A Tensor-Based Framework for rs-fMRI Classification and Functional Connectivity Construction

The Dimensions of dimensionality

Cognitive scientists often infer multidimensional representations from data. Whether the data involve text, neuroimaging, neural networks, or human judgments, researchers frequently infer and analyze latent representational spaces (i.e., embeddings). However, the properties of a latent representation (e.g., prediction performance, interpretability, compactness) depend on the inference procedure, which can vary widely across endeavors. For example, dimensions are not always globally interpretable and the dimensionality of different embeddings may not be readily comparable. Moreover, the dichotomy between multidimensional spaces and purportedly richer representational formats, such as graph representations, is misleading. We review what the different notions of dimension in cognitive science imply for how these latent representations should be used and interpreted.

The alterations of spontaneous neural activities and white matter microstructures in anti-N-methyl-D-aspartate receptor encephalitis: a resting-state fMRI and DTI study

BACKGROUND AND PURPOSE

Limited studies had jointly excavated the structural and functional changes in cognitive deficit in anti-N-methyl-D-aspartate receptor (NMDAR) encephalitis patients. We aimed to explore these changes in anti-NMDAR patients and their effect on cognitive function.

METHODS

Twenty-three patients and 25 healthy controls (HCs) underwent resting-state functional magnetic resonance imaging, diffusion tensor imaging scanning, and neuroethology tests. The significantly differentiated brain regions via the fractional amplitude of low-frequency fluctuation (fALFF) were defined as regions of interest (ROIs). Granger causal, functional connectivity, and tract-based spatial statistical analyses were applied to explore the functional changes in ROIs and assess the structural changes.

RESULTS

HCs outperformed patients in Montreal Cognitive Assessment. The fALFF values of right gyrus rectus (RGR) in patients were significantly reduced. The fractional anisotropy (FA) values of WM in the genu of corpus callosum and right superior corona radiata were significantly decreased and positively associated with neuroethology testing scores. The Granger causal connectivity (GCC) from the left inferior parietal lobule to RGR was significantly decreased and positively associated with inherent vigilance. Indicated by the multiple linear regression result, decreased FA value of the right superior corona radiata might be a reliable marker that reflects the cognitive impairment.

CONCLUSIONS

Significant changes in spontaneous neural activities, GCC, and WM structures in anti-NMDAR encephalitis were reported. These findings promote the understanding of underlying relationships between cerebral function, structural network alterations, and cognitive dysfunction.

Convergent functional changes of the episodic memory impairment in mild cognitive impairment: An ALE meta-analysis

Background

Mild cognitive impairment (MCI) is considered to be an intermediate stage between normal aging and Alzheimer's disease (AD). The earliest and most common symptom of MCI is impaired episodic memory. When episodic memory is impaired in MCI patients, specific functional changes occur in related brain areas. However, there is currently a lack of a unified conclusion on this change. Therefore, the purpose of this meta-analysis is to find MRI-specific functional changes in episodic memory in MCI patients.

Methods

Based on three commonly used indicators of brain function: functional connectivity (FC), the amplitude of low-frequency fluctuation /fractional amplitude of low-frequency fluctuation (ALFF/fALFF), and regional homogeneity (ReHo), we systematically searched PubMed, Web of Science and Ovid related literature and conducted the strict screening. Then we use the activation likelihood estimation (ALE) algorithm to perform the coordinate-based meta-analysis.

Results

Through strict screening, this meta-analysis finally included 21 related functional neuroimaging research articles. The final result displays that functional changes of episodic memory in MCI patients are mainly located in the parahippocampal gyrus, precuneus, posterior cingulate gyrus, cuneus, middle temporal gyrus, middle frontal gyrus, lingual gyrus, and thalamus.

Conclusions

There are specific functional changes in episodic memory brain regions in MCI patients, and the brain functional network can regulate episodic memory through these brain regions. And these specific changes can assist in the early diagnosis of MCI, providing new ideas and directions for early identification and intervention in the process of MCI.

Wavelet-Based Fractal Analysis of rs-fMRI for Classification of Alzheimer's Disease

The resting-state functional magnetic resonance imaging (rs-fMRI) modality has gained widespread acceptance as a promising method for analyzing a variety of neurological and psychiatric diseases. It is established that resting-state neuroimaging data exhibit fractal behavior, manifested in the form of slow-decaying auto-correlation and power-law scaling of the power spectrum across low-frequency components. With this property, the rs-fMRI signal can be broken down into fractal and nonfractal components. The fractal nature originates from several sources, such as cardiac fluctuations, respiration and system noise, and carries no information on the brain’s neuronal activities. As a result, the conventional correlation of rs-fMRI signals may not accurately reflect the functional dynamic of spontaneous neuronal activities. This problem can be solved by using a better representation of neuronal activities provided by the connectivity of nonfractal components. In this work, the nonfractal connectivity of rs-fMRI is used to distinguish Alzheimer’s patients from healthy controls. The automated anatomical labeling (AAL) atlas is used to extract the blood-oxygenation-level-dependent time series signals from 116 brain regions, yielding a 116 × 116 nonfractal connectivity matrix. From this matrix, significant connections evaluated using the p-value are selected as an input to a classifier for the classification of Alzheimer’s vs. normal controls. The nonfractal-based approach provides a good representation of the brain’s neuronal activity. It outperformed the fractal and Pearson-based connectivity approaches by 16.4% and 17.2%, respectively. The classification algorithm developed based on the nonfractal connectivity feature and support vector machine classifier has shown an excellent performance, with an accuracy of 90.3% and 83.3% for the XHSLF dataset and ADNI dataset, respectively. For further validation of our proposed work, we combined the two datasets (XHSLF+ADNI) and still received an accuracy of 90.2%. The proposed work outperformed the recently published work by a margin of 8.18% and 11.2%, respectively.

Biomarkers Derived from Alterations in Overlapping Community Structure of Resting-state Brain Functional Networks for Detecting Alzheimer's Disease

Recent studies show that overlapping community structure is an important feature of the brain functional network. However, alterations in such overlapping community structure in Alzheimer's disease (AD) patients have not been examined yet. In this study, we investigate the overlapping community structure in AD by using resting-state functional magnetic resonance imaging (rs-fMRI) data. The collective sparse symmetric non-negative matrix factorization (cssNMF) is adopted to detect the overlapping community structure. Experimental results on 28 AD patients and 32 normal controls (NCs) from the ADNI2 dataset show that the two groups have remarkable differences in terms of the optimal number of communities, the hierarchy of communities detected at different scales, network functional segregation, and nodal functional diversity. In particular, the frontal-parietal and basal ganglia networks exhibit significant differences between the two groups. A machine learning framework proposed in this paper for AD detection achieved an accuracy of 76.7% when using the detected community strengths of the frontal-parietal and basal ganglia networks only as input features. These findings provide novel insights into the understanding of pathological changes in the brain functional network organization of AD and show the potential of the community structure-related features for AD detection.