Functional division of the dorsal striatum based on a graph neural network

Qian Zheng; Xiaojuan Ba; Yiyang Xin; Jiaofen Nan; Xiao Cui; Lin Xu; Qian Zheng; Xiaojuan Ba; Yiyang Xin; Jiaofen Nan; Xiao Cui; Lin Xu

doi:10.3934/mbe.2024109

Mathematical Biosciences and Engineering

2024, Volume 21, Issue 2: 2470-2487. doi: 10.3934/mbe.2024109

Previous Article Next Article

Research article

Functional division of the dorsal striatum based on a graph neural network

1.
College of Software Engineering, Zhengzhou University of Light Industry, Zhengzhou 450000, China
2.
College of Intelligent Medicine, Chengdu University of Traditional Chinese Medicine, Chengdu 611137, China
3.
School of Clinical Medicine, Henan University, Zhengzhou 450000, China

Academic Editor: Vladimir Mityushev

Received: 02 November 2023 Revised: 31 December 2023 Accepted: 04 January 2024 Published: 17 January 2024

The dorsal striatum, an essential nucleus in subcortical areas, has a crucial role in controlling a variety of complex cognitive behaviors; however, few studies have been conducted in recent years to explore the functional subregions of the dorsal striatum that are significantly activated when performing multiple tasks. To explore the differences and connections between the functional subregions of the dorsal striatum that are significantly activated when performing different tasks, we propose a framework for functional division of the dorsal striatum based on a graph neural network model. First, time series information for each voxel in the dorsal striatum is extracted from acquired functional magnetic resonance imaging data and used to calculate the connection strength between voxels. Then, a graph is constructed using the voxels as nodes and the connection strengths between voxels as edges. Finally, the graph data are analyzed using the graph neural network model to functionally divide the dorsal striatum. The framework was used to divide functional subregions related to the four tasks including olfactory reward, "0-back" working memory, emotional picture stimulation, and capital investment decision-making. The results were further subjected to conjunction analysis to obtain 15 functional subregions in the dorsal striatum. The 15 different functional subregions divided based on the graph neural network model indicate that there is functional differentiation in the dorsal striatum when the brain performs different cognitive tasks. The spatial localization of the functional subregions contributes to a clear understanding of the differences and connections between functional subregions.
- dorsal striatum,
- functional magnetic resonance imaging,
- graph neural network,
- functional division,
- task
Citation: Qian Zheng, Xiaojuan Ba, Yiyang Xin, Jiaofen Nan, Xiao Cui, Lin Xu. Functional division of the dorsal striatum based on a graph neural network[J]. Mathematical Biosciences and Engineering, 2024, 21(2): 2470-2487. doi: 10.3934/mbe.2024109

Related Papers:

Abstract

The dorsal striatum, an essential nucleus in subcortical areas, has a crucial role in controlling a variety of complex cognitive behaviors; however, few studies have been conducted in recent years to explore the functional subregions of the dorsal striatum that are significantly activated when performing multiple tasks. To explore the differences and connections between the functional subregions of the dorsal striatum that are significantly activated when performing different tasks, we propose a framework for functional division of the dorsal striatum based on a graph neural network model. First, time series information for each voxel in the dorsal striatum is extracted from acquired functional magnetic resonance imaging data and used to calculate the connection strength between voxels. Then, a graph is constructed using the voxels as nodes and the connection strengths between voxels as edges. Finally, the graph data are analyzed using the graph neural network model to functionally divide the dorsal striatum. The framework was used to divide functional subregions related to the four tasks including olfactory reward, "0-back" working memory, emotional picture stimulation, and capital investment decision-making. The results were further subjected to conjunction analysis to obtain 15 functional subregions in the dorsal striatum. The 15 different functional subregions divided based on the graph neural network model indicate that there is functional differentiation in the dorsal striatum when the brain performs different cognitive tasks. The spatial localization of the functional subregions contributes to a clear understanding of the differences and connections between functional subregions.

References

[1]	D. Riva, M. Taddei, S. Bulgheroni, The neuropsychology of basal ganglia, Eur. J. Paediatr. Neurol., 22 (2018), 321–326. https://doi.org/10.1016/j.ejpn.2018.01.009 doi: 10.1016/j.ejpn.2018.01.009
[2]	W. H. Kaye, C. E. Wierenga, A. Bischoff-Grethe, L. A. Berner, A. V. Ely, U. F. Bailer, et al., Neural insensitivity to the effects of hunger in women remitted from anorexia nervosa, Am. J. Psychiatr. Assoc., 177 (2020), 601–610. https://doi.org/10.1176/appi.ajp.2019.19030261 doi: 10.1176/appi.ajp.2019.19030261
[3]	M. Yousuf, M. Heldmann, M. Göttlich, T. F. Münte, N. Doñamayor, Neural processing of food and monetary rewards is modulated by metabolic state, Brain Imaging Behav., 12 (2018), 1379–1392. https://doi.org/10.1007/s11682-017-9811-y doi: 10.1007/s11682-017-9811-y
[4]	C. B. Klune, B. Jin, L. A. DeNardo, Linking mPFC circuit maturation to the developmental regulation of emotional memory and cognitive flexibility, Elife, 10 (2021), 64567. https://doi.org/10.7554/eLife.64567 doi: 10.7554/eLife.64567
[5]	A. M. Lee, L. Tai, A. Zador, L. Wilbrecht, Between the primate and 'reptilian' brain: Rodent models demonstrate the role of corticostriatal circuits in decision making, Neuroscience, 296 (2015), 66–74. https://doi.org/10.1016/j.neuroscience.2014.12.042 doi: 10.1016/j.neuroscience.2014.12.042
[6]	G. Dong, H. Dong, M. Wang, J. Zhang, W. Zhou, X. Du, et al., Dorsal and ventral striatal functional connectivity shifts play a potential role in internet gaming disorder, Commun. Biol., 4 (2021), 866. https://doi.org/10.1038/s42003-021-02395-5 doi: 10.1038/s42003-021-02395-5
[7]	A. Raj, F. Powell, Network model of pathology spread recapitulates neurodegeneration and selective vulnerability in Huntington's disease, NeuroImage, 235 (2021), 118008. https://doi.org/10.1016/j.neuroimage.2021.118008 doi: 10.1016/j.neuroimage.2021.118008
[8]	X. Liu, S. B. Eickhoff, S. Caspers, J. Wu, S. Genon, F. Hoffstaedter, et al., Functional parcellation of human and macaque striatum reveals human-specific connectivity in the dorsal caudate, NeuroImage, 235 (2021) 118006. https://doi.org/10.1016/j.neuroimage.2021.118006 doi: 10.1016/j.neuroimage.2021.118006
[9]	K. Simonyan, Recent advances in understanding the role of the basal ganglia, F1000Research, 8 (2019), 122. https://doi.org/10.12688/f1000research.16524.1 doi: 10.12688/f1000research.16524.1
[10]	D. Ahmedt-Aristizabal, M. A. Armin, S. Denman, C, Fookes, L, Petersson, Graph-based deep learning for medical diagnosis and Analysis: past, present and future, Sensors, 21 (2021), 4758. https://doi.org/10.3390/s21144758 doi: 10.3390/s21144758
[11]	C. Gong, C. Jing, X. Chen, C. M. Pun, G. Huang, A. Saha, et al., Generative AI for brain image computing and brain network computing: a review, Front. Neurosci., 17 (2023), 1203104. https://doi.org/10.3389/fnins.2023.1203104 doi: 10.3389/fnins.2023.1203104
[12]	J. Pan, B. Lei, Y. Shen, Y. Liu, Z. Feng, S. Wang, Characterization multimodal connectivity of brain network by hypergraph GAN for Alzheimer's disease analysis, preprint, arXiv: 2107.09953.
[13]	Q. Zuo, N. Zhong, Y. Pan, H. Wu, B. Lei, S. Wan, Brain structure-function fusing representation learning using adversarial decomposed-VAE for analyzing MCI, IEEE Trans. Neural Syst. Rehabil. Eng., 31 (2023), 4017–4028. https://doi.org/10.1109/TNSRE.2023.3323432 doi: 10.1109/TNSRE.2023.3323432
[14]	T. N. Kipf, M. Welling, Semi-supervised classification with graph convolutional networks, preprint, arXiv: 1609.02907.
[15]	W. L. Hamilton, R. Ying, J. Leskovec, Inductive representation learning on large graphs, preprint, arXiv: 1706.02216.
[16]	M. Gori, G. Monfardini, F. Scarselli, A new model for learning in graph domains, in 2005 IEEE International Joint Conference on Neural Networks, 2 (2005), 729–734. https://doi.org/10.1109/IJCNN.2005.1555942
[17]	A. Campbell, A. G. Zippo, L. Passamonti, N. Toschi, P. Lio, DBGSL: Dynamic brain graph structure learning, preprint, arXiv: 2209.13513.
[18]	X. Kan, H. Cui, J. Lukemire, Y. Guo, C. Yang, Fbnetgen: Task-aware GNN -based fMRI analysis via functional brain network generation, Proc. Mach. Learn. Res., (2022), 618–637.
[19]	K. Zheng, S. Yu, B. Chen, CI-GNN: A granger Causality-Inspired Graph Neural Network for interpretable brain network-based psychiatric diagnosis, preprint, arXiv: 2301.01642.
[20]	X. Li, Y. Zhou, N. Dvornek, M. Zhang, S. Gao, J. Zhuang, et al., Braingnn: Interpretable brain graph neural network for fMRI analysis, Med. Image Anal., 74 (2021), 102233. https://doi.org/10.1016/j.media.2021.102233 doi: 10.1016/j.media.2021.102233
[21]	E. R. Pool, D. M. Tord, S. Delplanque, Y. Stussi, D. Cereghetti, P. Vuilleumier, et al., Differential contributions of ventral striatum subregions to the motivational and hedonic components of the affective processing of reward, J. Neurosci., 42 (2022), 2716–2728. https://doi.org/10.1523/JNEUROSCI.1124-21.2022 doi: 10.1523/JNEUROSCI.1124-21.2022
[22]	T. D. Wager, M. L. Davidson, B. L. Hughes, M, A. Lindquist, K, N. Ochsner, Prefrontal-subcortical pathways mediating successful emotion regulation, Neuron, 59 (2008), 1037–1050. https://doi.org/10.1016/j.neuron.2008.09.006 doi: 10.1016/j.neuron.2008.09.006
[23]	G. Repovš, D. M. Barch, Working memory related brain network connectivity in individuals with schizophrenia and their siblings, Front. Hum. Neurosci., 6 (2012), 137. https://doi.org/10.3389/fnhum.2012.00137 doi: 10.3389/fnhum.2012.00137
[24]	M. Piva, K. Velnoskey, R. Jia, A. Nair, I. Levy, S. W. Chang, The dorsomedial prefrontal cortex computes task-invariant relative subjective value for self and other, Elife, 8 (2019), 44939. https://doi.org/10.7554/eLife.44939 doi: 10.7554/eLife.44939
[25]	K. Uğurbil, Ultrahigh field and ultrahigh resolution fMRI, Curr. Opin. Biomed. Eng., 18 (2021), 100288. https://doi.org/10.1016/j.cobme.2021.100288 doi: 10.1016/j.cobme.2021.100288
[26]	C. Yan, X. Wang, X. Zuo, Y. Zang, DPABI: data processing & analysis for (resting-state) brain imaging, Neuroinformatics, 14 (2016), 339–351. https://doi.org/10.1007/s12021-016-9299-4 doi: 10.1007/s12021-016-9299-4
[27]	A. C. Evans, D. L. Collins, S. R. Mills, E. D. Brown, R. L. Kelly, T. M. Peters, 3D statistical neuroanatomical models from 305 MRI volumes, in 1993 IEEE Conference Record Nuclear Science Symposium and Medical Imaging Conference, 3 (1993), 1813–1817. https://doi.org/10.1109/NSSMIC.1993.373602
[28]	A. C. Evans, A. L. Janke, D. L. Collins, S. Baillet, Brain templates and atlases, Neuroimage, 62 (2012), 911–922. https://doi.org/10.1016/j.neuroimage.2012.01.024 doi: 10.1016/j.neuroimage.2012.01.024
[29]	J. Gan, X. Zhu, R. Hu, Y. Zhu, J. Ma, Z. Peng, et al., Multi-graph fusion for functional neuroimaging biomarker detection, in Twenty-Ninth International Joint Conference on Artificial Intelligence Main track, (2020), 580–586. https://doi.org/10.24963/ijcai.2020/81
[30]	X. Yang, Y. Jin, X. Chen, H. Zhang, G. Li, D. Shen, Functional connectivity network fusion with dynamic thresholding for MCI diagnosis, in International Workshop on Machine Learning in Medical Imaging, 10019 (2016), 246–253. https://doi.org/10.1007/978-3-319-47157-0_30
[31]	C. Cangea, P. Veličković, N. Jovanović, T. Kipf, P. Liò, Towards sparse hierarchical graph classifiers, preprint, arXiv: 1811.01287.
[32]	H. Gao, S. Ji, Graph U-Nets, preprint, arXiv: 1905.05178.

Reader Comments

Your name:*

Email:*
© 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)