Bao Ge

Supervised Dictionary Learning for Inferring Concurrent Brain Networks

Task-based fMRI (tfMRI) has been widely used to explore functional brain networks via predefined stimulus paradigm in the fMRI scan. Traditionally, the general linear model (GLM) has been a dominant approach to detect task-evoked networks. However, GLM focuses on task-evoked or event-evoked brain responses and possibly ignores the intrinsic brain functions. In comparison, dictionary learning and sparse coding methods have attracted much attention recently, and these methods have shown the promise of automatically and systematically decomposing fMRI signals into meaningful task-evoked and intrinsic concurrent networks. Nevertheless, two notable limitations of current data-driven dictionary learning method are that the prior knowledge of task paradigm is not sufficiently utilized and that the establishment of correspondences among dictionary atoms in different brains have been challenging. In this paper, we propose a novel supervised dictionary learning and sparse coding method for inferring functional networks from tfMRI data, which takes both of the advantages of model-driven method and data-driven method. The basic idea is to fix the task stimulus curves as predefined model-driven dictionary atoms and only optimize the other portion of data-driven dictionary atoms. Application of this novel methodology on the publicly available human connectome project (HCP) tfMRI datasets has achieved promising results.

Resting state fMRI-guided fiber clustering: methods and applications.

Clustering streamline fibers derived from diffusion tensor imaging (DTI) data into functionally meaningful bundles with group-wise correspondences across individuals and populations has been a fundamental step for tract-based analysis of white matter integrity and brain connectivity modeling. Many approaches of fiber clustering reported in the literature so far used geometric and/or anatomic information derived from structural MRI and/or DTI data only. In this paper, we take a novel, alternative multimodal approach of combining resting state fMRI (rsfMRI) and DTI data, and propose to use functional coherence as the criterion to guide the clustering of fibers derived from DTI tractography. Specifically, the functional coherence between two streamline fibers is defined as their rsfMRI time series’ correlations, and the affinity propagation (AP) algorithm is used to cluster DTI-derived streamline fibers into bundles. Currently, we use the corpus callosum (CC) fibers, which are the largest fiber bundle in the brain, as a test-bed for methodology development and validation. Our experimental results have shown that the proposed rsfMRI-guided fiber clustering method can achieve functionally homogeneous bundles that are reasonably consistent across individuals and populations, suggesting the close relationship between structural connectivity and brain function. The clustered fiber bundles were evaluated and validated via the benchmark data provided by task-based fMRI, via reproducibility studies, and via comparison with other methods. Finally, we have applied the proposed framework on a multimodal rsfMRI/DTI dataset of schizophrenia (SZ) and reproducible results were obtained.

HAFNI-enabled largescale platform for neuroimaging informatics (HELPNI).

Tremendous efforts have thus been devoted on the establishment of functional MRI informatics systems that recruit a comprehensive collection of statistical/computational approaches for fMRI data analysis. However, the state-of-the-art fMRI informatics systems are especially designed for specific fMRI sessions or studies of which the data size is not really big, and thus has difficulty in handling fMRI ‘big data.’ Given the size of fMRI data are growing explosively recently due to the advancement of neuroimaging technologies, an effective and efficient fMRI informatics system which can process and analyze fMRI big data is much needed. To address this challenge, in this work, we introduce our newly developed informatics platform, namely, ‘HAFNI-enabled largescale platform for neuroimaging informatics (HELPNI).’ HELPNI implements our recently developed computational framework of sparse representation of whole-brain fMRI signals which is called holistic atlases of functional networks and interactions (HAFNI) for fMRI data analysis. HELPNI provides integrated solutions to archive and process large-scale fMRI data automatically and structurally, to extract and visualize meaningful results information from raw fMRI data, and to share open-access processed and raw data with other collaborators through web. We tested the proposed HELPNI platform using publicly available 1000 Functional Connectomes dataset including over 1200 subjects. We identified consistent and meaningful functional brain networks across individuals and populations based on resting state fMRI (rsfMRI) big data. Using efficient sampling module, the experimental results demonstrate that our HELPNI system has superior performance than other systems for large-scale fMRI data in terms of processing and storing the data and associated results much faster.

Connectome-scale group-wise consistent resting-state network analysis in autism spectrum disorder

•A new effective volumetric network descriptor, named connectivity map.•A novel Spark-enabled functional connectomics framework•Identified 144 group-wisely common intrinsic connectivity networks (ICNs).•Revealed connectomics signatures characterizing and differentiating ASD patients and controls.

Group-wise consistent fiber clustering based on multimodal connectional and functional profiles.

Fiber clustering is an essential step towards brain connectivity modeling and tract-based analysis of white matter integrity via diffusion tensor imaging (DTI) in many clinical neuroscience applications. A variety of methods have been developed to cluster fibers based on various types of features such as geometry, anatomy, connection, or function. However, identification of group-wise consistent fiber bundles that are harmonious across multi-modalities is rarely explored yet. This paper proposes a novel hybrid two-stage approach that incorporates connectional and functional features, and identifies group-wise consistent fiber bundles across subjects. In the first stage, based on our recently developed 358 dense and consistent cortical landmarks, we identified consistent backbone bundles with representative fibers. In the second stage, other remaining fibers are then classified into the existing backbone bundles using their correlations of resting state fMRI signals at the two ends of fibers. Our experimental results show that the proposed methods can achieve group-wise consistent fiber bundles with similar shapes and anatomic profiles, as well as strong functional coherences.

Signal sampling for efficient sparse representation of resting state FMRI data.

As the size of brain imaging data such as fMRI grows explosively, it provides us with unprecedented and abundant information about the brain. How to reduce the size of fMRI data but not lose much information becomes a more and more pressing issue. Recent literature studies tried to deal with it by dictionary learning and sparse representation methods, however, their computation complexities are still high, which hampers the wider application of sparse representation method to large scale fMRI datasets. To effectively address this problem, this work proposes to represent resting state fMRI (rs-fMRI) signals of a whole brain via a statistical sampling based sparse representation. First we sampled the whole brain’s signals via different sampling methods, then the sampled signals were aggregate into an input data matrix to learn a dictionary, finally this dictionary was used to sparsely represent the whole brain’s signals and identify the resting state networks. Comparative experiments demonstrate that the proposed signal sampling framework can speed-up by ten times in reconstructing concurrent brain networks without losing much information. The experiments on the 1000 Functional Connectomes Project further demonstrate its effectiveness and superiority.

Construction of Multi-Scale Consistent Brain Networks: Methods and Applications

Mapping human brain networks provides a basis for studying brain function and dysfunction, and thus has gained significant interest in recent years. However, modeling human brain networks still faces several challenges including constructing networks at multiple spatial scales and finding common corresponding networks across individuals. As a consequence, many previous methods were designed for a single resolution or scale of brain network, though the brain networks are multi-scale in nature. To address this problem, this paper presents a novel approach to constructing multi-scale common structural brain networks from DTI data via an improved multi-scale spectral clustering applied on our recently developed and validated DICCCOLs (Dense Individualized and Common Connectivity-based Cortical Landmarks). Since the DICCCOL landmarks possess intrinsic structural correspondences across individuals and populations, we employed the multi-scale spectral clustering algorithm to group the DICCCOL landmarks and their connections into sub-networks, meanwhile preserving the intrinsically-established correspondences across multiple scales. Experimental results demonstrated that the proposed method can generate multi-scale consistent and common structural brain networks across subjects, and its reproducibility has been verified by multiple independent datasets. As an application, these multi-scale networks were used to guide the clustering of multi-scale fiber bundles and to compare the fiber integrity in schizophrenia and healthy controls. In general, our methods offer a novel and effective framework for brain network modeling and tract-based analysis of DTI data.

Automatic clustering of white matter fibers based on symbolic sequence analysis

Fiber clustering is a very important step towards tract-based, quantitative analysis of white matter via diffusion tensor imaging (DTI). This work proposes a new computational framework for white matter fiber clustering based on symbolic sequence analysis method. We first perform brain tissue segmentation on the DTI image using a multi-channel fusion method and parcellate the whole brain into anatomically labeled regions via a hybrid volumetric and surface warping algorithm. Then, we perform standard fiber tractography on the DTI image and encode each tracked fiber by a sequence of labeled brain regions. Afterwards, the similarity between any pair of anatomically encoded fibers is defined as the similarity of symbolic sequences, which is a well-studied problem in the bioinformatics domain such as is used for gene and protein symbolic sequences comparisons. Finally, the normalized graph cut algorithm is applied to cluster the fibers into bundles based on the above defined similarities between any pair of fibers. Our experiments show promising results of the proposed fiber clustering framework.

Exploring auditory network composition during free listening to audio excerpts via group-wise sparse representation

With the growing number of audio excerpts through various media and distribution channels, advanced audio analysis approaches have received significant interest in the multimedia field. However, current audio analysis approaches are still far from satisfactory due to the semantic gaps between the low-level acoustic features and high-level semantics perceived by human brain. In order to alleviate the problem, this paper propose a novel computational framework to bridge acoustic features with high-level semantic features derived from functional magnetic resonance imaging (fMRI) signals which record the brains response during free listening to music/speech excerpts, and to explore the brain auditory network composition of acoustic features for different types of music/speech excerpts. Specifically, we identify meaningful brain networks and corresponding brain activities representing high-level semantic features via a novel group-wise sparse representation of whole brain fMRI signals. Then we associate the brain activities with specific low-level acoustic features and analyze the auditory network composition of acoustic features for different types of music/speech excerpts. Experimental results demonstrate that multiple acoustic features are involved in the brain auditory networks during free listening to music/speech excerpts. Meanwhile, there is considerable variability of auditory network composition of acoustic features for different types of music/speech. Our results provide new insights of how to narrow the semantic gaps in audio content analysis.

Construction of multi-scale brain networks via DICCCOL landmarks

Mapping human brain networks has gained significant interest in the last few years, as it offers novel perspectives on the brain structure and function. However, most previous approaches were dedicated to a single resolution or scale of brain network, though the brain networks are multi-scale in nature. This paper presents a novel approach to constructing multi-scale structural brain networks from DTI images via multi-scale spectral clustering of our recently developed and validated DICCCOLs (Dense Individualized and Common Connectivity-based Cortical Landmarks). Since the DICCCOL landmarks possess structural and functional correspondences across subjects, the constructed multi-scale networks also have intrinsically-established correspondences across different brains, which is a prominent feature of this network construction method. Experimental results demonstrated that the proposed method can generated consistent and common structural brain networks, which will lay down the foundation for many other network-based neuroimaging analyses in the future.