用3D影像融合与自适应模型提升阿尔茨海默病早期诊断准确率
Alzheimer's Disease Diagnosis using a Multimodal Approach with 3D MRI and PET
- 结合3D MRI与PET，采用动态融合与专家路由机制提升诊断鲁棒性
- 在NC vs. AD任务中达到95.47%准确率，优于传统静态融合方法
- 模型可自动选择最优专家并可视化病变区域，适合临床辅助诊断
阿尔茨海默病（AD）是一种不可逆的神经退行性疾病，是全球主要死亡原因之一。早期诊断尤其在轻度认知障碍（MCI）阶段至关重要，及时干预可延缓疾病进展。结构和功能脑影像（如MRI与PET）能揭示早期脑变化。然而，现有多模态模型多采用静态拼接融合，对所有患者使用相同计算，难以应对个体与站点差异，且效率低下。为此，本文首次将3D卷积特征提取器与三种融合策略——拼接、门控多模态单元（GMU）和门控自注意力——结合，并引入稀疏门控专家混合（MoE）分类器，实现输入自适应路由，仅激活最相关专家。通过Grad-CAM可视化病灶区域，保障模型可解释性。在三个二分类任务（NC vs. MCI、MCI vs. AD、NC vs. AD）上验证，GMU在NC vs. MCI任务中达80.46%准确率，NC vs. AD达95.47%；门控自注意力在MCI vs. AD任务中达82.08%。消融实验表明，移除MoE会持续降低各任务准确率。结果证明，基于输入自适应的多模态建模能有效利用MRI与PET互补信息，提升诊断性能。
原文摘要 · Abstract (English)
Alzheimer's disease (AD) is an irreversible neurodegenerative disorder and a leading cause of death worldwide. Early diagnosis plays an important part especially at the Mild Cognitive Impairment stage, where timely intervention can help slow its progression before it advances to AD. Neuroimaging data, like Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET) scans, can help detect brain changes early by providing structural and functional brain changes related to the disease. Yet, many multimodal models still fuse MRI and PET with static concatenation and apply identical computation to all subjects, which limits robustness to patient/site heterogeneity and can waste computation. To address these limitations, we present the first study of combining 3D convolutional feature extractors with three fusion strategies - concatenation, Gated Multimodal Unit (GMU), and gated self-attention - and a sparsely gated Mixture-of-Experts (MoE) classifier that performs input-adaptive routing, activating only the most informative experts per case. Finally, we utilize Grad-CAM to visualize disease-related regions, ensuring model interpretability. Experiments are performed across three binary classification tasks (NC vs. MCI, MCI vs. AD, and NC vs. AD). Results show that GMU achieves accuracies of 80.46 % (NC vs. MCI) and 95.47 % (NC vs. AD), while gated self-attention attains 82.08 % on MCI vs. AD. Ablations show that removing the MoE consistently degrades accuracy across all tasks. These findings underscore the value of input-adaptive, multimodal modeling for AD diagnosis by leveraging the complementary nature of MRI and PET.
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。