Task-radMBNet: An Improved Task-Driven Dynamic Graph Sparsity Pattern Radiomics-Based Morphological Brain Network for Alzheimer's Disease Characterization.

Background: The study of task-driven dynamic adaptive graph sparsity patterns in Alzheimer's disease (AD) analysis is of great importance, as it allows for better focus on regions and connections of interest and enhances task sensitivity. Methods: In this study, we introduced a task-driven dynamic adaptive graph sparsity model (called task-driven radiomics-based morphological brain network [Task-radMBNet]) for AD diagnosis based on radiomics-based morphological brain network (radMBN). Specifically, the Task-radMBNet was established by devising a connectivity feature-based graph convolutional network (GCN) channel (called a connectivity-GCN channel) and a radiomics feature-based GCN channel (called a radiomics-GCN channel), where the two GCN channels shared a same dynamic sparse brain network in graph convolution but worked for different aims separately. The connectivity-GCN channel dynamically learned the graph's sparse topology that best suits the target task, while the radiomics-GCN channel combined radiomics node features and dynamic topology to improve AD diagnostic accuracy. Results: The Task-radMBNet achieved superior classification accuracy of 87.8% and 86.0% in early AD diagnosis across a total of 1273 subjects within the AD Neuroimaging Initiative and European Diffusion Tensor Imaging (DTI) Study on Dementia databases. We also visualized the topology heat map and important connectivity under different network sparse settings. Conclusions: The results demonstrated significant promise in the diagnosis of neurological disorders by integrating Task-radMBNet with radMBN.