arXiv subjects

Chee-Ming Ting

Publications and source records attributed to Chee-Ming Ting.

34 records · Page 2Linked to original sources

arXiv2024

Dynamic MRI reconstruction using low-rank plus sparse decomposition with smoothness regularization

The low-rank plus sparse (L+S) decomposition model has enabled better reconstruction of dynamic magnetic resonance imaging (dMRI) with separation into background (L) and dynamic (S) component. However, use of low-rank prior alone may not fully explain the slow variations or smoothness of the background part at the local scale. In this paper, we propose a smoothness-regularized L+S (SR-L+S) model for dMRI reconstruction from highly undersampled k-t-space data. We exploit joint low-rank and smooth priors on the background component of dMRI to better capture both its global and local temporal correlated structures. Extending the L+S formulation, the low-rank property is encoded by the nuclear norm, while the smoothness by a general \ell_{p}-norm penalty on the local differences of the columns of L. The additional smoothness regularizer can promote piecewise local consistency between neighboring frames. By smoothing out the noise and dynamic activities, it allows accurate recovery of the background part, and subsequently more robust dMRI reconstruction. Extensive experiments on multi-coil cardiac and synthetic data shows that the SR-L+S model outp

eess.IV↗

arXiv2023

RCS-YOLO: A Fast and High-Accuracy Object Detector for Brain Tumor Detection

With an excellent balance between speed and accuracy, cutting-edge YOLO frameworks have become one of the most efficient algorithms for object detection. However, the performance of using YOLO networks is scarcely investigated in brain tumor detection. We propose a novel YOLO architecture with Reparameterized Convolution based on channel Shuffle (RCS-YOLO). We present RCS and a One-Shot Aggregation of RCS (RCS-OSA), which link feature cascade and computation efficiency to extract richer information and reduce time consumption. Experimental results on the brain tumor dataset Br35H show that the proposed model surpasses YOLOv6, YOLOv7, and YOLOv8 in speed and accuracy. Notably, compared with YOLOv7, the precision of RCS-YOLO improves by 1%, and the inference speed by 60% at 114.8 images detected per second (FPS). Our proposed RCS-YOLO achieves state-of-the-art performance on the brain tumor detection task. The code is available at https://github.com/mkang315/RCS-YOLO.

cs.CV↗

arXiv2022

Graph-Regularized Manifold-Aware Conditional Wasserstein GAN for Brain Functional Connectivity Generation

Common measures of brain functional connectivity (FC) including covariance and correlation matrices are semi-positive definite (SPD) matrices residing on a cone-shape Riemannian manifold. Despite its remarkable success for Euclidean-valued data generation, use of standard generative adversarial networks (GANs) to generate manifold-valued FC data neglects its inherent SPD structure and hence the inter-relatedness of edges in real FC. We propose a novel graph-regularized manifold-aware conditional Wasserstein GAN (GR-SPD-GAN) for FC data generation on the SPD manifold that can preserve the global FC structure. Specifically, we optimize a generalized Wasserstein distance between the real and generated SPD data under an adversarial training, conditioned on the class labels. The resulting generator can synthesize new SPD-valued FC matrices associated with different classes of brain networks, e.g., brain disorder or healthy control. Furthermore, we introduce additional population graph-based regularization terms on both the SPD manifold and its tangent space to encourage the generator to respect the inter-subject similarity of FC patterns in the real data. This also helps in avoiding mode collapse and produces more stable GAN training. Evaluated on resting-state functional magnetic resonance imaging (fMRI) data of major depressive disorder (MDD), qualitative and quantitative results show that the proposed GR-SPD-GAN clearly outperforms several state-of-the-art GANs in generating more realistic fMRI-based FC samples. When applied to FC data augmentation for MDD identification, classification models trained on augmented data generated by our approach achieved the largest margin of improvement in classification accuracy among the competing GANs over baselines without data augmentation.

cs.LG↗

arXiv2022

Graph Autoencoders for Embedding Learning in Brain Networks and Major Depressive Disorder Identification

Brain functional connectivity (FC) reveals biomarkers for identification of various neuropsychiatric disorders. Recent application of deep neural networks (DNNs) to connectome-based classification mostly relies on traditional convolutional neural networks using input connectivity matrices on a regular Euclidean grid. We propose a graph deep learning framework to incorporate the non-Euclidean information about graph structure for classifying functional magnetic resonance imaging (fMRI)-derived brain networks in major depressive disorder (MDD). We design a novel graph autoencoder (GAE) architecture based on the graph convolutional networks (GCNs) to embed the topological structure and node content of large-sized fMRI networks into low-dimensional latent representations. In network construction, we employ the Ledoit-Wolf (LDW) shrinkage method to estimate the high-dimensional FC metrics efficiently from fMRI data. We consider both supervised and unsupervised approaches for the graph embedding learning. The learned embeddings are then used as feature inputs for a deep fully-connected neural network (FCNN) to discriminate MDD from healthy controls. Evaluated on two resting-state fMRI (rs-fMRI) MDD datasets, results show that the proposed GAE-FCNN model significantly outperforms several state-of-the-art methods for brain connectome classification, achieving the best accuracy using the LDW-FC edges as node features. The graph embeddings of fMRI FC networks learned by the GAE also reveal apparent group differences between MDD and HC. Our new framework demonstrates feasibility of learning graph embeddings on brain networks to provide discriminative information for diagnosis of brain disorders.

q-bio.NC↗

arXiv2021

BICNet: A Bayesian Approach for Estimating Task Effects on Intrinsic Connectivity Networks in fMRI Data

Intrinsic connectivity networks (ICNs) are specific dynamic functional brain networks that are consistently found under various conditions including rest and task. Studies have shown that some stimuli actually activate intrinsic connectivity through either suppression, excitation, moderation or modification. Nevertheless, the structure of ICNs and task-related effects on ICNs are not yet fully understood. In this paper, we propose a Bayesian Intrinsic Connectivity Network (BICNet) model to identify the ICNs and quantify the task-related effects on the ICN dynamics. Using an extended Bayesian dynamic sparse latent factor model, the proposed BICNet has the following advantages: (1) it simultaneously identifies the individual ICNs and group-level ICN spatial maps; (2) it robustly identifies ICNs by jointly modeling resting-state functional magnetic resonance imaging (rfMRI) and task-related functional magnetic resonance imaging (tfMRI); (3) compared to independent component analysis (ICA)-based methods, it can quantify the difference of ICNs amplitudes across different states; (4) it automatically performs feature selection through the sparsity of the ICNs rather than ad-hoc thresholding. The proposed BICNet was applied to the rfMRI and language tfMRI data from the Human Connectome Project (HCP) and the analysis identified several ICNs related to distinct language processing functions.

stat.AP↗

arXiv2021

Markov-Switching State-Space Models with Applications to Neuroimaging

State-space models (SSM) with Markov switching offer a powerful framework for detecting multiple regimes in time series, analyzing mutual dependence and dynamics within regimes, and asserting transitions between regimes. These models however present considerable computational challenges due to the exponential number of possible regime sequences to account for. In addition, high dimensionality of time series can hinder likelihood-based inference. This paper proposes novel statistical methods for Markov-switching SSMs using maximum likelihood estimation, Expectation-Maximization (EM), and parametric bootstrap. We develop solutions for initializing the EM algorithm, accelerating convergence, and conducting inference that are ideally suited to massive spatio-temporal data such as brain signals. We evaluate these methods in simulations and present applications to EEG studies of epilepsy and of motor imagery. All proposed methods are implemented in a MATLAB toolbox available at https://github.com/ddegras/switch-ssm.

stat.ME↗

arXiv2021

Separating Stimulus-Induced and Background Components of Dynamic Functional Connectivity in Naturalistic fMRI

We consider the challenges in extracting stimulus-related neural dynamics from other intrinsic processes and noise in naturalistic functional magnetic resonance imaging (fMRI). Most studies rely on inter-subject correlations (ISC) of low-level regional activity and neglect varying responses in individuals. We propose a novel, data-driven approach based on low-rank plus sparse (L+S) decomposition to isolate stimulus-driven dynamic changes in brain functional connectivity (FC) from the background noise, by exploiting shared network structure among subjects receiving the same naturalistic stimuli. The time-resolved multi-subject FC matrices are modeled as a sum of a low-rank component of correlated FC patterns across subjects, and a sparse component of subject-specific, idiosyncratic background activities. To recover the shared low-rank subspace, we introduce a fused version of principal component pursuit (PCP) by adding a fusion-type penalty on the differences between the rows of the low-rank matrix. The method improves the detection of stimulus-induced group-level homogeneity in the FC profile while capturing inter-subject variability. We develop an efficient algorithm via a linearized alternating direction method of multipliers to solve the fused-PCP. Simulations show accurate recovery by the fused-PCP even when a large fraction of FC edges are severely corrupted. When applied to natural fMRI data, our method reveals FC changes that were time-locked to auditory processing during movie watching, with dynamic engagement of sensorimotor systems for speech-in-noise. It also provides a better mapping to auditory content in the movie than ISC.

q-bio.NC↗

arXiv2020

Detecting Dynamic Community Structure in Functional Brain Networks Across Individuals: A Multilayer Approach

We present a unified statistical framework for characterizing community structure of brain functional networks that captures variation across individuals and evolution over time. Existing methods for community detection focus only on single-subject analysis of dynamic networks; while recent extensions to multiple-subjects analysis are limited to static networks. To overcome these limitations, we propose a multi-subject, Markov-switching stochastic block model (MSS-SBM) to identify state-related changes in brain community organization over a group of individuals. We first formulate a multilayer extension of SBM to describe the time-dependent, multi-subject brain networks. We develop a novel procedure for fitting the multilayer SBM that builds on multislice modularity maximization which can uncover a common community partition of all layers (subjects) simultaneously. By augmenting with a dynamic Markov switching process, our proposed method is able to capture a set of distinct, recurring temporal states with respect to inter-community interactions over subjects and the change points between them. Simulation shows accurate community recovery and tracking of dynamic community regimes over multilayer networks by the MSS-SBM. Application to task fMRI reveals meaningful non-assortative brain community motifs, e.g., core-periphery structure at the group level, that are associated with language comprehension and motor functions suggesting their putative role in complex information integration. Our approach detected dynamic reconfiguration of modular connectivity elicited by varying task demands and identified unique profiles of intra and inter-community connectivity across different task conditions. The proposed multilayer network representation provides a principled way of detecting synchronous, dynamic modularity in brain networks across subjects.

cs.LG↗

arXiv2019

Statistical Model for Dynamically-Changing Correlation Matrices with Application to Brain Connectivity

Background: Recent studies have indicated that functional connectivity is dynamic even during rest. A common approach to modeling the dynamic functional connectivity in whole-brain resting-state fMRI is to compute the correlation between anatomical regions via sliding time windows. However, the direct use of the sample correlation matrices is not reliable due to the image acquisition and processing noises in resting-sate fMRI. New method: To overcome these limitations, we propose a new statistical model that smooths out the noise by exploiting the geometric structure of correlation matrices. The dynamic correlation matrix is modeled as a linear combination of symmetric positive-definite matrices combined with cosine series representation. The resulting smoothed dynamic correlation matrices are clustered into disjoint brain connectivity states using the k-means clustering algorithm. Results: The proposed model preserves the geometric structure of underlying physiological dynamic correlation, eliminates unwanted noise in connectivity and obtains more accurate state spaces. The difference in the estimated dynamic connectivity states between males and females is identified. Comparison with existing methods: We demonstrate that the proposed statistical model has less rapid state changes caused by noise and improves the accuracy in identifying and discriminating different states. Conclusions: We propose a new regression model on dynamically changing correlation matrices that provides better performance over existing windowed correlation and is more reliable for the modeling of dynamic connectivity.

q-bio.NC↗

arXiv2019

Classification of EEG-Based Brain Connectivity Networks in Schizophrenia Using a Multi-Domain Connectome Convolutional Neural Network

We exploit altered patterns in brain functional connectivity as features for automatic discriminative analysis of neuropsychiatric patients. Deep learning methods have been introduced to functional network classification only very recently for fMRI, and the proposed architectures essentially focused on a single type of connectivity measure. We propose a deep convolutional neural network (CNN) framework for classification of electroencephalogram (EEG)-derived brain connectome in schizophrenia (SZ). To capture complementary aspects of disrupted connectivity in SZ, we explore combination of various connectivity features consisting of time and frequency-domain metrics of effective connectivity based on vector autoregressive model and partial directed coherence, and complex network measures of network topology. We design a novel multi-domain connectome CNN (MDC-CNN) based on a parallel ensemble of 1D and 2D CNNs to integrate the features from various domains and dimensions using different fusion strategies. Hierarchical latent representations learned by the multiple convolutional layers from EEG connectivity reveal apparent group differences between SZ and healthy controls (HC). Results on a large resting-state EEG dataset show that the proposed CNNs significantly outperform traditional support vector machine classifiers. The MDC-CNN with combined connectivity features further improves performance over single-domain CNNs using individual features, achieving remarkable accuracy of $93.06\%$ with a decision-level fusion. The proposed MDC-CNN by integrating information from diverse brain connectivity descriptors is able to accurately discriminate SZ from HC. The new framework is potentially useful for developing diagnostic tools for SZ and other disorders.

cs.LG↗

arXiv2018

Short-segment heart sound classification using an ensemble of deep convolutional neural networks

This paper proposes a framework based on deep convolutional neural networks (CNNs) for automatic heart sound classification using short-segments of individual heart beats. We design a 1D-CNN that directly learns features from raw heart-sound signals, and a 2D-CNN that takes inputs of two- dimensional time-frequency feature maps based on Mel-frequency cepstral coefficients (MFCC). We further develop a time-frequency CNN ensemble (TF-ECNN) combining the 1D-CNN and 2D-CNN based on score-level fusion of the class probabilities. On the large PhysioNet CinC challenge 2016 database, the proposed CNN models outperformed traditional classifiers based on support vector machine and hidden Markov models with various hand-crafted time- and frequency-domain features. Best classification scores with 89.22% accuracy and 89.94% sensitivity were achieved by the ECNN, and 91.55% specificity and 88.82% modified accuracy by the 2D-CNN alone on the test set.

cs.SD↗

arXiv2018

Modeling Brain Connectivity with Graphical Models on Frequency Domain

Multichannel electroencephalograms (EEGs) have been widely used to study cortical connectivity during acquisition of motor skills. In this paper, we introduce copula Gaussian graphical models on spectral domain to characterize dependence in oscillatory activity between channels. To obtain a simple and robust representation of brain connectivity that can explain the most variation in the observed signals, we propose a framework based on maximizing penalized likelihood with Lasso regularization to search for the sparse precision matrix. To address the optimization problem, graphical Lasso, Ledoit-Wolf and sparse estimation of a covariance matrix (SPCOV) algorithms were modified and implemented. Simulations show the benefit of using the proposed algorithms in terms of robustness and small estimation errors. Furthermore, analysis of the EEG data in a motor skill task conducted using algorithms of modified graphical LASSO and Ledoit-Wolf, reveal a sparse pattern of brain connectivity among cortices which is consistent with the results from other work in the literature.

stat.AP↗

arXiv2018

A Markov-Switching Model Approach to Heart Sound Segmentation and Classification

Objective: This paper considers challenges in developing algorithms for accurate segmentation and classification of heart sound (HS) signals. Methods: We propose an approach based on Markov switching autoregressive model (MSAR) to segmenting the HS into four fundamental components each with distinct second-order structure. The identified boundaries are then utilized for automated classification of pathological HS using the continuous density hidden Markov model (CD-HMM). The MSAR formulated in a state-space form is able to capture simultaneously both the continuous hidden dynamics in HS, and the regime switching in the dynamics using a discrete Markov chain. This overcomes the limitation of HMM which uses a single-layer of discrete states. We introduce three schemes for model estimation: (1.) switching Kalman filter (SKF); (2.) refined SKF; (3.) fusion of SKF and the duration-dependent Viterbi algorithm (SKF-Viterbi). Results: The proposed methods are evaluated on Physionet/CinC Challenge 2016 database. The SKF-Viterbi significantly outperforms SKF by improvement of segmentation accuracy from 71% to 84.2%. The use of CD-HMM as a classifier and Mel-frequency cepstral coefficients (MFCCs) as features can characterize not only the normal and abnormal morphologies of HS signals but also morphologies considered as unclassifiable (denoted as X-Factor). It gives classification rates with best gross F1 score of 90.19 (without X-Factor) and 82.7 (with X-Factor) for abnormal beats. Conclusion: The proposed MSAR approach for automatic localization and detection of pathological HS shows a noticeable performance on large HS dataset. Significance: It has potential applications in heart monitoring systems to assist cardiologists for pre-screening of heart pathologies.

eess.SP↗

arXiv2017

Multi-Scale Factor Analysis of High-Dimensional Brain Signals

In this paper, we develop an approach to modeling high-dimensional networks with a large number of nodes arranged in a hierarchical and modular structure. We propose a novel multi-scale factor analysis (MSFA) model which partitions the massive spatio-temporal data defined over the complex networks into a finite set of regional clusters. To achieve further dimension reduction, we represent the signals in each cluster by a small number of latent factors. The correlation matrix for all nodes in the network are approximated by lower-dimensional sub-structures derived from the cluster-specific factors. To estimate regional connectivity between numerous nodes (within each cluster), we apply principal components analysis (PCA) to produce factors which are derived as the optimal reconstruction of the observed signals under the squared loss. Then, we estimate global connectivity (between clusters or sub-networks) based on the factors across regions using the RV-coefficient as the cross-dependence measure. This gives a reliable and computationally efficient multi-scale analysis of both regional and global dependencies of the large networks. The proposed novel approach is applied to estimate brain connectivity networks using functional magnetic resonance imaging (fMRI) data. Results on resting-state fMRI reveal interesting modular and hierarchical organization of human brain networks during rest.

stat.AP↗

arXiv2017

Estimating Time-Varying Effective Connectivity in High-Dimensional fMRI Data Using Regime-Switching Factor Models

Recent studies on analyzing dynamic brain connectivity rely on sliding-window analysis or time-varying coefficient models which are unable to capture both smooth and abrupt changes simultaneously. Emerging evidence suggests state-related changes in brain connectivity where dependence structure alternates between a finite number of latent states or regimes. Another challenge is inference of full-brain networks with large number of nodes. We employ a Markov-switching dynamic factor model in which the state-driven time-varying connectivity regimes of high-dimensional fMRI data are characterized by lower-dimensional common latent factors, following a regime-switching process. It enables a reliable, data-adaptive estimation of change-points of connectivity regimes and the massive dependencies associated with each regime. We consider the switching VAR to quantity the dynamic effective connectivity. We propose a three-step estimation procedure: (1) extracting the factors using principal component analysis (PCA) and (2) identifying dynamic connectivity states using the factor-based switching vector autoregressive (VAR) models in a state-space formulation using Kalman filter and expectation-maximization (EM) algorithm, and (3) constructing the high-dimensional connectivity metrics for each state based on subspace estimates. Simulation results show that our proposed estimator outperforms the K-means clustering of time-windowed coefficients, providing more accurate estimation of regime dynamics and connectivity metrics in high-dimensional settings. Applications to analyzing resting-state fMRI data identify dynamic changes in brain states during rest, and reveal distinct directed connectivity patterns and modular organization in resting-state networks across different states.

stat.AP↗

arXiv2016

Exploratory Analysis of High Dimensional Time Series with Applications to Multichannel Electroencephalograms

In this paper, we address the the major hurdle of high dimensionality in EEG analysis by extracting the optimal lower dimensional representations. Using our approach, connectivity between regions in a high-dimensional brain network is characterized through the connectivity between region-specific factors. The proposed approach is motivated by our observation that electroencephalograms (EEGs) from channels within each region exhibit a high degree of multicollinearity and synchrony. These observations suggest that it would be sensible to extract summary factors for each region. We consider the general approach for deriving summary factors which are solutions to the criterion of squared error reconstruction. In this work, we focus on two special cases of linear auto encoder and decoder. In the first approach, the factors are characterized as instantaneous linear mixing of the observed high dimensional time series. In the second approach, the factors signals are linear filtered versions of the original signal which is more general than an instantaneous mixing. This exploratory analysis is the starting point to the multi-scale factor analysis model where the concatenated factors from all regions are represented by vector auto-regressive model that captures the connectivity in high dimensional signals. We performed evaluations on the two approaches via simulations under different conditions. The simulation results provide insights on the performance and application scope of the methods. We also performed exploratory analysis of EEG recorded over several epochs during resting state. Finally, we implemented these exploratory methods in a Matlab toolbox XHiDiTS available from https://goo.gl/uXc8ei .

stat.AP↗