Dual-path mixture of experts for Alzheimer’s diagnosis using volume and entropy MRI features
조회 482
Background
Alzheimer’s disease (AD) is a progressive neurodegenerative disorder marked by brain
atrophy, observable via MRI. Volumetric measures like hippocampal volume are widely used but
often miss early microstructural changes. Texture features such as intensity entropy capture tissue
heterogeneity and may improve early diagnosis. Combining these orthogonal modalities could yield
better biomarkers.
New method
We propose a Dual-Path Mixture of Experts (DP-MoE) model that integrates volumetric and entropy-based MRI features through two expert subnetworks and a self-attention gating
mechanism. A residual fusion branch preserves raw input distributions, enhancing flexibility and
expressiveness. The code is available at https://github.com/syoonni/DP-MOE.
Results
The model was evaluated on three binary classification tasks (CN vs. AD, CN vs. MCI,
MCI vs. AD) using T1-weighted and entropy-derived MRI. For CN vs. AD, it achieved an accuracy
of 93.02% (0.9302 ± 0.0109) and an AUC of 0.975 ± 0.004, outperforming both the baseline MoE
and logistic fusion models. Ablation studies confirmed the importance of both attention and residual
components.
Comparison with existing methods
Prior methods used concatenation or fixed weighting, neglecting modality-specific characteristics. Volume and entropy provide orthogonal, complementary information. While Mixture of Experts is common in other fields, it remains underused in AD imaging. Our adaptive fusion approach improved both interpretability and accuracy, especially in early-stage discrimination.
Conclusions
DP-MoE offers an effective, interpretable framework for fusing heterogeneous MRI
biomarkers and holds promise for deployment in early Alzheimer’s diagnosis workflows.
1. Department of Biomedical Engineering, Korea University, Seoul, Republic of Korea
Sangyoon Park, Yongha Gi, Hyeongjin Lim
2. College of Medicine, Korea University, Seoul, Republic of Korea
Byung‑Jo Kim, Seol‑Hee Baek
3. FieldCure Co., Ltd., Seoul, Republic of Korea
Jong Hyun Kim, Myonggeun Yoon
