arXiv:2606.07635cs.CVcs.AI2026-06

通过分层对齐融合动态与结构脑影像,提升轻度认知障碍检测精度

NeuroAlign: Hierarchical Multimodal Fusion of Dynamic and Structural Neuroimaging for MCI Analysis

论文配图:NeuroAlign: Hierarchical Multimodal Fusion of Dynamic and Structural Neuroimaging for MCI Analysis
图 1 · 摘自论文原文
  • 分层对齐动态与静态、功能与结构特征,解决多模态数据异构问题
  • 在三个数据集上实现轻度认知障碍与可疑轻度认知下降的准确识别
  • 提出无梯度归因方法,可解释各模态在脑区中的贡献模式

功能磁共振(fMRI)与扩散张量成像(DTI)的多模态脑影像融合为认知障碍分析提供互补信息,但受限于异构特征空间和表征错位。本文提出神经对齐框架(NeuroAlign),包含:(1) 双模态分层对齐(DMHA),建模多尺度动态连接性,并对齐动态-静态与功能-结构嵌入;(2) 双域分层交互(DDHI),实现连接级与区域级特征间的细粒度调制与全局交互。为支持特征层面的可解释性,设计了协同激活映射(SAM),一种无需梯度、面向标记的归因方法,适用于动态功能连接(DFC)、静态功能连接(SFC)、局部一致性(ALFF)和各向异性分数(FA)。在GUTCM、ADNI与OASIS数据集上,经五折验证,NeuroAlign实现了具有竞争力的轻度认知障碍(MCI)与可疑轻度认知下降(SCD)检测性能,并展现出初步的跨数据集迁移能力。归因分析揭示了模态特异性和部分一致的脑区模式,为多模态表征分析提供了模型驱动的证据。

原文摘要 · Abstract (English)

Multimodal neuroimaging fusion of functional MRI (fMRI) and diffusion tensor imaging (DTI) provides complementary information for cognitive impairment analysis, but remains challenged by heterogeneous feature spaces and misaligned representations. We propose \textit{NeuroAlign}, a hierarchical framework for structured multimodal fusion. It introduces (1) \textit{Dual-Modal Hierarchical Alignment} (DMHA), which models multi-scale dynamic connectivity and aligns dynamic-static and functional-structural embeddings; and (2) \textit{Dual-Domain Hierarchical Interaction} (DDHI), which enables fine-grained modulation and global interaction between connectivity- and region-level features. To support feature-level inspection, we design \textit{Synergistic Activation Mapping} (SAM), a gradient-free, marker-oriented attribution method for DFC, SFC, ALFF, and FA. Evaluated on GUTCM, ADNI, and OASIS under five-fold validation, NeuroAlign achieves competitive MCI/SCD detection and preliminary cross-dataset transferability. Attribution analyses reveal modality-specific and partially consistent brain patterns, providing model-derived evidence for multimodal representation analysis.

脑影像分析多模态融合认知障碍可解释性

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。