Learning Brain Connectivity Sub-networks by Group- Constrained Sparse Inverse Covariance Estimation for Alzheimer's Disease Classification

Mild cognitive impairment prediction based on multi-stream convolutional neural networks

BACKGROUND

Mild cognitive impairment (MCI) is the transition stage between the cognitive decline expected in normal aging and more severe cognitive decline such as dementia. The early diagnosis of MCI plays an important role in human healthcare. Current methods of MCI detection include cognitive tests to screen for executive function impairments, possibly followed by neuroimaging tests. However, these methods are expensive and time-consuming. Several studies have demonstrated that MCI and dementia can be detected by machine learning technologies from different modality data. This study proposes a multi-stream convolutional neural network (MCNN) model to predict MCI from face videos.

RESULTS

The total effective data are 48 facial videos from 45 participants, including 35 videos from normal cognitive participants and 13 videos from MCI participants. The videos are divided into several segments. Then, the MCNN captures the latent facial spatial features and facial dynamic features of each segment and classifies the segment as MCI or normal. Finally, the aggregation stage produces the final detection results of the input video. We evaluate 27 MCNN model combinations including three ResNet architectures, three optimizers, and three activation functions. The experimental results showed that the ResNet-50 backbone with Swish activation function and Ranger optimizer produces the best results with an F1-score of 89% at the segment level. However, the ResNet-18 backbone with Swish and Ranger achieves the F1-score of 100% at the participant level.

CONCLUSIONS

This study presents an efficient new method for predicting MCI from facial videos. Studies have shown that MCI can be detected from facial videos, and facial data can be used as a biomarker for MCI. This approach is very promising for developing accurate models for screening MCI through facial data. It demonstrates that automated, non-invasive, and inexpensive MCI screening methods are feasible and do not require highly subjective paper-and-pencil questionnaires. Evaluation of 27 model combinations also found that ResNet-50 with Swish is more stable for different optimizers. Such results provide directions for hyperparameter tuning to further improve MCI predictions.

Identifying discriminative features of brain network for prediction of Alzheimer's disease using graph theory and machine learning

Alzheimer's disease (AD) is a challenging neurodegenerative condition, necessitating early diagnosis and intervention. This research leverages machine learning (ML) and graph theory metrics, derived from resting-state functional magnetic resonance imaging (rs-fMRI) data to predict AD. Using Southwest University Adult Lifespan Dataset (SALD, age 21-76 years) and the Open Access Series of Imaging Studies (OASIS, age 64-95 years) dataset, containing 112 participants, various ML models were developed for the purpose of AD prediction. The study identifies key features for a comprehensive understanding of brain network topology and functional connectivity in AD. Through a 5-fold cross-validation, all models demonstrate substantial predictive capabilities (accuracy in 82-92% range), with the support vector machine model standing out as the best having an accuracy of 92%. Present study suggests that top 13 regions, identified based on most important discriminating features, have lost significant connections with thalamus. The functional connection strengths were consistently declined for substantia nigra, pars reticulata, substantia nigra, pars compacta, and nucleus accumbens among AD subjects as compared to healthy adults and aging individuals. The present finding corroborate with the earlier studies, employing various neuroimagining techniques. This research signifies the translational potential of a comprehensive approach integrating ML, graph theory and rs-fMRI analysis in AD prediction, offering potential biomarker for more accurate diagnostics and early prediction of AD.

Effective hyper-connectivity network construction and learning: Application to major depressive disorder identification

Functional connectivity (FC) derived from resting-state fMRI (rs-fMRI) is a primary approach for identifying brain diseases, but it is limited to capturing the pairwise correlation between regions-of-interest (ROIs) in the brain. Thus, hyper-connectivity which describes the higher-order relationship among multiple ROIs is receiving increasing attention. However, most hyper-connectivity methods overlook the directionality of connections. The direction of information flow constitutes a pivotal factor in shaping brain activity and cognitive processes. Neglecting this directional aspect can lead to an incomplete understanding of high-order interactions within the brain. To this end, we propose a novel effective hyper-connectivity (EHC) network that integrates direction detection and hyper-connectivity modeling. It characterizes the high-order directional information flow among multiple ROIs, providing a more comprehensive understanding of brain activity. Then, we develop a directed hypergraph convolutional network (DHGCN) to acquire deep representations from EHC network and functional indicators of ROIs. In contrast to conventional hypergraph convolutional networks designed for undirected hypergraphs, DHGCN is specifically tailored to handle directed hypergraph data structures. Moreover, unlike existing methods that primarily focus on fMRI time series, our proposed DHGCN model also incorporates multiple functional indicators, providing a robust framework for feature learning. Finally, deep representations generated via DHGCN, combined with demographic factors, are used for major depressive disorder (MDD) identification. Experimental results demonstrate that the proposed framework outperforms both FC and undirected hyper-connectivity models, as well as surpassing other state-of-the-art methods. The identification of EHC abnormalities through our framework can enhance the analysis of brain function in individuals with MDD.

Virtual Adversarial Training-Based Deep Feature Aggregation Network From Dynamic Effective Connectivity for MCI Identification

Dynamic functional connectivity (dFC) network inferred from resting-state fMRI reveals macroscopic dynamic neural activity patterns for brain disease identification. However, dFC methods ignore the causal influence between the brain regions. Furthermore, due to the complex non-Euclidean structure of brain networks, advanced deep neural networks are difficult to be applied for learning high-dimensional representations from brain networks. In this paper, a group constrained Kalman filter (gKF) algorithm is proposed to construct dynamic effective connectivity (dEC), where the gKF provides a more comprehensive understanding of the directional interaction within the dynamic brain networks than the dFC methods. Then, a novel virtual adversarial training convolutional neural network (VAT-CNN) is employed to extract the local features of dEC. The VAT strategy improves the robustness of the model to adversarial perturbations, and therefore avoids the overfitting problem effectively. Finally, we propose the high-order connectivity weight-guided graph attention networks (cwGAT) to aggregate features of dEC. By injecting the weight information of high-order connectivity into the attention mechanism, the cwGAT provides more effective high-level feature representations than the conventional GAT. The high-level features generated from the cwGAT are applied for binary classification and multiclass classification tasks of mild cognitive impairment (MCI). Experimental results indicate that the proposed framework achieves the classification accuracy of 90.9%, 89.8%, and 82.7% for normal control (NC) vs. early MCI (EMCI), EMCI vs. late MCI (LMCI), and NC vs. EMCI vs. LMCI classification respectively, outperforming the state-of-the-art methods significantly.

Convolutional Neural Network With Graphical Lasso to Extract Sparse Topological Features for Brain Disease Classification

The functional connectivity provides new insights into the mechanisms of the human brain at network-level, which has been proved to be an effective biomarker for brain disease classification. Recently, machine learning methods have played an important role in functional connectivity classification, among which convolutional neural network (CNN) based methods become a new hot topic since they can extract topological features in the brain network. However, the conventional CNN-based methods haven't taken sparse connectivity patterns (SCPs) of the human brain into consideration, which may lead to redundancy of the topological features, and limit their performance and generalization. To solve it, we propose a novel CNN-based model with graphical Lasso (CNNGLasso) to extract sparse topological features for brain disease classification. First, we develop a novel graphical Lasso model for revealing the SCPs at group-level. Then, the SCPs are used to guide the topological feature extraction. Finally, the obtained sparse topological features are used to classify the patients from normal controls. The experiment results on the ABIDE dataset demonstrate that the CNNGLasso outperforms the others on various performances. Besides, the abnormal brain regions derived from the trained model are consistent with the previous investigations, which further proves the application prospect of the CNNGLasso.

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

Recently, machine learning methods have gained lots of attention from researchers seeking to analyze brain images such as Resting-State Functional Magnetic Resonance Imaging (rs-fMRI) to obtain a deeper understanding of the brain and such related diseases, for example, Alzheimer's disease. Finding the common patterns caused by a brain disorder through analysis of the functional connectivity (FC) network along with discriminating brain diseases from normal controls have long been the two principal goals in studying rs-fMRI data. The majority of FC extraction methods calculate the FC matrix for each subject and then use simple techniques to combine them and obtain a general FC matrix. In addition, the state-of-the-art classification techniques for finding subjects with brain disorders also rely on calculating an FC for each subject, vectorizing, and feeding them to the classifier. Considering these problems and based on multi-dimensional nature of the data, we have come up with a novel tensor framework in which a general FC matrix is obtained without the need to construct an FC matrix for each sample. This framework also allows us to reduce the dimensionality and create a novel discriminant function that rather than using FCs works directly with each sample, avoids vectorization in any step, and uses the test data in the training process without forcing any prior knowledge of its label into the classifier. Extensive experiments using the ADNI dataset demonstrate that our proposed framework effectively boosts the fMRI classification performance and reveals novel connectivity patterns in Alzheimer's disease at its early stages.

Fusion of ULS Group Constrained High- and Low-Order Sparse Functional Connectivity Networks for MCI Classification

Functional connectivity networks, derived from resting-state fMRI data, have been found as effective biomarkers for identifying mild cognitive impairment (MCI) from healthy elderly. However, the traditional functional connectivity network is essentially a low-order network with the assumption that the brain activity is static over the entire scanning period, ignoring temporal variations among the correlations derived from brain region pairs. To overcome this limitation, we proposed a new type of sparse functional connectivity network to precisely describe the relationship of temporal correlations among brain regions. Specifically, instead of using the simple pairwise Pearson's correlation coefficient as connectivity, we first estimate the temporal low-order functional connectivity for each region pair based on an ULS Group constrained-UOLS regression algorithm, where a combination of ultra-least squares (ULS) criterion with a Group constrained topology structure detection algorithm is applied to detect the topology of functional connectivity networks, aided by an Ultra-Orthogonal Least Squares (UOLS) algorithm to estimate connectivity strength. Compared to the classical least squares criterion which only measures the discrepancy between the observed signals and the model prediction function, the ULS criterion takes into consideration the discrepancy between the weak derivatives of the observed signals and the model prediction function and thus avoids the overfitting problem. By using a similar approach, we then estimate the high-order functional connectivity from the low-order connectivity to characterize signal flows among the brain regions. We finally fuse the low-order and the high-order networks using two decision trees for MCI classification. Experimental results demonstrate the effectiveness of the proposed method on MCI classification.

Deep Spatial-Temporal Feature Fusion From Adaptive Dynamic Functional Connectivity for MCI Identification

Dynamic functional connectivity (dFC) analysis using resting-state functional Magnetic Resonance Imaging (rs-fMRI) is currently an advanced technique for capturing the dynamic changes of neural activities in brain disease identification. Most existing dFC modeling methods extract dynamic interaction information by using the sliding window-based correlation, whose performance is very sensitive to window parameters. Because few studies can convincingly identify the optimal combination of window parameters, sliding window-based correlation may not be the optimal way to capture the temporal variability of brain activity. In this paper, we propose a novel adaptive dFC model, aided by a deep spatial-temporal feature fusion method, for mild cognitive impairment (MCI) identification. Specifically, we adopt an adaptive Ultra-weighted-lasso recursive least squares algorithm to estimate the adaptive dFC, which effectively alleviates the problem of parameter optimization. Then, we extract temporal and spatial features from the adaptive dFC. In order to generate coarser multi-domain representations for subsequent classification, the temporal and spatial features are further mapped into comprehensive fused features with a deep feature fusion method. Experimental results show that the classification accuracy of our proposed method is reached to 87.7%, which is at least 5.5% improvement than the state-of-the-art methods. These results elucidate the superiority of the proposed method for MCI classification, indicating its effectiveness in the early identification of brain abnormalities.

Effective Diagnosis of Alzheimer's Disease via Multimodal Fusion Analysis Framework

Alzheimer’s disease (AD) is a complex neurodegenerative disease involving a variety of pathogenic factors, and the etiology detection of this disease has been a major concern of researchers. Neuroimaging is a basic and important means to explore the problem. It is the main current scientific research direction for combining neuroimaging with other modal data to dig deep into the potential information of AD through the complementarities among multiple data points. Machine learning methods possess great potentiality and have reached some achievements in this research area. A few studies have proposed some solutions to the effects of multimodal data fusion, however, the overall analytical framework for data fusion and fusion result analysis has thus far been ignored. In this paper, we first put forward a novel multimodal data fusion method, and further present a new machine learning framework of data fusion, classification, feature selection, and disease-causing factor extraction. The real dataset of 37 AD patients and 35 normal controls (NC) with functional magnetic resonance imaging (fMRI) and genetic data was used to verify the effectiveness of the framework, which was more accurate in classification and optimal feature extraction than other methods. Furthermore, we revealed disease-causing brain regions and genes, such as the olfactory cortex, insula, posterior cingulate gyrus, lingual gyrus, CNTNAP2, LRP1B, FRMD4A, and DAB1. The results show that the machine learning framework could effectively perform multimodal data fusion analysis, providing new insights and perspectives for the diagnosis of Alzheimer’s disease.

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.