用多模态信息教轻量CT模型，让癌症分类更准更可解释。
REACT-KD: Region-Aware Cross-modal Topological Knowledge Distillation for Interpretable Medical Image Classification
- 双教师设计：用PET/CT学结构功能，用低剂量CT学剂量敏感特征。
- 在内部数据上达93.5% AUC，低剂量下仍保持76.6%~81.5% AUC。
- 适合临床部署，对缺失或噪声数据有强鲁棒性，医生易信服。
从临床影像中实现可靠且可解释的肿瘤分类仍是核心挑战，主要源于模态质量异质、标注有限及缺乏结构化解剖引导。我们提出REACT-KD，一种区域感知的跨模态拓扑知识蒸馏框架，将高质量多模态源的监督信息迁移到轻量级的CT学生模型。该框架采用双教师设计：一支通过双示踪剂PET/CT捕捉结构-功能关系，另一支利用合成降质的低剂量CT建模剂量敏感特征。两者通过两个互补目标共同指导学生模型：第一项通过logits蒸馏实现语义对齐，第二项通过区域图蒸馏建模解剖拓扑。共享的CBAM3D模块确保跨模态注意力一致。为提升部署可靠性，训练时引入模态丢弃，使模型在部分或噪声输入下仍具鲁棒性。以肝细胞癌分期为例，框架在内部PET/CT队列上平均AUC达93.5%，在外部CT测试中不同剂量降级水平下仍维持76.6%至81.5% AUC。决策曲线分析进一步表明，REACT-KD在所有阈值下均提供最高净临床获益，证实其在真实诊断实践中的价值。代码已开源：https://github.com/Kinetics-JOJO/REACT-KD
原文摘要 · Abstract (English)
Reliable and interpretable tumor classification from clinical imaging remains a core challenge. The main difficulties arise from heterogeneous modality quality, limited annotations, and the absence of structured anatomical guidance. We present REACT-KD, a Region-Aware Cross-modal Topological Knowledge Distillation framework that transfers supervision from high-fidelity multi-modal sources into a lightweight CT-based student model. The framework employs a dual teacher design. One branch captures structure-function relationships through dual-tracer PET/CT, while the other models dose-aware features using synthetically degraded low-dose CT. These branches jointly guide the student model through two complementary objectives. The first achieves semantic alignment through logits distillation, and the second models anatomical topology through region graph distillation. A shared CBAM3D module ensures consistent attention across modalities. To improve reliability in deployment, REACT-KD introduces modality dropout during training, which enables robust inference under partial or noisy inputs. As a case study, we applied REACT-KD to hepatocellular carcinoma staging. The framework achieved an average AUC of 93.5\% on an internal PET/CT cohort and maintained 76.6\% to 81.5\% AUC across varying levels of dose degradation in external CT testing. Decision curve analysis further shows that REACT-KD consistently provides the highest net clinical benefit across all thresholds, confirming its value in real-world diagnostic practice. Code is available at: https://github.com/Kinetics-JOJO/REACT-KD
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。