变量和病理生物标志物在内的多模态数据。为了解决多中心成像的异质性，采用了领域对抗学习策略来减轻MRI协议偏差。此外，一个由LLM驱动的检索增强生成模块通过引用类似的既往病例进行pCR推断，增强了可解释性。该框架在多个数据集上表现出稳健的性能，在内部测试集上达到了0.815的AUC，在外部测试集上达到了0.774/0.712的AUC。 AI

影响该模型可以通过改进治疗前反应预测来增强乳腺癌患者的治疗分层。

排序理由该集群描述了一篇详细介绍用于特定医学预测任务的新AI模型的新研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CV TIER_1 English(EN) · 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 · 2026-07-02 04:00

ClinRAG-GRAPH: Clinical-prior Retrieval-Augmented Graph Model with Domain Adversarial Learning for Breast pCR Prediction

arXiv:2607.00798v1 Announce Type: new 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 insuf…
arXiv cs.CV TIER_1 English(EN) · Ritse Mann · 2026-07-01 11:28

ClinRAG-GRAPH：基于领域对抗学习的临床先验检索增强图模型用于乳腺pCR预测

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 imagin…

报道来源 [2]

ClinRAG-GRAPH: Clinical-prior Retrieval-Augmented Graph Model with Domain Adversarial Learning for Breast pCR Prediction

ClinRAG-GRAPH：基于领域对抗学习的临床先验检索增强图模型用于乳腺pCR预测

相关实体

相关话题