Your new experience awaits. Try the new design now and help us make it even better

ORIGINAL RESEARCH article

Front. Neurol.

Sec. Artificial Intelligence in Neurology

Volume 16 - 2025 | doi: 10.3389/fneur.2025.1626922

PlgFormer: Parallel extraction of local-global features for AD diagnosis on sMRI using a unified CNN-TransFormer architecture

Provisionally accepted
Gouxin  WangGouxin Wang1Yuxia  LiYuxia Li2Zhiyi  ZhouZhiyi Zhou3Shan  AnShan An4*Xuyang  CaoXuyang Cao4Yuxin  JinYuxin Jin4Zhengqin  SunZhengqin Sun2Guanqun  ChenGuanqun Chen5Mingkai  ZhangMingkai Zhang6Zhixiong  LiZhixiong Li7*Feng  YuFeng Yu1*
  • 1Zhejiang University, Hangzhou, China
  • 2Tangshan Central Hospital, Tangshan, Hebei Province, China
  • 3Tianjin University, Tianjin, Tianjin, China
  • 4JD Health International Inc., Beijing, China
  • 5Beijing Chaoyang Hospital, Capital Medical University, Beijing, Beijing Municipality, China
  • 6Xuanwu Hospital, Capital Medical University, Beijing, Beijing Municipality, China
  • 7People's hospital of karamay, karamay, China

The final, formatted version of the article will be published soon.

Structural magnetic resonance imaging (sMRI) is an important tool for the early diagnosis of Alzheimer's disease (AD). Previous methods based on Voxel, ROIs or Patch have limitations in characterizing discriminative features in sMRI for AD as they can only focus on specific local or global features. In this paper, we propose a computer-aided AD diagnosis method based on sMRI, named PlgFormer, which considers the extraction of both local and global features. By using a combination of convolution and self-attention, we can extract context features at both local and global levels. In the decision-making layer of the model, we design a feature fusion module that adaptively selects context features through a gating mechanism. Additionally, to account for changes in image input resolution during the downsampling operation, we embed a dynamic embedding block at each stage of the network, which can adaptively adjust the weights of the inputs with different resolutions. We evaluated the performance of our method on dichotomous AD vs normal control (NC) and mild cognitive impairment (MCI) vs NC, as well as trichotomous AD vs MCI vs NC classification tasks, using publicly available ADNI and XWNI datasets that we collected. The experimental results demonstrate the high precision and robustness of our method in diagnosing people with different stages of cognitive impairment. These findings underscore the clinical potential of our proposed PlgFormer as a reliable and interpretable framework for supporting early and accurate diagnosis of AD using sMRI.

Keywords: Alzheimer's disease diagnosis, attention mechanism, computer-aided diagnosis, sMRI, Multi-level feature fusion

Received: 12 May 2025; Accepted: 07 Aug 2025.

Copyright: © 2025 Wang, Li, Zhou, An, Cao, Jin, Sun, Chen, Zhang, Li and Yu. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence:
Shan An, JD Health International Inc., Beijing, China
Zhixiong Li, People's hospital of karamay, karamay, China
Feng Yu, Zhejiang University, Hangzhou, China

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.