基于解剖结构的专家混合模型，提升肺间质病诊断准确率
REN: Anatomically-Informed Mixture-of-Experts for Interstitial Lung Disease Diagnosis
- 按肺叶分区训练7个专用专家，融合解剖先验知识
- 多模态门控机制加权专家贡献，使平均AUC达0.8646，提升12.5%
- 适用于肺部影像分析，尤其适合关注区域病变模式的临床研究
混合专家（MoE）架构通过条件计算将输入路由至特定子网络实现可扩展学习。但传统MoE假设专家能力同质且路由无领域差异，与医学影像中解剖结构和区域疾病异质性决定病理特征的本质相悖。我们提出区域专家网络（REN），首个面向医学图像分类的解剖引导型MoE框架。REN通过训练7个专用专家，分别对应不同肺叶或双侧肺组合，精准建模区域特异性病理变化。多模态门控机制动态融合放射组学生物标志物与卷积神经网络（CNN）、Transformer（ViT）及状态空间模型（Mamba）提取的深度学习特征，以权重分配专家贡献。在包含597名患者、1,898次扫描的纵向队列上应用于肺间质病（ILD）分类，REN表现持续领先：放射组学引导的集成模型平均AUC达0.8646 ± 0.0467，较SwinUNETR单模型基线（AUC 0.7685，p=0.031）提升12.5%。下叶专家表现最优，AUC达0.88–0.90，优于深度学习基线（CNN: 0.76–0.79），与已知的基底肺部纤维化进展模式一致。经严格的患者级交叉验证，REN展现出强泛化能力与临床可解释性，建立了一种可扩展、解剖引导的框架，有望推广至其他结构化医学影像任务。代码已开源于GitHub：https://github.com/NUBagciLab/MoE-REN。
原文摘要 · Abstract (English)
Mixture-of-Experts (MoE) architectures achieve scalable learning by routing inputs to specialized subnetworks through conditional computation. However, conventional MoE designs assume homogeneous expert capability and domain-agnostic routing-assumptions that are fundamentally misaligned with medical imaging, where anatomical structure and regional disease heterogeneity govern pathological patterns. We introduce Regional Expert Networks (REN), the first anatomically-informed MoE framework for medical image classification. REN encodes anatomical priors by training seven specialized experts, each dedicated to a distinct lung lobe or bilateral lung combination, enabling precise modeling of region-specific pathological variation. Multi-modal gating mechanisms dynamically integrate radiomics biomarkers with deep learning (DL) features extracted by convolutional (CNN), Transformer (ViT), and state-space (Mamba) architectures to weight expert contributions at inference. Applied to interstitial lung disease (ILD) classification on a 597-patient, 1,898-scan longitudinal cohort, REN achieves consistently superior performance: the radiomics-guided ensemble attains an average AUC of 0.8646 +- 0.0467, a +12.5 % improvement over the SwinUNETR single-model baseline (AUC 0.7685, p=0.031). Lower-lobe experts reach AUCs of 0.88-0.90, outperforming DL baselines (CNN: 0.76-0.79) and mirroring known patterns of basal ILD progression. Evaluated under rigorous patient-level cross-validation, REN demonstrates strong generalizability and clinical interpretability, establishing a scalable, anatomically-guided framework potentially extensible to other structured medical imaging tasks. Code is available on our GitHub https://github.com/NUBagciLab/MoE-REN.
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。