REN: Anatomically-Informed Mixture-of-Experts for Interstitial Lung Disease Diagnosis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911554799140864 |
|---|---|
| author | Peltekian, Alec K. Aktas, Halil Ertugrul Durak, Gorkem Grudzinski, Kevin Bemiss, Bradford C. Richardson, Carrie Dematte, Jane E. Budinger, G. R. Scott Esposito, Anthony J. Misharin, Alexander Choudhary, Alok Agrawal, Ankit Bagci, Ulas |
| author_facet | Peltekian, Alec K. Aktas, Halil Ertugrul Durak, Gorkem Grudzinski, Kevin Bemiss, Bradford C. Richardson, Carrie Dematte, Jane E. Budinger, G. R. Scott Esposito, Anthony J. Misharin, Alexander Choudhary, Alok Agrawal, Ankit Bagci, Ulas |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_04923 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | REN: Anatomically-Informed Mixture-of-Experts for Interstitial Lung Disease Diagnosis Peltekian, Alec K. Aktas, Halil Ertugrul Durak, Gorkem Grudzinski, Kevin Bemiss, Bradford C. Richardson, Carrie Dematte, Jane E. Budinger, G. R. Scott Esposito, Anthony J. Misharin, Alexander Choudhary, Alok Agrawal, Ankit Bagci, Ulas Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | REN: Anatomically-Informed Mixture-of-Experts for Interstitial Lung Disease Diagnosis |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2510.04923 |