Frequent and discriminative subnetwork mining for mild cognitive impairment classification

Diagnosis of Mild Cognitive Impairment with Ordinal Pattern Kernel

Mild cognitive impairment (MCI) belongs to the prodromal stage of Alzheimer's disease (AD). Accurate diagnosis of MCI is very important for possibly deferring AD progression. Graph kernels, which measure the similarity between paired brain connectivity networks, have been widely used to diagnose brain diseases (e.g., MCI) and yielded promising classification performance. However, most of the existing graph kernels are based on unweighted graphs, and neglect the valuable weighted information of the edges in brain connectivity networks where edge weights convey the strengths of fiber connection or temporal correlation between paired brain regions. Accordingly, in this paper, we propose a new graph kernel called ordinal pattern kernel for measuring brain connectivity network similarity and apply it to brain disease classification tasks. Different from the existing graph kernels which measure the topological similarity of the unweighted graphs, our proposed ordinal pattern kernel can not only calculate the similarity of paired brain connectivity networks, but also capture the ordinal pattern relationship of edge weights in brain connectivity networks. To appraise the effectiveness of our proposed method, we perform extensive experiments in functional magnetic resonance imaging data of brain disease from Alzheimer's Disease Neuroimaging Initiative database. The experimental results show that our proposed ordinal pattern kernel outperforms the state-of-the-art graph kernels in the classification tasks of MCI.

A Transdiagnostic Biotype Detection Method for Schizophrenia and Autism Spectrum Disorder Based on Graph Kernel

Psychiatric diagnoses based on clinical manifestations are prone to be inaccurate. Schizophrenia (SZ) and autism spectrum disorder (ASD) were historically considered as the same disorder, and they still have many overlaps of clinical symptoms in the current standard. Therefore, there is an urgent need to explore the potential biotypes for them using neuroimaging measures such as brain functional connectivity (FC). However, previous studies have not effectively leveraged FC in detecting biotypes. Considering that graph theory helps reveal the topological information in FC, in this paper, we propose a graph kernel-based clustering method to explore transdiagnostic biotypes using FC estimated from functional magnetic resonance imaging (fMRI) data. In our method, frequent subnetworks are identified from the whole-brain FCs of all subjects, and then the graph kernel similarity is computed to measure the relationship between subjects for clustering. Based on fMRI data of 137 SZ and 150 ASD subjects, we obtained meaningful biotypes using our method, which shows significant differences between the identified biotypes in FC. In brief, our graph kernel-based clustering method is promising for transdiagnostic biotype detection.

Brain functional network modeling and analysis based on fMRI: a systematic review

In recent years, the number of patients with neurodegenerative diseases (i.e., Alzheimer's disease, Parkinson's disease, mild cognitive impairment) and mental disorders (i.e., depression, anxiety and schizophrenia) have increased dramatically. Researchers have found that complex network analysis can reveal the topology of brain functional networks, such as small-world, scale-free, etc. In the study of brain diseases, it has been found that these topologies have undergoed abnormal changes in different degrees. Therefore, the research of brain functional networks can not only provide a new perspective for understanding the pathological mechanism of neurological and psychiatric diseases, but also provide assistance for the early diagnosis. Focusing on the study of human brain functional networks, this paper reviews the research results in recent years. First, this paper introduces the background of the study of brain functional networks under complex network theory and the important role of topological properties in the study of brain diseases. Second, the paper describes how to construct a brain functional network using neural image data. Third, the common methods of functional network analysis, including network structure analysis and disease classification, are introduced. Fourth, the role of brain functional networks in pathological study, analysis and diagnosis of brain functional diseases is studied. Finally, the paper summarizes the existing studies of brain functional networks and points out the problems and future research directions.

A Multichannel Deep Neural Network Model Analyzing Multiscale Functional Brain Connectome Data for Attention Deficit Hyperactivity Disorder Detection

Purpose

To develop a multichannel deep neural network (mcDNN) classification model based on multiscale brain functional connectome data and demonstrate the value of this model by using attention deficit hyperactivity disorder (ADHD) detection as an example.

Materials and Methods

In this retrospective case-control study, existing data from the Neuro Bureau ADHD-200 dataset consisting of 973 participants were used. Multiscale functional brain connectomes based on both anatomic and functional criteria were constructed. The mcDNN model used the multiscale brain connectome data and personal characteristic data (PCD) as joint features to detect ADHD and identify the most predictive brain connectome features for ADHD diagnosis. The mcDNN model was compared with single-channel deep neural network (scDNN) models and the classification performance was evaluated through cross-validation and hold-out validation with the metrics of accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).

Results

In the cross-validation, the mcDNN model using combined features (fusion of the multiscale brain connectome data and PCD) achieved the best performance in ADHD detection with an AUC of 0.82 (95% confidence interval [CI]: 0.80, 0.83) compared with scDNN models using the features of the brain connectome at each individual scale and PCD, independently. In the hold-out validation, the mcDNN model achieved an AUC of 0.74 (95% CI: 0.73, 0.76).

Conclusion

An mcDNN model was developed for multiscale brain functional connectome data, and its utility for ADHD detection was demonstrated. By fusing the multiscale brain connectome data, the mcDNN model improved ADHD detection performance considerably over the use of a single scale.© RSNA, 2019.

Hybrid Functional Brain Network With First-Order and Second-Order Information for Computer-Aided Diagnosis of Schizophrenia

Brain functional connectivity network (BFCN) analysis has been widely used in the diagnosis of mental disorders, such as schizophrenia. In BFCN methods, brain network construction is one of the core tasks due to its great influence on the diagnosis result. Most of the existing BFCN construction methods only consider the first-order relationship existing in each pair of brain regions and ignore the useful high-order information, including multi-region correlation in the whole brain. Some early schizophrenia patients have subtle changes in brain function networks, which cannot be detected in conventional BFCN construction methods. It is well-known that the high-order method is usually more sensitive to the subtle changes in signal than the low-order method. To exploit high-order information among brain regions, we define the triplet correlation among three brain regions, and derive the second-order brain network based on the connectivity difference and ordinal information in each triplet. For making full use of the complementary information in different brain networks, we proposed a hybrid approach to fuse the first- and second-order brain networks. The proposed method is applied to identify the biomarkers of schizophrenia. The experimental results on six schizophrenia datasets (totally including 439 patients and 426 controls) show that the proposed method outperforms the existing brain network methods in the diagnosis of schizophrenia.

Subnetwork mining on functional connectivity network for classification of minimal hepatic encephalopathy

Hepatic encephalopathy (HE), as a complication of cirrhosis, is a serious brain disease, which may lead to death. Accurate diagnosis of HE and its intermediate stage, i.e., minimal HE (MHE), is very important for possibly early diagnosis and treatment. Brain connectivity network, as a simple representation of brain interaction, has been widely used for the brain disease (e.g., HE and MHE) analysis. However, those studies mainly focus on finding disease-related abnormal connectivity between brain regions, although a large number of studies have indicated that some brain diseases are usually related to local structure of brain connectivity network (i.e., subnetwork), rather than solely on some single brain regions or connectivities. Also, mining such disease-related subnetwork is a challenging task because of the complexity of brain network. To address this problem, we proposed a novel frequent-subnetwork-based method to mine disease-related subnetworks for MHE classification. Specifically, we first mine frequent subnetworks from both groups, i.e., MHE patients and non-HE (NHE) patients, respectively. Then we used the graph-kernel based method to select the most discriminative subnetworks for subsequent classification. We evaluate our proposed method on a MHE dataset with 77 cirrhosis patients, including 38 MHE patients and 39 NHE patients. The results demonstrate that our proposed method can not only obtain the improved classification performance in comparison with state-of-the-art network-based methods, but also identify disease-related subnetworks which can help us better understand the pathology of the brain diseases.

Benchmarking functional connectome-based predictive models for resting-state fMRI

Functional connectomes reveal biomarkers of individual psychological or clinical traits. However, there is great variability in the analytic pipelines typically used to derive them from rest-fMRI cohorts. Here, we consider a specific type of studies, using predictive models on the edge weights of functional connectomes, for which we highlight the best modeling choices. We systematically study the prediction performances of models in 6 different cohorts and a total of 2000 individuals, encompassing neuro-degenerative (Alzheimer's, Post-traumatic stress disorder), neuro-psychiatric (Schizophrenia, Autism), drug impact (Cannabis use) clinical settings and psychological trait (fluid intelligence). The typical prediction procedure from rest-fMRI consists of three main steps: defining brain regions, representing the interactions, and supervised learning. For each step we benchmark typical choices: 8 different ways of defining regions -either pre-defined or generated from the rest-fMRI data- 3 measures to build functional connectomes from the extracted time-series, and 10 classification models to compare functional interactions across subjects. Our benchmarks summarize more than 240 different pipelines and outline modeling choices that show consistent prediction performances in spite of variations in the populations and sites. We find that regions defined from functional data work best; that it is beneficial to capture between-region interactions with tangent-based parametrization of covariances, a midway between correlations and partial correlation; and that simple linear predictors such as a logistic regression give the best predictions. Our work is a step forward to establishing reproducible imaging-based biomarkers for clinical settings.

Multimodal hyper-connectivity of functional networks using functionally-weighted LASSO for MCI classification

Recent works have shown that hyper-networks derived from blood-oxygen-level-dependent (BOLD) fMRI, where an edge (called hyper-edge) can be connected to more than two nodes, are effective biomarkers for MCI classification. Although BOLD fMRI is a high temporal resolution fMRI approach to assess alterations in brain networks, it cannot pinpoint to a single correlation of neuronal activity since BOLD signals are composite. In contrast, arterial spin labeling (ASL) is a lower temporal resolution fMRI technique for measuring cerebral blood flow (CBF) that can provide quantitative, direct brain network physiology measurements. This paper proposes a novel sparse regression algorithm for inference of the integrated hyper-connectivity networks from BOLD fMRI and ASL fMRI. Specifically, a least absolution shrinkage and selection operator (LASSO) algorithm, which is constrained by the functional connectivity derived from ASL fMRI, is employed to estimate hyper-connectivity for characterizing BOLD-fMRI-based functional interaction among multiple regions. An ASL-derived functional connectivity is constructed by using an Ultra-GroupLASSO-UOLS algorithm, where the combination of ultra-least squares (ULS) criterion with a group LASSO (GroupLASSO) algorithm is applied to detect the topology of ASL-based functional connectivity networks, and then an ultra-orthogonal least squares (UOLS) algorithm is used to estimate the connectivity strength. By combining the complementary characterization conveyed by rs-fMRI and ASL fMRI, our multimodal hyper-networks demonstrated much better discriminative characteristics than either the conventional pairwise connectivity networks or the unimodal hyper-connectivity networks. Experimental results on publicly available ADNI dataset demonstrate that the proposed method outperforms the existing single modality based sparse functional connectivity inference methods.

Integrating the Local Property and Topological Structure in the Minimum Spanning Tree Brain Functional Network for Classification of Early Mild Cognitive Impairment

Abnormalities in the brain connectivity in patients with neurodegenerative diseases, such as early mild cognitive impairment (EMCI), have been widely reported. Current research shows that the combination of multiple features of the threshold connectivity network can improve the classification accuracy of diseases. However, in the construction of the threshold connectivity network, the selection of the threshold is very important, and an unreasonable setting can seriously affect the final classification results. Recent neuroscience research suggests that the minimum spanning tree (MST) brain functional network is helpful, as it avoids the methodological biases while comparing networks. In this paper, by employing the multikernel method, we propose a framework to integrate the multiple properties of the MST brain functional network for improving the classification performance. Initially, the Kruskal algorithm was used to construct an unbiased MST brain functional network. Subsequently, the vector kernel and graph kernel were used to quantify the two different complementary properties of the network, such as the local connectivity property and the topological property. Finally, the multikernel support vector machine (SVM) was adopted to combine the two different kernels for EMCI classification. We tested the performance of our proposed method for Alzheimer's Disease Neuroimaging Initiative (ANDI) datasets. The results showed that our method achieved a significant performance improvement, with the classification accuracy of 85%. The abnormal brain regions included the right hippocampus, left parahippocampal gyrus, left posterior cingulate gyrus, middle temporal gyrus, and other regions that are known to be important in the EMCI. Our results suggested that, combining the multiple features of the MST brain functional connectivity offered a better classification performance in the EMCI.

fMRI classification method with multiple feature fusion based on minimum spanning tree analysis

Resting state functional brain networks have been widely studied in brain disease research. Conventional network analysis methods are hampered by differences in network size, density and normalization. Minimum spanning tree (MST) analysis has been recently suggested to ameliorate these limitations. Moreover, common MST analysis methods involve calculating quantifiable attributes and selecting these attributes as features in the classification. However, a disadvantage of these methods is that information about the topology of the network is not fully considered, limiting further improvement of classification performance. To address this issue, we propose a novel method combining brain region and subgraph features for classification, utilizing two feature types to quantify two properties of the network. We experimentally validated our proposed method using a major depressive disorder (MDD) patient dataset. The results indicated that MSTs of MDD patients were more similar to random networks and exhibited significant differences in certain regions involved in the limbic-cortical-striatal-pallidal-thalamic (LCSPT) circuit, which is considered to be a major pathological circuit of depression. Moreover, we demonstrated that this novel classification method could effectively improve classification accuracy and provide better interpretability. Overall, the current study demonstrated that different forms of feature representation provide complementary information.

Ordinal Pattern: A New Descriptor for Brain Connectivity Networks

Brain connectivity networks based on magnetic resonance imaging (MRI) or functional MRI (fMRI) data provide a straightforward way to quantify the structural or functional systems of the brain. Currently, there are several network descriptors developed for representing and analyzing brain connectivity networks. However, most of them are designed for unweighted networks, regardless of the valuable weight information of edges, or do not take advantage of the ordinal relationship of weighted edges (even though they are designed for weighted networks). In this paper, we propose a new network descriptor (i.e., ordinal pattern that contains a sequence of weighted edges) for brain connectivity network analysis. Compared with previous network properties, the proposed ordinal patterns cannot only take advantage of the weight information of edges but also explicitly model the ordinal relationship of weighted edges in brain connectivity networks. We further develop an ordinal pattern-based learning framework for brain disease diagnosis using resting-state fMRI data. Specifically, we first construct a set of brain functional connectivity networks, where each network is corresponding to a particular subject. We then develop an algorithm to identify ordinal patterns that frequently appear in brain connectivity networks of patients and normal controls. We further perform discriminative ordinal pattern selection and extract feature representations for subjects based on the selected ordinal patterns, followed by a learning model for automated brain disease diagnosis. Experimental results on both Alzheimer's Disease Neuroimaging Initiative and attention deficit hyperactivity disorder-200 data sets demonstrate that our method outperforms the several state-of-the-art approaches in the tasks of disease classification and clinical score regression.

Non-negative discriminative brain functional connectivity for identifying schizophrenia on resting-state fMRI

Background

Schizophrenia is a clinical syndrome, and its causes have not been well determined. The objective of this study was to investigate the alteration of brain functional connectivity between schizophrenia and healthy control, and present a practical solution for accurately identifying schizophrenia at single-subject level.

Methods

24 schizophrenia patients and 21 matched healthy subjects were recruited to undergo the resting-state functional magnetic resonance imaging (rs-fMRI) scanning. First, we constructed the brain network by calculating the Pearson correlation coefficient between each pair of the brain regions. Then, this study proposed a novel non-negative discriminant functional connectivity selection method, i.e. non-negative elastic-net based method (N2EN), to extract the alteration of brain functional connectivity between schizophrenia and healthy control. It ranks the significance of the connectivity with a uniform criterion by introducing the non-negative constraint. Finally, kernel discriminant analysis (KDA) is exploited to classify the subjects with the selected discriminant brain connectivity features.

Results

The proposed method is applied into schizophrenia classification, and achieves the sensitivity, specificity and accuracy of 100, 90.48 and 95.56%, respectively. Our findings also indicate the alteration of functional network can be used as the biomarks for guiding the schizophrenia diagnosis. The regions of cuneus, superior frontal gyrus, medial, paracentral lobule, calcarine fissure, surrounding cortex, etc. are highly relevant to schizophrenia.

Conclusions

This study provides a method for accurately identifying schizophrenia, which outperforms several state-of-the-art methods, including conventional brain network classification, multi-threshold brain network based classification, frequent sub-graph based brain network classification and support vector machine. Our investigation suggested that the selected discriminant resting-state functional connectivities are meaningful features for classifying schizophrenia and healthy control.

Brain multiplexes reveal morphological connectional biomarkers fingerprinting late brain dementia states

Accurate diagnosis of mild cognitive impairment (MCI) before conversion to Alzheimer's disease (AD) is invaluable for patient treatment. Many works showed that MCI and AD affect functional and structural connections between brain regions as well as the shape of cortical regions. However, 'shape connections' between brain regions are rarely investigated -e.g., how morphological attributes such as cortical thickness and sulcal depth of a specific brain region change in relation to morphological attributes in other regions. To fill this gap, we unprecedentedly design morphological brain multiplexes for late MCI/AD classification. Specifically, we use structural T1-w MRI to define morphological brain networks, each quantifying similarity in morphology between different cortical regions for a specific cortical attribute. Then, we define a brain multiplex where each intra-layer represents the morphological connectivity network of a specific cortical attribute, and each inter-layer encodes the similarity between two consecutive intra-layers. A significant performance gain is achieved when using the multiplex architecture in comparison to other conventional network analysis architectures. We also leverage this architecture to discover morphological connectional biomarkers fingerprinting the difference between late MCI and AD stages, which included the right entorhinal cortex and right caudal middle frontal gyrus.

Early prediction of cognitive deficits in very preterm infants using functional connectome data in an artificial neural network framework

Investigation of the brain's functional connectome can improve our understanding of how an individual brain's organizational changes influence cognitive function and could result in improved individual risk stratification. Brain connectome studies in adults and older children have shown that abnormal network properties may be useful as discriminative features and have exploited machine learning models for early diagnosis in a variety of neurological conditions. However, analogous studies in neonates are rare and with limited significant findings. In this paper, we propose an artificial neural network (ANN) framework for early prediction of cognitive deficits in very preterm infants based on functional connectome data from resting state fMRI. Specifically, we conducted feature selection via stacked sparse autoencoder and outcome prediction via support vector machine (SVM). The proposed ANN model was unsupervised learned using brain connectome data from 884 subjects in autism brain imaging data exchange database and SVM was cross-validated on 28 very preterm infants (born at 23-31 weeks of gestation and without brain injury; scanned at term-equivalent postmenstrual age). Using 90 regions of interests, we found that the ANN model applied to functional connectome data from very premature infants can predict cognitive outcome at 2 years of corrected age with an accuracy of 70.6% and area under receiver operating characteristic curve of 0.76. We also noted that several frontal lobe and somatosensory regions, significantly contributed to prediction of cognitive deficits 2 years later. Our work can be considered as a proof of concept for utilizing ANN models on functional connectome data to capture the individual variability inherent in the developing brains of preterm infants. The full potential of ANN will be realized and more robust conclusions drawn when applied to much larger neuroimaging datasets, as we plan to do.

Machine-Learning Classifier for Patients with Major Depressive Disorder: Multifeature Approach Based on a High-Order Minimum Spanning Tree Functional Brain Network

High-order functional connectivity networks are rich in time information that can reflect dynamic changes in functional connectivity between brain regions. Accordingly, such networks are widely used to classify brain diseases. However, traditional methods for processing high-order functional connectivity networks generally include the clustering method, which reduces data dimensionality. As a result, such networks cannot be effectively interpreted in the context of neurology. Additionally, due to the large scale of high-order functional connectivity networks, it can be computationally very expensive to use complex network or graph theory to calculate certain topological properties. Here, we propose a novel method of generating a high-order minimum spanning tree functional connectivity network. This method increases the neurological significance of the high-order functional connectivity network, reduces network computing consumption, and produces a network scale that is conducive to subsequent network analysis. To ensure the quality of the topological information in the network structure, we used frequent subgraph mining technology to capture the discriminative subnetworks as features and combined this with quantifiable local network features. Then we applied a multikernel learning technique to the corresponding selected features to obtain the final classification results. We evaluated our proposed method using a data set containing 38 patients with major depressive disorder and 28 healthy controls. The experimental results showed a classification accuracy of up to 97.54%.

Machine Learning Classification Combining Multiple Features of A Hyper-Network of fMRI Data in Alzheimer's Disease

Exploring functional interactions among various brain regions is helpful for understanding the pathological underpinnings of neurological disorders. Brain networks provide an important representation of those functional interactions, and thus are widely applied in the diagnosis and classification of neurodegenerative diseases. Many mental disorders involve a sharp decline in cognitive ability as a major symptom, which can be caused by abnormal connectivity patterns among several brain regions. However, conventional functional connectivity networks are usually constructed based on pairwise correlations among different brain regions. This approach ignores higher-order relationships, and cannot effectively characterize the high-order interactions of many brain regions working together. Recent neuroscience research suggests that higher-order relationships between brain regions are important for brain network analysis. Hyper-networks have been proposed that can effectively represent the interactions among brain regions. However, this method extracts the local properties of brain regions as features, but ignores the global topology information, which affects the evaluation of network topology and reduces the performance of the classifier. This problem can be compensated by a subgraph feature-based method, but it is not sensitive to change in a single brain region. Considering that both of these feature extraction methods result in the loss of information, we propose a novel machine learning classification method that combines multiple features of a hyper-network based on functional magnetic resonance imaging in Alzheimer's disease. The method combines the brain region features and subgraph features, and then uses a multi-kernel SVM for classification. This retains not only the global topological information, but also the sensitivity to change in a single brain region. To certify the proposed method, 28 normal control subjects and 38 Alzheimer's disease patients were selected to participate in an experiment. The proposed method achieved satisfactory classification accuracy, with an average of 91.60%. The abnormal brain regions included the bilateral precuneus, right parahippocampal gyrus\hippocampus, right posterior cingulate gyrus, and other regions that are known to be important in Alzheimer's disease. Machine learning classification combining multiple features of a hyper-network of functional magnetic resonance imaging data in Alzheimer's disease obtains better classification performance.

Resting-state whole-brain functional connectivity networks for MCI classification using L2-regularized logistic regression

Mild cognitive impairment (MCI) has been considered as a transition phase to Alzheimer's disease (AD), and the diagnosis of MCI may help patients to carry out appropriate treatments to delay or even prevent AD. Recent advanced network analysis techniques utilizing resting-state functional Magnetic Resonance Imaging (rs-fMRI) has been widely used to get more comprehensive understanding of neurological disorders at a whole-brain connectivity level. However, how to explore effective brain functional connectivity from fMRI data is still a challenge especially when the ultimate goal is to train classifiers for discriminating patients effectively. In our research, we studied the functional connectivity of the whole brain by calculating Pearson's correlation coefficients based on rs-fMRI data, and proposed a set of novel features by applying Two Sample T-Test on the correlation coefficients matrix to identify the most discriminative correlation coefficients. We trained a L2-regularized Logistic Regression classifier based on the five novel features for the first time and evaluated the classification performance via leave-one-out cross validation. We also iterated 10-fold cross validation ten times in order to evaluate the statistical significance of our method. The experiment result demonstrates that classification accuracy and the area under receiver operating characteristic (ROC) curve in our method are 87.5% and 0.929 respectively, and the statistical results prove that our method is statistically significant better than other three algorithms, which means our method could be meaningful to assist physicians efficiently in "real-world" diagnostic situations.