AMSF: attention-based multi-view slice fusion for early diagnosis of Alzheimer's disease

Yameng Zhang; Shaokang Peng; Zhihua Xue; Guohua Zhao; Qing Li; Zhiyuan Zhu; Yufei Gao; Lingfei Kong; Alzheimer’s Disease Neuroimaging Initiative

doi:10.7717/peerj-cs.1706

AMSF: attention-based multi-view slice fusion for early diagnosis of Alzheimer's disease

PeerJ Comput Sci. 2023 Nov 23:9:e1706. doi: 10.7717/peerj-cs.1706. eCollection 2023.

Authors

Yameng Zhang¹, Shaokang Peng², Zhihua Xue³, Guohua Zhao⁴, Qing Li⁵, Zhiyuan Zhu⁶, Yufei Gao², Lingfei Kong¹; Alzheimer’s Disease Neuroimaging Initiative

Affiliations

¹ Department of Pathology, Henan Provincial People's Hospital, People's Hospital of Zhengzhou University, Zhengzhou, China.
² School of Cyber Science and Engineering, Zhengzhou University, SongShan Laboratory, Zhengzhou, China.
³ Laboratory Animal Center, Academy of Medical Sciences, Zhengzhou University, Zhengzhou, China.
⁴ Department of Magnetic Resonance Imaging, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China.
⁵ State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University, Beijing, China.
⁶ School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China.

Abstract

Alzheimer's disease (AD) is an irreversible neurodegenerative disease with a high prevalence in the elderly population over 65 years of age. Intervention in the early stages of AD is of great significance to alleviate the symptoms. Recent advances in deep learning have shown extreme advantages in computer-aided diagnosis of AD. However, most studies only focus on extracting features from slices in specific directions or whole brain images, ignoring the complementarity between features from different angles. To overcome the above problem, attention-based multi-view slice fusion (AMSF) is proposed for accurate early diagnosis of AD. It adopts the fusion of three-dimensional (3D) global features with multi-view 2D slice features by using an attention mechanism to guide the fusion of slice features for each view, to generate a comprehensive representation of the MRI images for classification. The experiments on the public dataset demonstrate that AMSF achieves 94.3% accuracy with 1.6-7.1% higher than other previous promising methods. It indicates that the better solution for AD early diagnosis depends not only on the large scale of the dataset but also on the organic combination of feature construction strategy and deep neural networks.

Keywords: Alzheimer’s disease; Attention mechanism; Magnetic resonance imaging; Multi-view slice fusion.

Grants and funding

This work was supported by the Nature Science Foundation of China (62006210, 62001284, 62206252), the Key Scientific and Technology Project in Henan Province of China (221100210100), the Key Project of Collaborative Innovation in Nanyang (22XTCX12001), the Research Foundation for Advanced Talents of Zhengzhou University (32340306). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.