A study on post-traumatic stress disorder classification based on multi-atlas multi-kernel graph convolutional network_Journal of Biomedical Engineering

Authors：

ZHOU Lijun ^1,2 , ZHU Hongru ^3,4 , LIU Yunfei ¹ , MO Xian ¹ , YUAN Jun ¹ , LUO Changyu ¹ ,  ZHANG Junran ¹

1. College of Electrical Engineering, Sichuan University, Chengdu 610065, P. R. China;
2. College of Electrical Engineering, Northwest Minzu University, Lanzhou 730030, P. R. China;
3. Mental Health Center, West China Hospital, Sichuan University, Chengdu 610041, P. R. China;
4. Med-X Center for Informatics, Sichuan University, Chengdu 610041, P. R. China;

Corresponding author：

ZHANG Junran, Email: zhangjunran@126.com

Keywords：

Post-traumatic stress disorder; Functional connectivity; Multi-atlas; Multi-kernel graph convolution; Classification

DOI：

10.7507/1001-5515.202407031

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Post-traumatic stress disorder (PTSD) presents with complex and diverse clinical manifestations, making accurate and objective diagnosis challenging when relying solely on clinical assessments. Therefore, there is an urgent need to develop reliable and objective auxiliary diagnostic models to provide effective diagnosis for PTSD patients. Currently, the application of graph neural networks for representing PTSD is limited by the expressiveness of existing models, which does not yield optimal classification results. To address this, we proposed a multi-graph multi-kernel graph convolutional network (MK-GCN) model for classifying PTSD data. First, we constructed functional connectivity matrices at different scales for the same subjects using different atlases, followed by employing the k-nearest neighbors algorithm to build the graphs. Second, we introduced the MK-GCN methodology to enhance the feature extraction capability of brain structures at different scales for the same subjects. Finally, we classified the extracted features from multiple scales and utilized graph class activation mapping to identify the top 10 brain regions contributing to classification. Experimental results on seismic-induced PTSD data demonstrated that our model achieved an accuracy of 84.75%, a specificity of 84.02%, and an AUC of 85% in the classification task distinguishing between PTSD patients and non-affected subjects. The findings provide robust evidence for the auxiliary diagnosis of PTSD following earthquakes and hold promise for reliably identifying specific brain regions in other PTSD diagnostic contexts, offering valuable references for clinicians.

Citation： ZHOU Lijun, ZHU Hongru, LIU Yunfei, MO Xian, YUAN Jun, LUO Changyu, ZHANG Junran. A study on post-traumatic stress disorder classification based on multi-atlas multi-kernel graph convolutional network. Journal of Biomedical Engineering, 2024, 41(6): 1110-1118. doi: 10.7507/1001-5515.202407031 Copy

1.	Koenen K C, Ratanatharathorn A, Ng L, et al. Posttraumatic stress disorder in the world mental health surveys. Psychol Med, 2017, 47(13): 2260-2274.
2.	Pathak G A, Singh K, Wendt F R, et al. Genetically regulated multi-omics study for symptom clusters of posttraumatic stress disorder highlights pleiotropy with hematologic and cardiometabolic traits. Mol Psychiatry, 2022, 27(3): 1394-1404.
3.	Pathak G A, Singh K, Choi K W, et al. Genetic liability to posttraumatic stress disorder symptoms and its association with cardiometabolic and respiratory outcomes. JAMA Psychiat, 2024, 81(1): 34-44.
4.	Shalev A, Liberzon I, Marmar C. Post-traumatic stress disorder. N Engl J Med, 2017, 376(25): 2459-2469.
5.	Ben-Zion Z, Zeevi Y, Keynan N J, et al. Multi-domain potential biomarkers for post-traumatic stress disorder (PTSD) severity in recent trauma survivors. Transl Psychiat, 2020, 10(1): 208,1-11.
6.	Sheynin S, Wolf L, Ben-Zion Z, et al. Deep learning model of fMRI connectivity predicts PTSD symptom trajectories in recent trauma survivors. Neuroimage, 2021, 238: 118242.
7.	Buckner R L, Krienen F M, Yeo B T T. Opportunities and limitations of intrinsic functional connectivity MRI. Nat Neurosci, 2013, 16(7): 832-837.
8.	Li Y, Liu J, Tang Z, et al. Deep spatial-temporal feature fusion from adaptive dynamic functional connectivity for MCI identification. IEEE Trans Med Imaging, 2020, 39(9): 2818-2830.
9.	Li Y, Zhang Y, Cui W, et al. Dual encoder-based dynamic-channel graph convolutional network with edge enhancement for retinal vessel segmentation. IEEE Trans Med Imaging, 2022, 41(8): 1975-1989.
10.	Wang W, Xiao L, Qu G, et al. Multiview hyperedge-aware hypergraph embedding learning for multisite, multiatlas fMRI based functional connectivity network analysis. Med Image Anal, 2024, 94: 103144.
11.	Campbell J M, Huang Z, Zhang J, et al. Pharmacologically informed machine learning approach for identifying pathological states of unconsciousness via resting-state fMRI. Neuroimage, 2020, 206: 116316.
12.	Chang M, Womer F Y, Gong X, et al. Identifying and validating subtypes within major psychiatric disorders based on frontal–posterior functional imbalance via deep learning. Mol Psychiat, 2021, 26(7): 2991-3002.
13.	Zheng J C, Wei X L, Wang J Y, et al. Diagnosis of schizophrenia based on deep learning using fMRI. Comput Math Methods Med, 2021, 2021: 8437260.
14.	Kong Y, Wang W, Liu X, et al. Multi-connectivity representation learning network for major depressive disorder diagnosis. IEEE Trans Med Imaging, 2023, 42(10): 3012-3024.
15.	Shao L, Fu C, You Y, et al. Classification of ASD based on fMRI data with deep learning. Cogn Neurodyn, 2021, 15(6): 961-974.
16.	An N, Ding H, Yang J, et al. Deep ensemble learning for Alzheimer’s disease classification. J Biomed Inf, 2020, 105: 103411.
17.	Zhu Z, Lei D, Qin K, et al. Combining deep learning and graph-theoretic brain features to detect posttraumatic stress disorder at the individual level. Diagnostics, 2021, 11(8): 1416.
18.	Zhu X, Kim Y, Ravid O, et al. Neuroimaging-based classification of PTSD using data-driven computational approaches: A multisite big data study from the ENIGMA-PGC PTSD consortium. Neuroimage, 2023, 283: 120412.
19.	Wu Z, Pan S, Chen F, et al. A comprehensive survey on graph neural networks. IEEE Trans Neural Netw Learn Syst, 2020, 32(1): 4-24.
20.	Gallo S, El-Gazzar A, Zhutovsky P, et al. Functional connectivity signatures of major depressive disorder: machine learning analysis of two multicenter neuroimaging studies. Mol Psychiat, 2023, 28(7): 3013-3022.
21.	Ji J, Zhang Y. Functional brain network classification based on deep graph hashing learning. IEEE Trans Med Imaging, 2022, 41(10): 2891-2902.
22.	Lei B, Zhu Y, Yu S, et al. Multi-scale enhanced graph convolutional network for mild cognitive impairment detection. Pattern Recogn, 2023, 134: 109106.
23.	Duan J, Li Y, Zhang X, et al. Predicting treatment response in adolescents and young adults with major depressive episodes from fMRI using graph isomorphism network. Neuroimage Clin, 2023, 40: 103534.
24.	Chu Y, Wang G, Cao L, et al. Multi-scale graph representation learning for autism identification with functional MRI. Front Neuroinform, 2022, 15: 802305.
25.	Ma Y, Cui W, Liu J, et al. A multi-graph cross-attention based region-aware feature fusion network using multi-template for brain disorder diagnosis. IEEE Trans Med Imaging, 2023, 43(3): 1045-1059.
26.	Lee D J, Shin D H, Son Y H, et al. Spectral graph neural network-based multi-atlas brain network fusion for major depressive disorder diagnosis. IEEE J Biomed Health Inform, 2024, 28(5): 2967-2978.
27.	Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks// 5th International Conference on Learning Representations, ICLR 2017. Toulon: ICLR: 1-14.
28.	Kazi A, Shekarforoush S, Arvind Krishna S, et al. InceptionGCN: receptive field aware graph convolutional network for disease prediction// IPMI 2019. Hong Kong: Springer, 2019: 73-85.
29.	Lee J, Lee I, Kang J. Self-attention graph pooling// PMLR 2019. California: IMLS, 2019: 3734-3743.
30.	Arslan S, Ktena S I, Glocker B, et al. Graph saliency maps through spectral convolutional networks: Application to sex classification with brain connectivity// GRAIL 2018. Granada: Springer, 2018: 3-13.
31.	Xia M, Wang J, He Y. BrainNet viewer: A network visualization tool for human brain connectomics. PLoS ONE, 2013, 8(7): 1-15.
32.	Zhu H, Yuan M, Qiu C, et al. Multivariate classification of earthquake survivors with post‐traumatic stress disorder based on large‐scale brain networks. Acta Psychiat Scand, 2020, 141(3): 285-298.
33.	Zhang Q, Wu Q, Zhu H, et al. Multimodal MRI-based classification of trauma survivors with and without post-traumatic stress disorder. Front Neurosci, 2016, 10: 292.
34.	Geuze E, Vermetten E, Ruf M, et al. Neural correlates of associative learning and memory in veterans with posttraumatic stress disorder. J Psychiat Res, 2008, 42(8): 659-669.
35.	Meng L, Jiang J, Jin C, et al. Trauma-specific grey matter alterations in PTSD. Sci Rep, 2016, 6(1): 33748.
36.	Herringa R, Phillips M, Almeida J, et al. Post-traumatic stress symptoms correlate with smaller subgenual cingulate, caudate, and insula volumes in unmedicated combat veterans. Psychiat Res, 2012, 203: 139-145.

1. Koenen K C, Ratanatharathorn A, Ng L, et al. Posttraumatic stress disorder in the world mental health surveys. Psychol Med, 2017, 47(13): 2260-2274.
2. Pathak G A, Singh K, Wendt F R, et al. Genetically regulated multi-omics study for symptom clusters of posttraumatic stress disorder highlights pleiotropy with hematologic and cardiometabolic traits. Mol Psychiatry, 2022, 27(3): 1394-1404.
3. Pathak G A, Singh K, Choi K W, et al. Genetic liability to posttraumatic stress disorder symptoms and its association with cardiometabolic and respiratory outcomes. JAMA Psychiat, 2024, 81(1): 34-44.
4. Shalev A, Liberzon I, Marmar C. Post-traumatic stress disorder. N Engl J Med, 2017, 376(25): 2459-2469.
5. Ben-Zion Z, Zeevi Y, Keynan N J, et al. Multi-domain potential biomarkers for post-traumatic stress disorder (PTSD) severity in recent trauma survivors. Transl Psychiat, 2020, 10(1): 208,1-11.
6. Sheynin S, Wolf L, Ben-Zion Z, et al. Deep learning model of fMRI connectivity predicts PTSD symptom trajectories in recent trauma survivors. Neuroimage, 2021, 238: 118242.
7. Buckner R L, Krienen F M, Yeo B T T. Opportunities and limitations of intrinsic functional connectivity MRI. Nat Neurosci, 2013, 16(7): 832-837.
8. Li Y, Liu J, Tang Z, et al. Deep spatial-temporal feature fusion from adaptive dynamic functional connectivity for MCI identification. IEEE Trans Med Imaging, 2020, 39(9): 2818-2830.
9. Li Y, Zhang Y, Cui W, et al. Dual encoder-based dynamic-channel graph convolutional network with edge enhancement for retinal vessel segmentation. IEEE Trans Med Imaging, 2022, 41(8): 1975-1989.
10. Wang W, Xiao L, Qu G, et al. Multiview hyperedge-aware hypergraph embedding learning for multisite, multiatlas fMRI based functional connectivity network analysis. Med Image Anal, 2024, 94: 103144.
11. Campbell J M, Huang Z, Zhang J, et al. Pharmacologically informed machine learning approach for identifying pathological states of unconsciousness via resting-state fMRI. Neuroimage, 2020, 206: 116316.
12. Chang M, Womer F Y, Gong X, et al. Identifying and validating subtypes within major psychiatric disorders based on frontal–posterior functional imbalance via deep learning. Mol Psychiat, 2021, 26(7): 2991-3002.
13. Zheng J C, Wei X L, Wang J Y, et al. Diagnosis of schizophrenia based on deep learning using fMRI. Comput Math Methods Med, 2021, 2021: 8437260.
14. Kong Y, Wang W, Liu X, et al. Multi-connectivity representation learning network for major depressive disorder diagnosis. IEEE Trans Med Imaging, 2023, 42(10): 3012-3024.
15. Shao L, Fu C, You Y, et al. Classification of ASD based on fMRI data with deep learning. Cogn Neurodyn, 2021, 15(6): 961-974.
16. An N, Ding H, Yang J, et al. Deep ensemble learning for Alzheimer’s disease classification. J Biomed Inf, 2020, 105: 103411.
17. Zhu Z, Lei D, Qin K, et al. Combining deep learning and graph-theoretic brain features to detect posttraumatic stress disorder at the individual level. Diagnostics, 2021, 11(8): 1416.
18. Zhu X, Kim Y, Ravid O, et al. Neuroimaging-based classification of PTSD using data-driven computational approaches: A multisite big data study from the ENIGMA-PGC PTSD consortium. Neuroimage, 2023, 283: 120412.
19. Wu Z, Pan S, Chen F, et al. A comprehensive survey on graph neural networks. IEEE Trans Neural Netw Learn Syst, 2020, 32(1): 4-24.
20. Gallo S, El-Gazzar A, Zhutovsky P, et al. Functional connectivity signatures of major depressive disorder: machine learning analysis of two multicenter neuroimaging studies. Mol Psychiat, 2023, 28(7): 3013-3022.
21. Ji J, Zhang Y. Functional brain network classification based on deep graph hashing learning. IEEE Trans Med Imaging, 2022, 41(10): 2891-2902.
22. Lei B, Zhu Y, Yu S, et al. Multi-scale enhanced graph convolutional network for mild cognitive impairment detection. Pattern Recogn, 2023, 134: 109106.
23. Duan J, Li Y, Zhang X, et al. Predicting treatment response in adolescents and young adults with major depressive episodes from fMRI using graph isomorphism network. Neuroimage Clin, 2023, 40: 103534.
24. Chu Y, Wang G, Cao L, et al. Multi-scale graph representation learning for autism identification with functional MRI. Front Neuroinform, 2022, 15: 802305.
25. Ma Y, Cui W, Liu J, et al. A multi-graph cross-attention based region-aware feature fusion network using multi-template for brain disorder diagnosis. IEEE Trans Med Imaging, 2023, 43(3): 1045-1059.
26. Lee D J, Shin D H, Son Y H, et al. Spectral graph neural network-based multi-atlas brain network fusion for major depressive disorder diagnosis. IEEE J Biomed Health Inform, 2024, 28(5): 2967-2978.
27. Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks// 5th International Conference on Learning Representations, ICLR 2017. Toulon: ICLR: 1-14.
28. Kazi A, Shekarforoush S, Arvind Krishna S, et al. InceptionGCN: receptive field aware graph convolutional network for disease prediction// IPMI 2019. Hong Kong: Springer, 2019: 73-85.
29. Lee J, Lee I, Kang J. Self-attention graph pooling// PMLR 2019. California: IMLS, 2019: 3734-3743.
30. Arslan S, Ktena S I, Glocker B, et al. Graph saliency maps through spectral convolutional networks: Application to sex classification with brain connectivity// GRAIL 2018. Granada: Springer, 2018: 3-13.
31. Xia M, Wang J, He Y. BrainNet viewer: A network visualization tool for human brain connectomics. PLoS ONE, 2013, 8(7): 1-15.
32. Zhu H, Yuan M, Qiu C, et al. Multivariate classification of earthquake survivors with post‐traumatic stress disorder based on large‐scale brain networks. Acta Psychiat Scand, 2020, 141(3): 285-298.
33. Zhang Q, Wu Q, Zhu H, et al. Multimodal MRI-based classification of trauma survivors with and without post-traumatic stress disorder. Front Neurosci, 2016, 10: 292.
34. Geuze E, Vermetten E, Ruf M, et al. Neural correlates of associative learning and memory in veterans with posttraumatic stress disorder. J Psychiat Res, 2008, 42(8): 659-669.
35. Meng L, Jiang J, Jin C, et al. Trauma-specific grey matter alterations in PTSD. Sci Rep, 2016, 6(1): 33748.
36. Herringa R, Phillips M, Almeida J, et al. Post-traumatic stress symptoms correlate with smaller subgenual cingulate, caudate, and insula volumes in unmedicated combat veterans. Psychiat Res, 2012, 203: 139-145.

Journal of Biomedical Engineering

A study on post-traumatic stress disorder classification based on multi-atlas multi-kernel graph convolutional network

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content