Differential Diagnosis among Alzheimer's Disease, Mild Cognitive Impairment, and Normal Subjects Using Resting-State fMRI Data Extracted from Multi-Subject Dictionary Learning Atlas: A Deep Learning-Based Study

Purpose: A powerful imaging method for evaluating brain patches is resting-state functional Magnetic Resonance (rs-fMRI) Imaging, in which the subject is at rest. Artificial Neural Networks (ANN) are one of the several Alzheimer's Disease (AD) analysis and diagnosis methods used in this study. We investigate ANNs' ability to diagnose AD using rs-fMRI data. Materials and Methods: The acquisition of functional and structural magnetic resonance imaging was applied for 15 AD, 17 mild cognitive impairment, and ten normal healthy participants. Time series of blood oxygen level-dependent were extracted from the multi-subject dictionary learning brain atlas after pre-processing. This study develops a one-dimensional Convolutional Neural Network (CNN) using extracted signals of the functional atlas for differential diagnosis of AD. Results: Applying the proposed method to rs-fMRI signals for classifying three classes of Alzheimer’s patients resulted in overall accuracy, F1-score, and precision of 0.685, 0.663, and 0.681, respectively. Using 39 regions in the brain and proposing a quite simple network than most of the available deep learning-based methods are the main advantages of this model. Conclusion: rs-fMRI signal recognition based on a functional atlas with the application of a deep neural network has a pattern recognition capability that can make a differential diagnosis with an acceptable level of accuracy and precision. Therefore, deep neural networks can be considered as a tool for the early diagnosis of AD.