Multi-modal feature selection with self-expression topological manifold for end-stage renal disease associated with mild cognitive impairment

Abstract

<abstract> <p>Effectively selecting discriminative brain regions in multi-modal neuroimages is one of the effective means to reveal the neuropathological mechanism of end-stage renal disease associated with mild cognitive impairment (ESRDaMCI). Existing multi-modal feature selection methods usually depend on the <italic>Euclidean</italic> distance to measure the similarity between data, which tends to ignore the implied data manifold. A self-expression topological manifold based multi-modal feature selection method (SETMFS) is proposed to address this issue employing self-expression topological manifold. First, a dynamic brain functional network is established using functional magnetic resonance imaging (fMRI), after which the betweenness centrality is extracted. The feature matrix of fMRI is constructed based on this centrality measure. Second, the feature matrix of arterial spin labeling (ASL) is constructed by extracting the cerebral blood flow (CBF). Then, the topological relationship matrices are constructed by calculating the topological relationship between each data point in the two feature matrices to measure the intrinsic similarity between the features, respectively. Subsequently, the graph regularization is utilized to embed the self-expression model into topological manifold learning to identify the linear self-expression of the features. Finally, the selected well-represented feature vectors are fed into a multicore support vector machine (MKSVM) for classification. The experimental results show that the classification performance of SETMFS is significantly superior to several state-of-the-art feature selection methods, especially its classification accuracy reaches 86.10%, which is at least 4.34% higher than other comparable methods. This method fully considers the topological correlation between the multi-modal features and provides a reference for ESRDaMCI auxiliary diagnosis.</p> </abstract>

Multimodal Classification Framework Based on Hypergraph Latent Relation for End-Stage Renal Disease Associated with Mild Cognitive Impairment

“…ASMFS, proposed by Shi et al [ 17 ], updates the similarity matrix in real-time, but it does not consider outliers and noise in the features. SETMFS proposed by Song et al [ 18 ] only focuses on the topological relationships between different modalities without considering the latent relation among features within each modality and the handling of noise. They also neglect the quantity and quality of useful information contained in the original feature matrix.…”

“…Traditional Euclidean distance calculation in constructing the similarity matrix may not be suitable for capturing complex network topology structures [ 47 ]. In the upcoming work, we will integrate topological manifold terms [ 18 ] to compute the topological relationship matrix between features, thereby obtaining a more accurate similarity matrix. HLR involves many parameters and requires multiple parameters tuning to get the optimal model, and the process is complex, requiring further model refinement.…”

“…We employ the same original dataset as Song et al [ 18 ]. Forty-four patients with ESRDaMCI from the Affiliated Changzhou No.2 People’s Hospital of Nanjing Medical University were selected as the ESRD group.…”

“…In the experiment, nine methods are selected for comparison to validate the effectiveness of the proposed framework. The baseline methods include MKSVM [ 33 ], MKSVM with Lasso feature selection performed independently on single modality (Lasso-MKSVM) [ 35 ], manifold regularized-based multimodal feature selection (M2TFS) [ 15 ], hypergraph-based multimodal feature selection (HMTFS) [ 16 ], ASMFS [ 17 ], self-expression topological manifolds-based multimodal feature selection (SETMFS) [ 18 ], multimodal classification framework based on ordinary features’ latent relation (OLR), unimodal fMRI and unimodal ASL. The first six methods and unimodal fMRI, along with the proposed framework, depend on SHMR-based brain functional networks to obtain hypergraph feature matrices.…”

“…In recent research, Shi et al [ 17 ] introduced adaptive similarity learning, resulting in more accurate similarity matrices. Song et al [ 18 ] introduced topological manifold terms to construct similarity matrices with topological relations.…”