{"ID":2859939,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.04923","arxiv_id":"2510.04923","title":"REN: Anatomically-Informed Mixture-of-Experts for Interstitial Lung Disease Diagnosis","abstract":"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.","short_abstract":"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 anat...","url_abs":"https://arxiv.org/abs/2510.04923","url_pdf":"https://arxiv.org/pdf/2510.04923v3","authors":"[\"Alec K. Peltekian\",\"Halil Ertugrul Aktas\",\"Gorkem Durak\",\"Kevin Grudzinski\",\"Bradford C. Bemiss\",\"Carrie Richardson\",\"Jane E. Dematte\",\"G. R. Scott Budinger\",\"Anthony J. Esposito\",\"Alexander Misharin\",\"Alok Choudhary\",\"Ankit Agrawal\",\"Ulas Bagci\"]","published":"2025-10-06T15:35:08Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Transformer\",\"Convolutional Neural Network\"]","has_code":false,"code_links":[{"ID":608685,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2859939,"paper_url":"https://arxiv.org/abs/2510.04923","paper_title":"REN: Anatomically-Informed Mixture-of-Experts for Interstitial Lung Disease Diagnosis","repo_url":"https://github.com/NUBagciLab/MoE-REN","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}