Quantification of Cognitive Function in Alzheimer’s Disease Based on Deep Learning

Abstract

Alzheimer disease (AD) is mainly manifested as insidious onset, chronic progressive cognitive decline and non-cognitive neuropsychiatric symptoms, which seriously affects the quality of life of the elderly and causes a very large burden on society and families. This paper uses graph theory to analyze the constructed brain network, and extracts the node degree, node efficiency, and node betweenness centrality parameters of the two modal brain networks. The T test method is used to analyze the difference of graph theory parameters between normal people and AD patients, and brain regions with significant differences in graph theory parameters are selected as brain network features. By analyzing the calculation principles of the conventional convolutional layer and the depth separable convolution unit, the computational complexity of them is compared. The depth separable convolution unit decomposes the traditional convolution process into spatial convolution for feature extraction and point convolution for feature combination, which greatly reduces the number of multiplication and addition operations in the convolution process, while still being able to obtain comparisons. Aiming at the special convolution structure of the depth separable convolution unit, this paper proposes a channel pruning method based on the convolution structure and explains its pruning process. Multimodal neuroimaging can provide complete information for the quantification of Alzheimer’s disease. This paper proposes a cascaded three-dimensional neural network framework based on single-modal and multi-modal images, using MRI and PET images to distinguish AD and MCI from normal samples. Multiple three-dimensional CNN networks are used to extract recognizable information in local image blocks. The high-level two-dimensional CNN network fuses multi-modal features and selects the features of discriminative regions to perform quantitative predictions on samples. The algorithm proposed in this paper can automatically extract and fuse the features of multi-modality and multi-regions layer by layer, and the visual analysis results show that the abnormally changed regions affected by Alzheimer’s disease provide important information for clinical quantification.

Relationship between topological efficiency of white matter structural connectome and plasma biomarkers across the Alzheimer's disease continuum

“…Deep learning‐based cognitive function quantification validates graph theory‐based brain network features. Increased NfL levels indicate neurodegeneration, but cognitive decline requires specific network efficiency impairment (He et al, 2021). These findings enhance our understanding of Alzheimer's cognitive decline mechanism.…”

Evaluation of Neuro Images for the Diagnosis of Alzheimer's Disease Using Deep Learning Neural Network

“…To run on such soft tissues, software programdriven techniques and algorithms have to be extra particular in choosing the highest quality direction for attaining the procedural region. Statistical analysis has determined whether the proposed approach might be outperforming under the favorable learning rate, discount factor, and the exploration factor (20). The network is built with multiple layers to learn features through a training process, which eliminates the need for extracting the features, resulting in higher prediction performance when compared to other approaches.…”

Use of 3D-CAPSNET and RNN models for 4D fMRI-based Alzheimer’s Disease Pre-detection

“…Also, deep neural networks are capable of learning more hidden disease-related patterns. For example, He et al constructed an FC matrix by calculating the time series correlation coefficient between each pair of brain regions based on both the variance of the mean value of all voxel time series in the two brain regions over time and the covariance of the time series mean value of the two brain regions [10]. Then, feeding the adjacency matrix of each subject into a simplified instance of 3D-MobileNet [11] architecture.…”