Brain Functional Networks with Dynamic Hypergraph Manifold Regularization for Classification of End-Stage Renal Disease Associated with Mild Cognitive Impairment

Abstract

The structure and function of brain networks have been altered in patients with end-stage renal disease (ESRD). Manifold regularization (MR) only considers the pairing relationship between two brain regions and cannot represent functional interactions or higher-order relationships between multiple brain regions. To solve this issue, we developed a method to construct a dynamic brain functional network (DBFN) based on dynamic hypergraph MR (DHMR) and applied it to the classification of ESRD associated with mild cognitive impairment (ESRDaMCI). The construction of DBFN with Pearson's correlation (PC) was transformed into an optimization model. Node convolution and hyperedge convolution superposition were adopted to dynamically modify the hypergraph structure, and then got the dynamic hypergraph to form the manifold regular terms of the dynamic hypergraph. The DHMR and L 1 norm regularization were introduced into the PC-based optimization model to obtain the final DHMR-based DBFN (DDBFN). Experiment results demonstrated the validity of the DDBFN method by comparing the classification results with several related brain functional network construction methods. Our work not only improves better classification performance but also reveals the discriminative regions of ESRDaMCI, providing a reference for clinical research and auxiliary diagnosis of concomitant cognitive impairments.

Characterizing Topological Properties of Brain Functional Networks Using Multi-Threshold Derivative for End-Stage Renal Disease with Mild Cognitive Impairment

“…The results showed that the classification performance was best when L was set to 85 and s to 3, which is consistent with the research conclusion of Xi et al [ 23 ]. As L and s increase, the classification performance first improves and then deteriorates.…”

“…Bian et al [ 22 ] extracted brain network multidimensional persistent features based on persistent homology with multi-threshold filtering (MTF) and identified brain connectivity patterns specific to Alzheimer’s disease. Xi et al [ 23 ] constructed dynamic hypergraphs and introduced hypergraph popular regularization and L1-norm regularization terms into the brain network construction model, extracting hypergraph features for the classification of patients with ESRDaMCI and health control (HC). Zhang et al [ 24 ] used graph theory to extract the AUC value of the topological properties within the sparse threshold range as a feature using the GRETNA toolbox to predict the degree of cognitive impairment in ESRD patients and HC individuals.…”

Constructing brain functional networks with adaptive manifold regularization for early mild cognitive impairment

“…The baseline methods include Pearson correlation (PC), 14 sparse representation (SR), 15 graph regularization (MR), 18 sparse and hypergraph manifold regularization (SHMR), 19 and dynamic hypergraph manifold regularization (DHMR). 20 All methods adopted the same feature extraction and selection methods, used SVM for classification, and compared the final optimal results. The detailed classification performance is presented in Table 3, with the optimal results highlighted in bold.…”

“…We evaluated the effectiveness of AMR by comparing it with five state‐of‐the‐art methods for constructing BFNs. The baseline methods include Pearson correlation (PC), 14 sparse representation (SR), 15 graph regularization (MR), 18 sparse and hypergraph manifold regularization (SHMR), 19 and dynamic hypergraph manifold regularization (DHMR) 20 . All methods adopted the same feature extraction and selection methods, used SVM for classification, and compared the final optimal results.…”

“…Ji et al 19 adopted the hypergraph as a substitute for the original graph, introducing hypergraph manifold regularization term to construct a BFN. Xi et al 20 constructed a BFN with dynamic hypergraph manifold regularization to improve classification accuracy.…”