Alzheimer's Disease Diagnosis With Brain Structural MRI Using Multiview-Slice Attention and 3D Convolution Neural Network

• Published in: Frontiers in aging neuroscience Vol. 14; p. 871706
• Main Authors: Chen, Lin, Qiao, Hezhe, Zhu, Fan
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 26.04.2022; Frontiers Media S.A
• Subjects: 3D convolution neural network; Aging; Aging Neuroscience; Alzheimer's disease; Alzheimer's disease (AD); Artificial intelligence; Attention; Biomarkers; Brain slice preparation; brain sMRI image; Cognitive ability; Complementarity; Datasets; Dementia disorders; Diagnosis; disease prognosis; Magnetic resonance imaging; Medical diagnosis; Medical prognosis; multi-view-slice attention; Neural networks; Neurodegenerative diseases; Neuroimaging; Older people; brain sMRI image; 3D convolution neural network; Alzheimer's disease (AD); multi-view-slice attention; disease prognosis
• ISSN: 1663-4365; 1663-4365
• DOI: 10.3389/fnagi.2022.871706

Numerous artificial intelligence (AI) based approaches have been proposed for automatic Alzheimer's disease (AD) prediction with brain structural magnetic resonance imaging (sMRI). Previous studies extract features from the whole brain or individual slices separately, ignoring the properties of multi-view slices and feature complementarity. For this reason, we present a novel AD diagnosis model based on the multiview-slice attention and 3D convolution neural network (3D-CNN). Specifically, we begin by extracting the local slice-level characteristic in various dimensions using multiple sub-networks. Then we proposed a slice-level attention mechanism to emphasize specific 2D-slices to exclude the redundancy features. After that, a 3D-CNN was employed to capture the global subject-level structural changes. Finally, all these 2D and 3D features were fused to obtain more discriminative representations. We conduct the experiments on 1,451 subjects from ADNI-1 and ADNI-2 datasets. Experimental results showed the superiority of our model over the state-of-the-art approaches regarding dementia classification. Specifically, our model achieves accuracy values of 91.1 and 80.1% on ADNI-1 for AD diagnosis and mild cognitive impairment (MCI) convention prediction, respectively.