Scholarlink

Abstract <p>Parkinson’s disease (PD) is a progressive degenerative neurological disease in which timely diagnosis is essential for slowing clinical deterioration. Existing multimodal neuroimaging methods based on structural MRI (sMRI) and functional MRI (fMRI) often learn suboptimal modality-specific representations and rely on shallow fusion strategies that underutilize cross-modal dependencies. To solve these challenges, a <b>S</b>patial-<b>T</b>emporal dual-pathway network with multi-scale attention <b>Fusion</b> is proposed for PD diagnosis (<b>STFusion</b>). In particular, a hybrid CNN-Transformer branch models both local and global structural patterns from sMRI, while a spatial-temporal Transformer branch characterizes dynamic functional connectivity from fMRI. A cross-modality multi-scale attention integration (CMAI) block is further introduced to adaptively integrate complementary information across modalities. Comprehensive evaluations on a public PPMI cohort and an external cohort show that <b>STFusion</b> achieves the best performance, reaching accuracies of 0.926 and 0.858, respectively.</p> Graphical Abstract <p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

STFusion: A Spatial-Temporal Dual-Pathway Network with Multi-scale Attention Fusion for Early Diagnosis of Parkinson’s Disease

  • 期刊论文

  • 发表日期：

    2026年4月4日

查看全文
  • Hailin Yue,
  • Hulin Kuang,
  • Mengshen He,
  • Junjian Li,
  • Yijin Wang,
  • Jianxin Wang

摘要

Abstract

Parkinson’s disease (PD) is a progressive degenerative neurological disease in which timely diagnosis is essential for slowing clinical deterioration. Existing multimodal neuroimaging methods based on structural MRI (sMRI) and functional MRI (fMRI) often learn suboptimal modality-specific representations and rely on shallow fusion strategies that underutilize cross-modal dependencies. To solve these challenges, a Spatial-Temporal dual-pathway network with multi-scale attention Fusion is proposed for PD diagnosis (STFusion). In particular, a hybrid CNN-Transformer branch models both local and global structural patterns from sMRI, while a spatial-temporal Transformer branch characterizes dynamic functional connectivity from fMRI. A cross-modality multi-scale attention integration (CMAI) block is further introduced to adaptively integrate complementary information across modalities. Comprehensive evaluations on a public PPMI cohort and an external cohort show that STFusion achieves the best performance, reaching accuracies of 0.926 and 0.858, respectively.

Graphical Abstract