Evolutional Neural Architecture Search for Optimization of Spatiotemporal Brain Network Decomposition

HCTMFS: A multi-modal feature selection framework with higher-order correlated topological manifold for ESRDaMCI

BACKGROUND AND OBJECTIVE

The diagnosis of end-stage renal disease associated with mild cognitive impairment (ESRDaMCI) mainly relies on objective cognitive assessment, clinical observation, and neuro-psychological evaluation, while only adopting clinical tools often limits the diagnosis accuracy.

METHODS

We proposed a multi-modal feature selection framework with higher-order correlated topological manifold (HCTMFS) to classify ESRDaMCI patients and identify the discriminative brain regions. It constructed brain structural and functional networks with diffuse kurtosis imaging (DKI) and functional magnetic resonance imaging (fMRI) data, and extracted node efficiency and clustering coefficient from the brain networks to construct multi-modal feature matrices. The topological relationship matrices were constructed to measure the lower-order topological correlation between features. Then the consensus matrices were learned to approximate the topological relationship matrices at different confidence levels and eliminate the noise influence of individual matrices.

RESULTS

The higher-order topological correlation between features was explored by the Laplacian matrix of the hypergraph, which was calculated through the consensus matrix. The new framework achieved an accuracy rate of 93.56 % for classifying ESRDaMCI patients, and outperformed the existing state-of-the-art methods in terms of sensitivity, specificity, and area under the curve.

CONCLUSIONS

This study contributes to effectively reflect the functional neural degradation of ESRDaMCI and provide a reference for the diagnosis of ESRDaMCI by selecting discriminative brain regions.

Classification of bipolar disorders using the multilayer modularity in dynamic minimum spanning tree from resting state fMRI

The diagnosis of bipolar disorders (BD) mainly depends on the clinical history and behavior observation, while only using clinical tools often limits the diagnosis accuracy. The study aimed to create a novel BD diagnosis framework using multilayer modularity in the dynamic minimum spanning tree (MST). We collected 45 un-medicated BD patients and 47 healthy controls (HC). The sliding window approach was utilized to construct dynamic MST via resting-state functional magnetic resonance imaging (fMRI) data. Firstly, we used three null models to explore the effectiveness of multilayer modularity in dynamic MST. Furthermore, the module allegiance exacted from dynamic MST was applied to train a classifier to discriminate BD patients. Finally, we explored the influence of the FC estimator and MST scale on the performance of the model. The findings indicated that multilayer modularity in the dynamic MST was not a random process in the human brain. And the model achieved an accuracy of 83.70% for identifying BD patients. In addition, we found the default mode network, subcortical network (SubC), and attention network played a key role in the classification. These findings suggested that the multilayer modularity in dynamic MST could highlight the difference between HC and BD patients, which opened up a new diagnostic tool for BD patients.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11571-022-09907-x.

Extracting transition features among brain states based on coarse-grained similarity measurement for autism spectrum disorder analysis

BACKGROUND

The abnormal brain functional connectivity (FC) of patients with mental diseases is closely linked to the transition features among brain states. However, the current research on state transition will produce certain division deviations in the measurement method of state division, and also ignore the transition features among multiple states that contain more abundant information for analyzing brain diseases.

PURPOSE

To investigate the potential of the proposed method based on coarse-grained similarity measurement to solve the problem of state division, and consider the transition features among multiple states to analyze the FC abnormalities of autism spectrum disorder (ASD) patients.

METHODS

We used resting-state functional magnetic resonance imaging to examine 45 ASD and 47 healthy controls (HC). The FC between brain regions was calculated by the sliding window and correlation algorithm, and a novel coarse-grained similarity measure method was used to cluster the FC networks into five states, and then extract the features both of the state itself and the transition features among multiple states for analysis and diagnosis.

RESULTS

(1) The state as divided by the coarse-grained measurement method improves the diagnostic performance of individuals with ASD compared with previous methods. (2) The transition features among multiple states can provide complementary information to the features of the state itself in the ASD analysis and diagnosis. (3) ASD individuals have different brain state transitions than HC. Specifically, the abnormalities in intra- and inter-network connectivity of ASD patients mainly occur in the default mode network, the visual network, and the cerebellum.

CONCLUSIONS

Such results demonstrate that our approach with new measurements and new features is effective and promising in brain state analysis and ASD diagnosis.

A generic framework for embedding human brain function with temporally correlated autoencoder

Learning an effective and compact representation of human brain function from high-dimensional fMRI data is crucial for studying the brain's functional organization. Traditional representation methods such as independent component analysis (ICA) and sparse dictionary learning (SDL) mainly rely on matrix decomposition which represents the brain function as spatial brain networks and the corresponding temporal patterns. The correspondence of those brain networks across individuals are built by viewing them as one-hot vectors and then performing the matching. However, those one-hot vectors do not encode the regularity and/or variability of different brains very well, and thus are limited in effectively representing the functional brain activities across individuals and among different time points. To address this problem, in this paper, we formulate the human brain functional representation as an embedding problem, and propose a novel embedding framework based on the Transformer model to encode the brain function in a compact, stereotyped and comparable latent space where the brain activities are represented as dense embedding vectors. We evaluate the proposed embedding framework on the publicly available Human Connectome Project (HCP) task fMRI dataset. The experiments on brain state prediction task indicate the effectiveness and generalizability of the learned embedding. We also explore the interpretability of the learned embedding from both spatial and temporal perspective. In general, our approach provides novel insights on representing the regularity and variability of human brain function in a general, comparable, and stereotyped latent space.

Computing personalized brain functional networks from fMRI using self-supervised deep learning

A novel self-supervised deep learning (DL) method is developed to compute personalized brain functional networks (FNs) for characterizing brain functional neuroanatomy based on functional MRI (fMRI). Specifically, a DL model of convolutional neural networks with an encoder-decoder architecture is developed to compute personalized FNs directly from fMRI data. The DL model is trained to optimize functional homogeneity of personalized FNs without utilizing any external supervision in an end-to-end fashion. We demonstrate that a DL model trained on fMRI scans from the Human Connectome Project can identify personalized FNs and generalizes well across four different datasets. We further demonstrate that the identified personalized FNs are informative for predicting individual differences in behavior, brain development, and schizophrenia status. Taken together, the self-supervised DL allows for rapid, generalizable computation of personalized FNs.

Hierarchical Individual Naturalistic Functional Brain Networks with Group Consistency uncovered by a Two-Stage NAS-Volumetric Sparse DBN Framework

The functional magnetic resonance imaging under naturalistic paradigm (NfMRI) showed great advantages in identifying complex and interactive functional brain networks due to its dynamics and multimodal information. In recent years, various deep learning models, such as deep convolutional autoencoder (DCAE), deep belief network (DBN) and volumetric sparse deep belief network (vsDBN), can obtain hierarchical functional brain networks (FBN) and temporal features from fMRI data. Among them, the vsDBN model revealed a good capability in identifying hierarchical FBNs by modelling fMRI volume images. However, due to the high dimensionality of fMRI volumes and the diverse training parameters of deep learning methods, especially the network architecture that is the most critical parameter for uncovering the hierarchical organization of human brain function, researchers still face challenges in designing an appropriate deep learning framework with automatic network architecture optimization to model volumetric NfMRI. In addition, most of the existing deep learning models ignore the group-wise consistency and inter-subject variation properties embedded in NfMRI volumes. To solve these problems, we proposed a two-stage neural architecture search and vs DBN model (two-stage NAS-vsDBN model) to identify the hierarchical human brain spatio-temporal features possessing both group-consistency and individual-uniqueness under naturalistic condition. Moreover, our model defined reliable network structure for modelling volumetric NfMRI data via NAS framework, and the group-level and individual-level FBNs and associated temporal features exhibited great consistency. In general, our method well identified the hierarchical temporal and spatial features of the brain function and revealed the crucial properties of neural processes under natural viewing condition.Significance StatementIn this paper, we proposed and applied a novel analytical strategy - a two-stage NAS-vsDBN model to identify both group-level and individual-level spatio-temporal features at multi-scales from volumetric NfMRI data. The proposed PSO-based NAS framework can find optimal neural structure for both group-wise and individual-level vs-DBN models. Furthermore, with well-established correspondence between two stages of vsDBN models, our model can effectively detect group-level FBNs that reveal the consistency in neural processes across subjects and individual-level FBNs that maintain the subject specific variability, verifying the inherent property of brain function under naturalistic condition.

Hierarchical Spatio-Temporal Modeling of Naturalistic Functional Magnetic Resonance Imaging Signals via Two-Stage Deep Belief Network With Neural Architecture Search

Naturalistic functional magnetic resonance imaging (NfMRI) has become an effective tool to study brain functional activities in real-life context, which reduces the anxiety or boredom due to difficult or repetitive tasks and avoids the problem of unreliable collection of brain activity caused by the subjects’ microsleeps during resting state. Recent studies have made efforts on characterizing the brain’s hierarchical organizations from fMRI data by various deep learning models. However, most of those models have ignored the properties of group-wise consistency and inter-subject difference in brain function under naturalistic paradigm. Another critical issue is how to determine the optimal neural architecture of deep learning models, as manual design of neural architecture is time-consuming and less reliable. To tackle these problems, we proposed a two-stage deep belief network (DBN) with neural architecture search (NAS) combined framework (two-stage NAS-DBN) to model both the group-consistent and individual-specific naturalistic functional brain networks (FBNs), which reflected the hierarchical organization of brain function and the nature of brain functional activities under naturalistic paradigm. Moreover, the test-retest reliability and spatial overlap rate of the FBNs identified by our model reveal better performance than that of widely used traditional methods. In general, our model provides a promising method for characterizing hierarchical spatiotemporal features under the natural paradigm.