BPARC: A novel spatio-temporal (4D) data-driven brain parcellation scheme based on deep residual networks

Kazemivash, Behnam; Calhoun, Vince D.

doi:10.1109/bibe50027.2020.00181

Cited by 7 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Spatiotemporal brain dynamism forms the backbone of our group comparison study, characterized by a 5D set of brain networks extracted from fMRI data. We incorporated a brain parcellation framework [20, 21] including 53 pre-trained models each of which produces a score map (probabilistic map) for a specific brain network, varying over space, time and across subjects and consequently is able to encode spatiotemporal brain dynamics. Each of the models is a residual U-Net style regressor containing 36 layers such as 3D convolution, transposed 3D convolution, max pooling, batch normalization, and dropout layers grouped into encoding and decoding blocks and was trained and evaluated using 1470 samples (volumes) from a subset of 3 preprocessed fMRI images in the UK Biobank dataset as the input and relevant extracted ICA maps as priors due to supervised training approach.…”

Section: Methodsmentioning

confidence: 99%

A deep residual model for characterization of 5D spatiotemporal network dynamics reveals widespread spatiodynamic changes in schizophrenia

Kazemivash

vanErp

Kochunov

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Schizophrenia is a severe brain disorder with serious symptoms including delusions, disorganized speech, and hallucinations that can have a long-term detrimental impact on different aspects of a patient's life. It is still unclear what the main cause of schizophrenia is, but a combination of altered brain connectivity and structure may play a role. Neuroimaging data has been useful in characterizing schizophrenia, but there has been very little work focused on voxel-wise changes in multiple brain networks over time, despite evidence that functional networks exhibit complex spatiotemporal changes over time within individual subjects. Recent studies have primarily focused on static (average) features of functional data or on temporal variations between fixed networks; however, such approaches are not able to capture multiple overlapping networks which change at the voxel level. In this work, we employ a deep residual convolutional neural network (CNN) model to extract 53 different spatiotemporal networks each of which captures dynamism within various domains including subcortical, cerebellar, visual, sensori-motor, auditory, cognitive control, and default mode. We apply this approach to study spatiotemporal brain dynamism at the voxel level within multiple functional networks extracted from a large functional magnetic resonance imaging (fMRI) dataset of individuals with schizophrenia (N=708) and controls (N=510). Our analysis reveals widespread group level differences across multiple networks and spatiotemporal features including voxel-wise variability, magnitude, and temporal functional network connectivity in widespread regions expected to be impacted by the disorder. We compare with typical average spatial amplitude and show highly structured and neuroanatomically relevant results are missed if one does not consider the voxel-wise spatial dynamics. Importantly, our approach can summarize static, temporal dynamic, spatial dynamic, and spatiotemporal dynamics features, thus proving a powerful approach to unify and compare these various perspectives. In sum, we show the proposed approach highlights the importance of accounting for both temporal and spatial dynamism in whole brain neuroimaging data generally, shows a high-level of sensitivity to schizophrenia highlighting global but spatially unique dynamics showing group differences, and may be especially important in studies focused on the development of brain-based biomarkers.

show abstract

Section: Methodsmentioning

confidence: 99%

A deep residual model for characterization of 5D spatiotemporal network dynamics reveals widespread spatiodynamic changes in schizophrenia

Kazemivash

vanErp

Kochunov

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Spatiotemporal brain dynamism forms the backbone of our group comparison study, characterized by a 5D set of brain networks extracted from fMRI data. We incorporated a brain parcellation framework (Kazemivash, 2020(Kazemivash, , 2022 including 53 pre-trained models each of which produces a score map (probabilistic map) for a specific brain network, varying over space, time and across subjects and consequently is able to encode spatiotemporal brain dynamics. Each of the models is a residual U-Net style regressor containing 36 layers such as 3D convolution, transposed 3D convolution, max pooling, batch normalization, and dropout layers grouped into encoding and decoding blocks and was trained and evaluated using 1,470 samples (volumes) from a subset of 3 preprocessed fMRI images in the UK Biobank dataset as the input and relevant extracted ICA maps as priors due to supervised training approach.…”

Section: Model Structurementioning

confidence: 99%

A deep residual model for characterization of 5D spatiotemporal network dynamics reveals widespread spatiodynamic changes in schizophrenia

Kazemivash¹,

Erp²,

Kochunov³

et al. 2023

Front. Neuroimaging

Self Cite

View full text Add to dashboard Cite

Schizophrenia is a severe brain disorder with serious symptoms including delusions, disorganized speech, and hallucinations that can have a long-term detrimental impact on different aspects of a patient's life. It is still unclear what the main cause of schizophrenia is, but a combination of altered brain connectivity and structure may play a role. Neuroimaging data has been useful in characterizing schizophrenia, but there has been very little work focused on voxel-wise changes in multiple brain networks over time, despite evidence that functional networks exhibit complex spatiotemporal changes over time within individual subjects. Recent studies have primarily focused on static (average) features of functional data or on temporal variations between fixed networks; however, such approaches are not able to capture multiple overlapping networks which change at the voxel level. In this work, we employ a deep residual convolutional neural network (CNN) model to extract 53 different spatiotemporal networks each of which captures dynamism within various domains including subcortical, cerebellar, visual, sensori-motor, auditory, cognitive control, and default mode. We apply this approach to study spatiotemporal brain dynamism at the voxel level within multiple functional networks extracted from a large functional magnetic resonance imaging (fMRI) dataset of individuals with schizophrenia (N = 708) and controls (N = 510). Our analysis reveals widespread group level differences across multiple networks and spatiotemporal features including voxel-wise variability, magnitude, and temporal functional network connectivity in widespread regions expected to be impacted by the disorder. We compare with typical average spatial amplitude and show highly structured and neuroanatomically relevant results are missed if one does not consider the voxel-wise spatial dynamics. Importantly, our approach can summarize static, temporal dynamic, spatial dynamic, and spatiotemporal dynamics features, thus proving a powerful approach to unify and compare these various perspectives. In sum, we show the proposed approach highlights the importance of accounting for both temporal and spatial dynamism in whole brain neuroimaging data generally, shows a high-level of sensitivity to schizophrenia highlighting global but spatially unique dynamics showing group differences, and may be especially important in studies focused on the development of brain-based biomarkers.

show abstract

“…Deep Neural Networks (DNNs) are constantly growing in demand due to their vast applicability in different areas such as computer vision [37,42,43], language modeling [62], and recommendation systems [49]. In order to improve accuracy and enable emerging applications, the general trend has been towards an increase in both model size and the training dataset [24].…”

Section: Introductionmentioning

confidence: 99%

Themis

Rashidi

Won

Srinivasan

et al. 2022

Proceedings of the 49th Annual International Symposium on Computer Architecture

View full text Add to dashboard Cite

Distributed training is a solution to reduce DNN training time by splitting the task across multiple NPUs (e.g., GPU/TPU). However, distributed training adds communication overhead between the NPUs in order to synchronize the gradients and/or activation, depending on the parallelization strategy. In next-generation platforms for training at scale, NPUs will be connected through multidimensional networks with diverse, heterogeneous bandwidths. This work identifies a looming challenge of keeping all network dimensions busy and maximizing the network BW within the hybrid environment if we leverage scheduling techniques for collective communication on systems today. We propose Themis, a novel collective scheduling scheme that dynamically schedules collectives (divided into chunks) to balance the communication loads across all dimensions, further improving the network BW utilization. Our results show that on average, Themis can improve the network BW utilization of the single All-Reduce by 1.72× (2.70× max), and improve the end-to-end training iteration performance of real workloads such as ResNet-152, GNMT, DLRM, and Transformer-1T by 1.49× (2.25× max), 1.30× (1.78× max), 1.30× (1.77× max), and 1.25× (1.53× max), respectively.

show abstract

BPARC: A novel spatio-temporal (4D) data-driven brain parcellation scheme based on deep residual networks

Cited by 7 publications

References 15 publications

A deep residual model for characterization of 5D spatiotemporal network dynamics reveals widespread spatiodynamic changes in schizophrenia

A deep residual model for characterization of 5D spatiotemporal network dynamics reveals widespread spatiodynamic changes in schizophrenia

A deep residual model for characterization of 5D spatiotemporal network dynamics reveals widespread spatiodynamic changes in schizophrenia

Themis

Contact Info

Product

Resources

About