- NSF-PAR ID:
- 10359048
- Date Published:
- Journal Name:
- Medical Image Computing and Computer Assisted Intervention – MICCAI 2022. Lecture Notes in Computer Science.
- Volume:
- 13431
- Page Range / eLocation ID:
- 356–365
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
Brain large-scale dynamics is constrained by the heterogeneity of intrinsic anatomical substrate. Little is known how the spatiotemporal dynamics adapt for the heterogeneous structural connectivity (SC). Modern neuroimaging modalities make it possible to study the intrinsic brain activity at the scale of seconds to minutes. Diffusion magnetic resonance imaging (dMRI) and functional MRI reveals the large-scale SC across different brain regions. Electrophysiological methods (i.e. MEG/EEG) provide direct measures of neural activity and exhibits complex neurobiological temporal dynamics which could not be solved by fMRI. However, most of existing multimodal analytical methods collapse the brain measurements either in space or time domain and fail to capture the spatio-temporal circuit dynamics. In this paper, we propose a novel spatio-temporal graph Transformer model to integrate the structural and functional connectivity in both spatial and temporal domain. The proposed method learns the heterogeneous node and graph representation via contrastive learning and multi-head attention based graph Transformer using multimodal brain data (i.e. fMRI, MRI, MEG and behavior performance). The proposed contrastive graph Transformer representation model incorporates the heterogeneity map constrained by T1-to-T2-weighted (T1w/T2w) to improve the model fit to structurefunction interactions. The experimental results with multimodal resting state brain measurements demonstrate the proposed method could highlight the local properties of large-scale brain spatio-temporal dynamics and capture the dependence strength between functional connectivity and behaviors. In summary, the proposed method enables the complex brain dynamics explanation for different modal variants.more » « less
-
The transformation and transmission of brain stimuli reflect the dynamical brain activity in space and time. Compared with functional magnetic resonance imaging (fMRI), magneto- or electroencephalography (M/EEG) fast couples to the neural activity through generated magnetic fields. However, the MEG signal is inhomogeneous throughout the whole brain, which is affected by the signal-to-noise ratio, the sensors’ location and distance. Current non-invasive neuroimaging modalities such as fMRI and M/EEG excel high resolution in space or time but not in both. To solve the main limitations of current technique for brain activity recording, we propose a novel recurrent memory optimization approach to predict the internal behavioral states in space and time. The proposed method uses Optimal Polynomial Projections to capture the long temporal history with robust online compression. The training process takes the pairs of fMRI and MEG data as inputs and predicts the recurrent brain states through the Siamese network. In the testing process, the framework only uses fMRI data to generate the corresponding neural response in space and time. The experimental results with Human connectome project (HCP) show that the predicted signal could reflect the neural activity with high spatial resolution as fMRI and high temporal resolution as MEG signal. The experimental results demonstrate for the first time that the proposed method is able to predict the brain response in both milliseconds and millimeters using only fMRI signal.more » « less
-
Abstract Spontaneous infra-slow (<0.1 Hz) fluctuations in functional magnetic resonance imaging (fMRI) signals are temporally correlated within large-scale functional brain networks, motivating their use for mapping systems-level brain organization. However, recent electrophysiological and hemodynamic evidence suggest state-dependent propagation of infra-slow fluctuations, implying a functional role for ongoing infra-slow activity. Crucially, the study of infra-slow temporal lag structure has thus far been limited to large groups, as analyzing propagation delays requires extensive data averaging to overcome sampling variability. Here, we use resting-state fMRI data from 11 extensively-sampled individuals to characterize lag structure at the individual level. In addition to stable individual-specific features, we find spatiotemporal topographies in each subject similar to the group average. Notably, we find a set of early regions that are common to all individuals, are preferentially positioned proximal to multiple functional networks, and overlap with brain regions known to respond to diverse behavioral tasks—altogether consistent with a hypothesized ability to broadly influence cortical excitability. Our findings suggest that, like correlation structure, temporal lag structure is a fundamental organizational property of resting-state infra-slow activity.
-
Background Consumption of alcohol during pregnancy impacts fetal development and may lead to a variety of physical, cognitive, and behavioral abnormalities in childhood collectively known as fetal alcohol spectrum disorder (FASD). The FASD spectrum includes children with fetal alcohol syndrome (FAS), partial fetal alcohol syndrome (pFAS), and alcohol‐related neurodevelopmental disorder (ARND). Children with a FASD or prenatal alcohol exposure (PAE) have impaired white matter, reduced structural volumes, impaired resting‐state functional connectivity when measured with fMRI, and spectral hypersynchrony as infants. Magnetoencephalography (MEG) provides high temporal resolution and good spatial precision for examining spectral power and connectivity patterns unique from fMRI. The impact of PAE on MEG resting‐state spectral power in children remains unknown.
Methods We collected 2 minutes of eyes‐open and eyes‐closed resting‐state data in 51 children (8 to 12 years of age) with 3 subgroups included: 10 ARND/PAE, 15 FAS/pFAS, and 26 controls (TDC). MEG data were collected on the Elekta Neuromag system. The following spectral metrics were compared between subgroups: power, normalized power, half power, 95% power, and Shannon spectral entropy (SSE). MEG spectral data were correlated with behavioral measures.
Results Our results indicate children with FAS/pFAS had reduced spectral power and normalized power, particularly within the alpha frequency band in sensor parietal and source superior parietal and lateral occipital regions, along with elevated half power, 95% power, and SSE. We also found select hemisphere specific effects further indicating reduced corpus callosum connectivity in children with a FASD. Interestingly, while the ARND/PAE subgroup had significant differences from the FAS/pFAS subgroup, in many cases spectral data were not significantly different from TDC.
Conclusions Our results were consistent with previous studies and provide new insight into resting‐state oscillatory differences both between children with FAS and TDC, and within FASD subgroups. Further understanding of these resting‐state variations and their impact on cognitive function may help provide early targets for intervention and enhance outcomes for individuals with a FASD.
-
Background and Objectives: Prediction of decline to dementia using objective biomarkers in high-risk patients with amnestic mild cognitive impairment (aMCI) has immense utility. Our objective was to use multimodal MRI to (1) determine whether accurate and precise prediction of dementia conversion could be achieved using baseline data alone, and (2) generate a map of the brain regions implicated in longitudinal decline to dementia. Methods: Participants meeting criteria for aMCI at baseline ( N = 55) were classified at follow-up as remaining stable/improved in their diagnosis ( N = 41) or declined to dementia ( N = 14). Baseline T1 structural MRI and resting-state fMRI (rsfMRI) were combined and a semi-supervised support vector machine (SVM) which separated stable participants from those who decline at follow-up with maximal margin. Cross-validated model performance metrics and MRI feature weights were calculated to include the strength of each brain voxel in its ability to distinguish the two groups. Results: Total model accuracy for predicting diagnostic change at follow-up was 92.7% using baseline T1 imaging alone, 83.5% using rsfMRI alone, and 94.5% when combining T1 and rsfMRI modalities. Feature weights that survived the p < 0.01 threshold for separation of the two groups revealed the strongest margin in the combined structural and functional regions underlying the medial temporal lobes in the limbic system. Discussion: An MRI-driven SVM model demonstrates accurate and precise prediction of later dementia conversion in aMCI patients. The multi-modal regions driving this prediction were the strongest in the medial temporal regions of the limbic system, consistent with literature on the progression of Alzheimer’s disease.more » « less