Discovering hierarchical common brain networks via multimodal deep belief network

Zhang, Shu; Dong, Qinglin; Zhang, Wei; Huang, Heng; Zhu, Dajiang; Liu, Tianming

doi:10.1016/j.media.2019.03.011

Cited by 17 publications

(9 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several alternative methods have been developed to identify personalized FNs of different individuals jointly and enforce inter-individual correspondence of FNs using spatial group sparsity regularization 10 or regularizations based on certain assumptions about statistical distribution of loadings of corresponding FNs of different individuals 16, 19 . Deep belief networks (DBNs) have also been utilized to identify FNs of multiple individuals jointly 39 . However, all these methods cannot directly make inference for new individuals and are computationally expensive.…”

Section: Discussionmentioning

confidence: 99%

Computing personalized brain functional networks from fMRI using self-supervised deep learning

Dhivya

Cui

et al. 2021

Preprint

View full text Add to dashboard Cite

A novel self-supervised deep learning (DL) method is developed for computing bias-free, personalized brain functional networks (FNs) that provide unique opportunities to better understand brain function, behavior, and disease. Specifically, convolutional neural networks with an encoder-decoder architecture are employed to compute personalized FNs from resting-state fMRI data without utilizing any external supervision by optimizing functional homogeneity of personalized FNs in a self-supervised setting. We demonstrate that a DL model trained on fMRI scans from the Human Connectome Project can identify canonical FNs and generalizes well across four different datasets. We further demonstrate that the identified personalized FNs are informative for predicting individual differences in behavior, brain development, and schizophrenia status. Taken together, self-supervised DL allows for rapid, generalizable computation of personalized FNs.

show abstract

Section: Discussionmentioning

confidence: 99%

Computing personalized brain functional networks from fMRI using self-supervised deep learning

Dhivya

Cui

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The ordinary GRU structure will be replaced by the cell structure searched for multiple different GRU connections. Darts search for GRU can be expressed as formula (10), where D∈R n×m , Z∈R n×m :…”

Section: Gru Structure Searchmentioning

confidence: 99%

“…Especially, the representation of functional brain network helps us to know the cognitive behavior of human brain well and improve our understanding of brain regions as each brain region is involved in specific cognitive behaviors or perceptual tasks. The early models of brain functional networks representation include general linear model (GLM) [1], [2], independent component analysis (ICA) [3], [4] and sparse dictionary learning (SDL) [5] Due to the superior representation power, deep-learning (DL) based models were employed for the study of spatiotemporal BFNs, such as convolutional autoencoder (DCAE), deep variational autoencoder DVAE and deep belief Network (DBN) [6]- [10]. However, it is proved that the cognitive behavior of brain regions is related to their early behaviors with a potential long distance in time [11].…”

Section: Introductionmentioning

confidence: 99%

SA-NAS-BFNR: Spatiotemporal Attention Neural Architecture Search for Task-based Brain Functional Network Representation

Duan

Cao

Gao

2022

Proceedings of the 2022 International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

The spatiotemporal representation of task-based brain functional networks is a key topic in functional magnetic resonance image (fMRI) research. At present, deep learning has been more powerful and flexible in brain functional network research than traditional methods. However, the dominant deep learning models failed in capturing the long-distance dependency (LDD) in task-based fMRI images (tfMRI) due to the time correlation among different task stimuli, the nature between temporal and spatial dimensions, which resulting in inaccurate brain pattern extraction. To address this issue, this paper proposes a spatiotemporal attention neural architecture search (NAS) model for task-based brain functional networks representation (SA-NAS-BFNR), where attention mechanism and gate recurrent unit (GRU) are integrated into a novel framework and GRU structure is searched by the differentiable neural architecture search. This model can not only achieve meaningful brain functional networks (BFNs) by addressing the LDD, but also simplify the existing recurrent structure models in tfMRI. Experiments show that the proposed model is capable of improving the fitting ability between time series and task stimulus sequence, and extracting the BFNs effectively as well. CCS CONCEPTS CCS CONCEPTS•Computing methodologies~Artificial intelligence~Knowledge representation and reasoning~Temporal reasoning

show abstract

“…After decades of active research using the fMRI technique, functional brain networks and their interactions have been well described with rest and task data (Baajour et al, 2020;Elbich, Molenaar, & Scherf, 2019;Yuan et al, 2018;Zhang et al, 2019Zhang et al, , 2020. Thus, it is more likely to achieve a better understanding of the relationship between energy consumption and functional network interactions.…”

Section: Introductionmentioning

confidence: 99%

Control energy assessment of spatial interactions among macro‐scale brain networks

Yuan

Luo

et al. 2022

Human Brain Mapping

Self Cite

View full text Add to dashboard Cite

Many recent studies have revealed that spatial interactions of functional brain networks derived from fMRI data can well model functional connectomes of the human brain. However, it has been rarely explored what the energy consumption characteristics are for such spatial interactions of macro-scale functional networks, which remains crucial for the understanding of brain organization, behavior, and dynamics. To explore this unanswered question, this article presents a novel framework for quantitative assessment of energy consumptions of macroscale functional brain network's spatial interactions via two main effective computational methodologies. First, we designed a novel scheme combining dictionary learning and hierarchical clustering to derive macro-scale consistent brain network templates that can be used to define a common reference space for brain network interactions and energy assessments. Second, the control energy consumption for driving the brain networks during their spatial interactions is computed from the viewpoint of the linear network control theory. Especially, the energetically favorable brain networks were identified and their energy characteristics were comprehensively analyzed. Experimental results on the Human Connectome Project (HCP) task-based fMRI (tfMRI) data showed that the proposed methods can reveal meaningful, diverse energy consumption patterns of macro-scale network interactions. In particular, those networks present remarkable differences in energy consumption. The energetically least favorable brain networks are stable and consistent across HCP tasks such as motor, language, social, and working memory tasks. In general, our framework provides a new perspective to characterize human brain functional connectomes by quantitative assessment for the energy consumption of spatial interactions of macro-scale brain networks.

show abstract

Discovering hierarchical common brain networks via multimodal deep belief network

Cited by 17 publications

References 64 publications

Computing personalized brain functional networks from fMRI using self-supervised deep learning

Computing personalized brain functional networks from fMRI using self-supervised deep learning

SA-NAS-BFNR: Spatiotemporal Attention Neural Architecture Search for Task-based Brain Functional Network Representation

Control energy assessment of spatial interactions among macro‐scale brain networks

Contact Info

Product

Resources

About