Classification of Alzheimer's disease: application of a transfer learning deep Q‐network method

• Published in: The European journal of neuroscience Vol. 59; no. 8; pp. 2118 - 2127
• Main Authors: Ma, Huibin, Wang, Yadan, Hao, Zeqi, Yu, Yang, Jia, Xize, Li, Mengting, Chen, Lanfen
• Format: Journal Article
• Language: English
• Published: France Wiley Subscription Services, Inc 01.04.2024
• Subjects: Alzheimer Disease - diagnostic imaging; Alzheimer's disease; Brain; Brain mapping; Classification; deep Q‐network; Diagnosis; Female; Functional magnetic resonance imaging; Humans; local metrics; Machine Learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Neurodegenerative diseases; Neuroimaging; reinforcement learning; Reproducibility of Results; resting‐state fMRI; Sexism; Transfer learning; local metrics; transfer learning; deep Q‐network; Alzheimer's disease; reinforcement learning; resting‐state fMRI
• ISSN: 0953-816X; 1460-9568; 1460-9568
• DOI: 10.1111/ejn.16261

Early diagnosis is crucial to slowing the progression of Alzheimer's disease (AD), so it is urgent to find an effective diagnostic method for AD. This study intended to investigate whether the transfer learning approach of deep Q‐network (DQN) could effectively distinguish AD patients using local metrics of resting‐state functional magnetic resonance imaging (rs‐fMRI) as features. This study included 1310 subjects from the Consortium for Reliability and Reproducibility (CoRR) and 50 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) GO/2. The amplitude of low‐frequency fluctuation (ALFF), fractional ALFF (fALFF) and percent amplitude of fluctuation (PerAF) were extracted as features using the Power 264 atlas. Based on gender bias in AD, we searched for transferable similar parts between the CoRR feature matrix and the ADNI feature matrix, resulting in the CoRR similar feature matrix served as the source domain and the ADNI similar feature matrix served as the target domain. A DQN classifier was pre‐trained in the source domain and transferred to the target domain. Finally, the transferred DQN classifier was used to classify AD and healthy controls (HC). A permutation test was performed. The DQN transfer learning achieved a classification accuracy of 86.66% (p < 0.01), recall of 83.33% and precision of 83.33%. The findings suggested that the transfer learning approach using DQN could be an effective way to distinguish AD from HC. It also revealed the potential value of local brain activity in AD clinical diagnosis. The deep Q‐network using transfer learning methods could effectively classify small‐sample Alzheimer's disease (AD) data. The local brain neural activity of AD patients can serve as effective biomarkers to differentiate between AD and healthy controls (HC).