A pairwise functional connectivity similarity measure method based on few-shot learning for early MCI detection

• Published in: Frontiers in neuroscience Vol. 16; p. 1081788
• Main Authors: Zhang, Xiangfei, Shams, Shayel Parvez, Yu, Hang, Wang, Zhengxia, Zhang, Qingchen
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 19.12.2022; Frontiers Media S.A
• Subjects: Alzheimer's disease; Artificial intelligence; automatic diagnosis; Biomarkers; Brain mapping; Classification; Deep learning; few-shot learning; Functional magnetic resonance imaging; Machine learning; Medical imaging; Neural networks; Neurodegenerative diseases; Neuroimaging; Neuroscience; rs-fMRI; Similarity measures; smart medical; Support vector machines; Time series; automatic diagnosis; smart medical; Alzheimer's disease; rs-fMRI; few-shot learning
• ISSN: 1662-453X; 1662-4548; 1662-453X
• DOI: 10.3389/fnins.2022.1081788

Alzheimer's disease is an irreversible neurological disease, therefore prompt diagnosis during its early stage, i.e., early mild cognitive impairment (MCI), is crucial for effective treatment. In this paper, we propose an automatic diagnosis method, a few-shot learning-based pairwise functional connectivity (FC) similarity measure method, to detect early MCI. We first employ a sliding window strategy to generate a dynamic functional connectivity network (FCN) using each subject's rs-fMRI data. Then, normal controls (NCs) and early MCI patients are distinguished by measuring the similarity between the dynamic FC series of corresponding brain regions of interest (ROIs) pairs in different subjects. However, previous studies have shown that FC patterns in different ROI-pairs contribute differently to disease classification. To enable the FCs of different ROI-pairs to make corresponding contributions to disease classification, we adopt a self-attention mechanism to weight the FC features. We evaluated the suggested strategy using rs-fMRI data obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, and the results point to the viability of our approach for detecting MCI at an early stage.