30 April 2021 in IEEE Transactions on Medical Imaging
The combination of multimodal imaging and genomics provides a more comprehensive way for the study of mental illnesses and brain functions. Deep network-based data fusion models have been developed to capture their complex associations, resulting in improved diagnosis of diseases. However, deep learning models are often difficult to interpret, bringing about challenges for uncovering biological mechanisms using these models. In this work, we develop an interpretable multimodal fusion model to perform automated diagnosis and result interpretation simultaneously. We name it Grad-CAM guided convolutional collaborative learning (gCAM-CCL), which is achieved by combining intermediate feature maps with gradient-based weights. The gCAM-CCL model can generate interpretable activation maps to quantify pixel-level contributions of the input features. Moreover, the estimated activation maps are class-specific, which can therefore facilitate the identification of biomarkers underlying different groups. We validate the gCAM-CCL model on a brain imaging-genetic study, and demonstrate its applications to both the classification of cognitive function groups and the discovery of underlying biological mechanisms. Specifically, our analysis results suggest that during task-fMRI scans, several object recognition related regions of interests (ROIs) are activated followed by several downstream encoding ROIs. In addition, the high cognitive group may have stronger neurotransmission signaling while the low cognitive group may have problems in brain/neuron development due to genetic variations.
9 April 2021 in Human Brain Mapping
Functional network connectivity has been widely acknowledged to characterize brain functions, which can be regarded as “brain fingerprinting” to identify an individual from a pool of subjects. Both common and unique information has been shown to exist in the connectomes across individuals. However, very little is known about whether and how this information can be used to predict the individual variability of the brain. In this paper, we propose to enhance the uniqueness of individual connectome based on an autoencoder network. Specifically, we hypothesize that the common neural activities shared across individuals may reduce the individual identification. By removing contributions from shared activities, inter‐subject variability can be enhanced. Our experimental results on HCP data show that the refined connectomes obtained by utilizing autoencoder with sparse dictionary learning can distinguish an individual from the remaining participants with high accuracy (up to 99.5% for the rest–rest pair). Furthermore, high‐level cognitive behaviors (e.g., fluid intelligence, executive function, and language comprehension) can also be better predicted with the obtained refined connectomes. We also find that high‐order association cortices contribute more to both individual discrimination and behavior prediction. In summary, our proposed framework provides a promising way to leverage functional connectivity networks for cognition and behavior study, in addition to a better understanding of brain functions.
19 July 2019 in IEEE Transactions on Medical Imaging
Estimating dynamic functional network connectivity (dFNC) of the brain from functional magnetic resonance imaging (fMRI) data can reveal both spatial and temporal organization and can be applied to track the developmental trajectory of brain maturity as well as to study mental illness. Resting state fMRI (rs-fMRI) is regarded as a promising task since it reflects the spontaneous brain activity without an external stimulus. The sliding window method has been successfully used to extract dFNC but typically assumes a fixed window size. The hidden Markov model (HMM) based method is an alternative approach for estimating time-varying connectivity. In this paper, we propose a sparse HMM based on Gaussian HMM and Gaussian graphical model (GGM). In this model, the time-varying neural processes are represented as discrete brain states which are described with functional connectivity networks. By enforcing the sparsity on the precision matrix, we can get interpretable connectivity between different functional regions. The optimization of our model can be realized with the expectation maximization (EM) and graphical least absolute shrinkage and selection operator (glasso) algorithms. The proposed model is validated on both simulated blood oxygenation-level dependent (BOLD) time series and rs-fMRI data. Results indicate that the proposed model can capture both stationary and abrupt brain activity fluctuations. We also compare dFNC patterns between children and young adults from the Philadelphia Neurodevelopmental Cohort (PNC) study. Both spatial and temporal behavior of the dFNC are analyzed and compared. The results provide insight into the developmental trajectory across childhood and motivate further research on brain connectivity.
22 December 2017 in IEEE Transactions on Medical Imaging
Functional connectivity (FC) estimated from functional magnetic resonance imaging (fMRI) time series, especially during resting state periods, provides a powerful tool to assess human brain functional architecture in health, disease, and developmental states. Recently, the focus of connectivity analysis has shifted toward the subnetworks of the brain, which reveals co-activating patterns over time. Most prior works produced a dense set of high-dimensional vectors, which are hard to interpret. In addition, their estimations to a large extent were based on an implicit assumption of spatial and temporal stationarity throughout the fMRI scanning session. In this paper, we propose an approach called dynamic sparse connectivity patterns (dSCPs), which takes advantage of both matrix factorization and time-varying fMRI time series to improve the estimation power of FC. The feasibility of analyzing dynamic FC with our model is first validated through simulated experiments. Then, we use our framework to measure the difference between young adults and children with real fMRI data set from the Philadelphia Neurodevelopmental Cohort (PNC). The results from the PNC data set showed significant FC differences between young adults and children in four different states. For instance, young adults had reduced connectivity between the default mode network and other subnetworks, as well as hyperconnectivity within the visual system in states 1 and 3, and hypoconnectivity in state 2. Meanwhile, they exhibited temporal correlation patterns that changed over time within functional subnetworks. In addition, the dSCPs model indicated that older people tend to spend more time within a relatively connected FC pattern. Overall, the proposed method provides a valid means to assess dynamic FC, which could facilitate the study of brain networks.
9 November 2018 in IEEE Transactions on Biomedical Engineering
Functional connectivity (FC) within the human brain evaluated through functional magnetic resonance imaging (fMRI) data has attracted increasing attention and has been employed to study the development of the brain or health conditions of the brain. Many different approaches have been proposed to estimate FC from fMRI data, whereas many of them rely on an implicit assumption that functional connectivity should be static throughout the fMRI scan session. Recently, the fMRI community has realized the limitation of assuming static connectivity and dynamic approaches are more prominent in the resting state fMRI (rs-fMRI) analysis. The sliding window technique has been widely used in many studies to capture network dynamics, but has a number of limitations. In this study, we apply a time-varying graphical lasso (TVGL) model, an extension from the traditional graphical lasso, to address the challenge, which can greatly improve the estimation of FC. The performance of estimating dynamic FC is evaluated with the TVGL through both simulated experiments and real rs-fMRI data from the Philadelphia Neurodevelopmental Cohort project. Improved performance is achieved over the sliding window technique. In particular, group differences and transition behaviors between young adults and children are investigated using the estimated dynamic connectivity networks, which help us to better unveil the mechanisms underlying the evolution of the brain over time.
1 November 2020 in NeuroImage
Recently, functional network connectivity (FNC) has been extended from static to dynamic analysis to explore the time-varying functional organization of brain networks. Nowadays, a majority of dynamic FNC (dFNC) analysis frameworks identified recurring FNC patterns with linear correlations based on the amplitude of fMRI time series. However, the brain is a complex dynamical system and phase synchronization provides more informative measures. This paper proposes a novel framework for the prediction/classification of behaviors and cognitions based on the dFNCs derived from phase locking value. When applying to the analysis of fMRI data from Human Connectome Project (HCP), four dFNC states are identified for the study of sleep quality. State 1 exhibits most intense phase synchronization across the whole brain. States 2 and 3 have low and weak connections, respectively. State 4 exhibits strong phase synchronization in intra and inter-connections of somatomotor, visual and cognitive control networks. Through the two-sample t-test, we reveal that for the group with bad sleep quality, state 4 shows decreased phase synchronization within and between networks such as subcortical, auditory, somatomotor and visual, but increased phase synchronization within cognitive control network, and between this network and somatomotor/visual/default-mode/cerebellar networks. The networks with increased phase synchronization in state 4 behave oppositely in state 2. Group differences are absent in state 3, and weak in state 1. We establish a prediction model by linear regression of FNC against sleep quality, and adopt a support vector machine approach for the classification. We compare the performance between conventional FNC and PLV-based dFNC with cross-validation. Results show that the PLV-based dFNC significantly outperforms the conventional FNC in terms of both predictive power and classification accuracy. We also observe that combining static and dynamic features does not significantly improve the classification over using dFNC features alone. Overall, the proposed approach provides a novel means to assess dFNC, which can be used as brain fingerprints to facilitate prediction and classification.