Research
Hierarchical MoE for Multi-Modal ILD Diagnosis
arXiv:2608.25261v1 Announce Type: cross Abstract: Mixture-of-experts (MoE) models combine specialized predictors under learned routing, offering a principled mechanism for leveraging heterogeneity in
arXiv:2608.25261v1 Announce Type: cross Abstract: Mixture-of-experts (MoE) models combine specialized predictors under learned routing, offering a principled mechanism for leveraging heterogeneity in medical data. We present a hierarchical multimodal MoE for interstitial lung disease (ILD) classification that integrates a frozen, pre-trained imaging expert with structured electronic health records (EHR) via two-stage gating. A modality-level gate assigns patient-specific weights to imaging and EHR predictions, while a sub-gating module decomposes the EHR branch into clinically defined feature groups with learned, group-specific contributions. This design preserves stable imaging representations while enabling input-dependent clinical weighting and explicit EHR specialization. Under strict patient-level cross-validation, the model achieved the highest mean AUC among the evaluated methods (0.8750 +- 0.0443), compared with 0.8646 for imaging-only REN and 0.7685 for SwinUNETR. The framework extends interpretability across anatomical regions, imaging--EHR utilization, and clinically defined EHR feature groups.
Related
- Beyond Routing: Characterising Expert Tuning and Representation in Vision Mixture-of-Experts
- SegMoTE: Token-Level Mixture of Experts for Medical Image Segmentation
- Sparse Mixture-of-Experts Routing in Visual Diffusion Transformers:Diagnosis, Boundary Calibration and Evolutionary Roadmap from Routing Collapse to Selective Deadlock
- Beyond Global Routing Aggregation: Phase-Aware Expert Merging for MoE Vision-Language Models
- BioVLM: Routing Prompts, Not Parameters, for Cross-Modality Generalization in Biomedical VLMs
Source: arXiv cs.CV | 2026-08-27