1
|
Oota SR, Yadav A, Dash A, Bapi RS, Sharma A. Attention-based fusion of multiple graphheat networks for structural to functional brain mapping. Sci Rep 2024; 14:1184. [PMID: 38216636 PMCID: PMC10786906 DOI: 10.1038/s41598-023-50408-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/17/2023] [Accepted: 12/19/2023] [Indexed: 01/14/2024] Open
Abstract
Over the last decade, there has been growing interest in learning the mapping from structural connectivity (SC) to functional connectivity (FC) of the brain. The spontaneous fluctuations of the brain activity during the resting-state as captured by functional MRI (rsfMRI) contain rich non-stationary dynamics over a relatively fixed structural connectome. Among the modeling approaches, graph diffusion-based methods with single and multiple diffusion kernels approximating static or dynamic functional connectivity have shown promise in predicting the FC given the SC. However, these methods are computationally expensive, not scalable, and fail to capture the complex dynamics underlying the whole process. Recently, deep learning methods such as GraphHeat networks and graph diffusion have been shown to handle complex relational structures while preserving global information. In this paper, we propose a novel attention-based fusion of multiple GraphHeat networks (A-GHN) for mapping SC-FC. A-GHN enables us to model multiple heat kernel diffusion over the brain graph for approximating the complex Reaction Diffusion phenomenon. We argue that the proposed deep learning method overcomes the scalability and computational inefficiency issues but can still learn the SC-FC mapping successfully. Training and testing were done using the rsfMRI data of 1058 participants from the human connectome project (HCP), and the results establish the viability of the proposed model. On HCP data, we achieve a high Pearson correlation of 0.788 (Desikan-Killiany atlas with 87 regions) and 0.773 (AAL atlas with 86 regions). Furthermore, experiments demonstrate that A-GHN outperforms the existing methods in learning the complex nature of the structure-function relation of the human brain.
Collapse
Affiliation(s)
- Subba Reddy Oota
- Computer Science, Inria Bordeaux, Bordeaux, France.
- Cognitive Science Lab (CSL), International Institute of Information Technology (IIIT), Hyderabad, India.
| | - Archi Yadav
- Cognitive Science Lab (CSL), International Institute of Information Technology (IIIT), Hyderabad, India
| | - Arpita Dash
- Cognitive Science Lab (CSL), International Institute of Information Technology (IIIT), Hyderabad, India
| | - Raju S Bapi
- Cognitive Science Lab (CSL), International Institute of Information Technology (IIIT), Hyderabad, India
| | - Avinash Sharma
- Cognitive Science Lab (CSL), International Institute of Information Technology (IIIT), Hyderabad, India
- CVIT Lab, International Institute of Information Technology (IIIT), Hyderabad, India
| |
Collapse
|
2
|
Complexity Evaluation of an Environmental Control and Life-Support System Based on Directed and Undirected Structural Entropy Methods. ENTROPY 2021; 23:e23091173. [PMID: 34573798 PMCID: PMC8465968 DOI: 10.3390/e23091173] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/22/2021] [Revised: 09/01/2021] [Accepted: 09/03/2021] [Indexed: 11/25/2022]
Abstract
During manned space missions, an environmental control and life-support system (ECLSS) is employed to meet the life-supporting requirements of astronauts. The ECLSS is a type of hierarchical system, with subsystem—component—single machines, forming a complex structure. Therefore, system-level conceptual designing and performance evaluation of the ECLSS must be conducted. This study reports the top-level scheme of ECLSS, including the subsystems of atmosphere revitalization, water management, and waste management. We propose two schemes based on the design criteria of improving closure and reducing power consumption. In this study, we use the structural entropy method (SEM) to calculate the system order degree to quantitatively evaluate the ECLSS complexity at the top level. The complexity of the system evaluated by directed SEM and undirected SEM presents different rules. The results show that the change in the system structure caused by the replacement of some single technologies will not have great impact on the overall system complexity. The top-level scheme design and complexity evaluation presented in this study may provide technical support for the development of ECLSS in future manned spaceflights.
Collapse
|
3
|
Harmah DJ, Li C, Li F, Liao Y, Wang J, Ayedh WMA, Bore JC, Yao D, Dong W, Xu P. Measuring the Non-linear Directed Information Flow in Schizophrenia by Multivariate Transfer Entropy. Front Comput Neurosci 2020; 13:85. [PMID: 31998105 PMCID: PMC6966771 DOI: 10.3389/fncom.2019.00085] [Citation(s) in RCA: 19] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/15/2019] [Accepted: 12/04/2019] [Indexed: 12/31/2022] Open
Abstract
People living with schizophrenia (SCZ) experience severe brain network deterioration. The brain is constantly fizzling with non-linear causal activities measured by electroencephalogram (EEG) and despite the variety of effective connectivity methods, only few approaches can quantify the direct non-linear causal interactions. To circumvent this problem, we are motivated to quantitatively measure the effective connectivity by multivariate transfer entropy (MTE) which has been demonstrated to be able to capture both linear and non-linear causal relationships effectively. In this work, we propose to construct the EEG effective network by MTE and further compare its performance with the Granger causal analysis (GCA) and Bivariate transfer entropy (BVTE). The simulation results quantitatively show that MTE outperformed GCA and BVTE under varied signal-to-noise conditions, edges recovered, sensitivity, and specificity. Moreover, its applications to the P300 task EEG of healthy controls (HC) and SCZ patients further clearly show the deteriorated network interactions of SCZ, compared to that of the HC. The MTE provides a novel tool to potentially deepen our knowledge of the brain network deterioration of the SCZ.
Collapse
Affiliation(s)
- Dennis Joe Harmah
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, China
- School of Life Science and Technology, Center for Information in Medicine, University of Electronic Science and Technology of China, Chengdu, China
| | - Cunbo Li
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, China
- School of Life Science and Technology, Center for Information in Medicine, University of Electronic Science and Technology of China, Chengdu, China
| | - Fali Li
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, China
- School of Life Science and Technology, Center for Information in Medicine, University of Electronic Science and Technology of China, Chengdu, China
| | - Yuanyuan Liao
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, China
- School of Life Science and Technology, Center for Information in Medicine, University of Electronic Science and Technology of China, Chengdu, China
| | - Jiuju Wang
- Institute of Mental Health, Peking University Sixth Hospital, National Clinical Research Center for Mental Disorders & Key Laboratory of Mental Health, Ministry of Health, Peking University, Beijing, China
| | - Walid M. A. Ayedh
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, China
- School of Life Science and Technology, Center for Information in Medicine, University of Electronic Science and Technology of China, Chengdu, China
| | - Joyce Chelangat Bore
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, China
- School of Life Science and Technology, Center for Information in Medicine, University of Electronic Science and Technology of China, Chengdu, China
| | - Dezhong Yao
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, China
- School of Life Science and Technology, Center for Information in Medicine, University of Electronic Science and Technology of China, Chengdu, China
| | - Wentian Dong
- Institute of Mental Health, Peking University Sixth Hospital, National Clinical Research Center for Mental Disorders & Key Laboratory of Mental Health, Ministry of Health, Peking University, Beijing, China
| | - Peng Xu
- The Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for Neuroinformation, University of Electronic Science and Technology of China, Chengdu, China
- School of Life Science and Technology, Center for Information in Medicine, University of Electronic Science and Technology of China, Chengdu, China
| |
Collapse
|