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 powerful imaging method for evaluating brain patches is resting-state functional magnetic resonance imaging, in which the subject is at rest. Artificial neural networks are one of the several Alzheimer's disease analysis and diagnosis methods which is used in this study. We investigate artificial neural networks' ability to diagnose Alzheimer's disease using resting-state functional magnetic resonance imaging data.

Functional and structural magnetic resonance imaging data acquisition was applied for 15 Alzheimer’s disease, 17 mild cognitive impaired, and ten normal healthy participants. Time series of blood oxygen level dependent extracted from the multi subject dictionary learning brain atlas after pre-processing. This study develops a one-dimensional convolutional neural network using extracted signals of the functional atlas for differential diagnosis of Alzheimer's disease.

Applying the proposed method to resting-state functional magnetic resonance imaging signals for classifying three classes of Alzheimer's disease 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 quiet simple network than most of the available deep learning-based methods are the main advantages of this model.

Resting-state functional magnetic resonance imaging 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 Alzheimer’s disease.