skip to main content


Title: A CONTRASTIVE LEARNING-BASED APPROACH TO MEASURE SPATIAL COUPLING AMONG BRAIN NETWORKS: A SCHIZOPHRENIA STUDY
Resting-state functional magnetic resonance imaging (rsfMRI) has become a widely used approach for detecting subtle differences in functional brain fluctuations in various studies of the healthy and disordered brain. Such studies are often based on temporal functional connectivity (i.e., the correlation between time courses derived from regions or networks within the fMRI data). While being successful for a number of tasks, temporal connectivity does not fully leverage the available spatial information. In this research study, we present a new perspective on spatial functional connectivity, which involves learning patterns of spatial coupling among brain networks by utilizing recent advances in deep learning as well as the contrastive learning framework. We show that we can learn domain-specific mappings of brain networks that can, in turn, be used to characterize differences between schizophrenia patients and control. Furthermore, we show that the coupling of intradomain networks in the controls is stronger than in patients suffering from the disorder. We also evaluate the coupling among networks of different domains and find various patterns of stronger or weaker coupling among certain domains, which provide additional insights about the brain.  more » « less
Award ID(s):
2112455
NSF-PAR ID:
10332735
Author(s) / Creator(s):
;
Date Published:
Journal Name:
IEEE International Symposium on Biomedical Imaging (ISBI)
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    The analysis of time‐varying activity and connectivity patterns (i.e., the chronnectome) using resting‐state magnetic resonance imaging has become an important part of ongoing neuroscience discussions. The majority of previous work has focused on variations of temporal coupling among fixed spatial nodes or transition of the dominant activity/connectivity pattern over time. Here, we introduce an approach to capture spatial dynamics within functional domains (FDs), as well as temporal dynamics within and between FDs. The approach models the brain as a hierarchical functional architecture with different levels of granularity, where lower levels have higher functional homogeneity and less dynamic behavior and higher levels have less homogeneity and more dynamic behavior. First, a high‐order spatial independent component analysis is used to approximate functional units. A functional unit is a pattern of regions with very similar functional activity over time. Next, functional units are used to construct FDs. Finally, functional modules (FMs) are calculated from FDs, providing an overall view of brain dynamics. Results highlight the spatial fluidity within FDs, including a broad spectrum of changes in regional associations, from strong coupling to complete decoupling. Moreover, FMs capture the dynamic interplay between FDs. Patients with schizophrenia show transient reductions in functional activity and state connectivity across several FDs, particularly the subcortical domain. Activity and connectivity differences convey unique information in many cases (e.g., the default mode) highlighting their complementarity information. The proposed hierarchical model to capture FD spatiotemporal variations provides new insight into the macroscale chronnectome and identifies changes hidden from existing approaches.

     
    more » « less
  2. Abstract

    The brain is highly dynamic, reorganizing its activity at different interacting spatial and temporal scales, including variation within and between brain networks. The chronnectome is a model of the brain in which nodal activity and connectivity patterns change in fundamental and recurring ways over time. Most literature assumes fixed spatial nodes/networks, ignoring the possibility that spatial nodes/networks may vary in time. Here, we introduce an approach to calculate a spatially fluid chronnectome (called the spatial chronnectome for clarity), which focuses on the variations of networks coupling at the voxel level, and identify a novel set of spatially dynamic features. Results reveal transient spatially fluid interactions between intra‐ and internetwork relationships in which brain networks transiently merge and separate, emphasizing dynamic segregation and integration. Brain networks also exhibit distinct spatial patterns with unique temporal characteristics, potentially explaining a broad spectrum of inconsistencies in previous studies that assumed static networks. Moreover, we show anticorrelative connections to brain networks are transient as opposed to constant across the entire scan. Preliminary assessments using a multi‐site dataset reveal the ability of the approach to obtain new information and nuanced alterations that remain undetected during static analysis. Patients with schizophrenia (SZ) display transient decreases in voxel‐wise network coupling within visual and auditory networks, and higher intradomain coupling variability. In summary, the spatial chronnectome represents a new direction of research enabling the study of functional networks which are transient at the voxel level, and the identification of mechanisms for within‐ and between‐subject spatial variability.

     
    more » « less
  3. There is a growing research interest to extract the temporal dependency between brain networks. Among several existing methods, functional network connectivity (FNC) is one of the widely used approaches to capture the intrinsic functional relationships among brain networks. In this study, we introduced a novel approach that uses FNC matrices of Adolescent Brain and Cognitive Development (ABCD) data to evaluate multiple overlapping brain functional change patterns (FCPs). Results show several highly structured FCPs that have a significant change over a two-year period and become stronger with age including brain functional connectivity between visual (VS) and sensorimotor (SM) domains. Our approach is a powerful tool to visualize and evaluate patterns of whole brain functional changes in longitudinal data. 
    more » « less
  4. Abstract

    Previous studies have suggested that disorders of consciousness (DOC) after severe brain injury may result from disconnections of the thalamo‐cortical system. However, thalamo‐cortical connectivity differences between vegetative state (VS), minimally conscious state minus (MCS−, i.e., low‐level behavior such as visual pursuit), and minimally conscious state plus (MCS+, i.e., high‐level behavior such as language processing) remain unclear. Probabilistic tractography in a sample of 25 DOC patients was employed to assess whether structural connectivity in various thalamo‐cortical circuits could differentiate between VS, MCS−, and MCS+ patients. First, the thalamus was individually segmented into seven clusters based on patterns of cortical connectivity and tested for univariate differences across groups. Second, reconstructed whole‐brain thalamic tracks were used as features in a multivariate searchlight analysis to identify regions along the tracks that were most informative in distinguishing among groups. At the univariate level, it was found that VS patients displayed reduced connectivity in most thalamo‐cortical circuits of interest, including frontal, temporal, and sensorimotor connections, as compared with MCS+, but showed more pulvinar‐occipital connections when compared with MCS−. Moreover, MCS− exhibited significantly less thalamo‐premotor and thalamo‐temporal connectivity than MCS+. At the multivariate level, it was found that thalamic tracks reaching frontal, parietal, and sensorimotor regions, could discriminate, up to 100% accuracy, across each pairwise group comparison. Together, these findings highlight the role of thalamo‐cortical connections in patients' behavioral profile and level of consciousness. Diffusion tensor imaging combined with machine learning algorithms could thus potentially facilitate diagnostic distinctions in DOC and shed light on the neural correlates of consciousness.Hum Brain Mapp 38:431–443, 2017. ©2016 Wiley Periodicals, Inc.

     
    more » « less
  5. Abstract Cortical ischaemic strokes result in cognitive deficits depending on the area of the affected brain. However, we have demonstrated that difficulties with attention and processing speed can occur even with small subcortical infarcts. Symptoms appear independent of lesion location, suggesting they arise from generalized disruption of cognitive networks. Longitudinal studies evaluating directional measures of functional connectivity in this population are lacking. We evaluated six patients with minor stroke exhibiting cognitive impairment 6–8 weeks post-infarct and four age-similar controls. Resting-state magnetoencephalography data were collected. Clinical and imaging evaluations of both groups were repeated 6- and 12 months later. Network Localized Granger Causality was used to determine differences in directional connectivity between groups and across visits, which were correlated with clinical performance. Directional connectivity patterns remained stable across visits for controls. After the stroke, inter-hemispheric connectivity between the frontoparietal cortex and the non-frontoparietal cortex significantly increased between visits 1 and 2, corresponding to uniform improvement in reaction times and cognitive scores. Initially, the majority of functional links originated from non-frontal areas contralateral to the lesion, connecting to ipsilesional brain regions. By visit 2, inter-hemispheric connections, directed from the ipsilesional to the contralesional cortex significantly increased. At visit 3, patients demonstrating continued favourable cognitive recovery showed less reliance on these inter-hemispheric connections. These changes were not observed in those without continued improvement. Our findings provide supporting evidence that the neural basis of early post-stroke cognitive dysfunction occurs at the network level, and continued recovery correlates with the evolution of inter-hemispheric connectivity. 
    more » « less