Research on Functional Brain Network Metrics for Depression Patients Automatic Identification

Abstract:

Nowadays, Brain network as a means of emerging brain disease research has been fully recognized which is applied to the neurological diseases, such as major depressive disorder (MDD). It also can detect the exception of the whole brain network topological. But there is no evidence to prove that abnormal brain network topology metrics can be an effective feature in the classification model to distinguish the healthy control and MDD. So, we hypothesize the abnormal brain network topology metrics can be used as an valid classification feature. Resting state functional brain networks were constructed for 26 healthy controls and 34 MDD patients by thresholding partial correlation matrices of 90 regions. According to the theory-based approaches, the global and local metrics were calculated. Non-parametric permutation tests were then used for group comparisons of topological metrics, which were used as classified features in support vector machine algorithm. The current study demonstrate that MDD is associated with abnormal function brain network topological metrics and statistically significance network metrics can be successfully used for feature selection in classification algorithms.

• Periodical: Applied Mechanics and Materials (Volumes 427-429)
• Pages: 1440-1446
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.427-429.1440
• Online since: September 2013
• Authors: Chen Cheng*, Wen Zhao Liu, Jun Jie Chen
• Keywords: Artificial Intelligence (AI), Brain Network, Depression, Graph Theory, Machine Learning (ML)

References

[1] Zhang JR, Wang JH, et al. Disrupted Brain Connectivity Networks in Drug-Naive, First-Episode Major Depressive Disorder. BIOL PSYCHIATRY Vol. 70 (2011), pp.334-342.

DOI: 10.1016/j.biopsych.2011.05.018

[2] Michael D. Greicius, Benjamin H. Flores, et al. Resting-State Functional Connectivity in Major Depression: Abnormally Increased Contributions from Subgenual Cingulate Cortex and Thalamus, BIOL PSYCHIATRY Vol. 62 (2007), pp.429-437.

DOI: 10.1016/j.biopsych.2006.09.020

[3] He Y, Chen ZJ, Evans. Small-world anatomical networks in the human brainrevealed by cortical thickness from MRI, Cereb Cortex Vol. 17 (2007), pp.2407-2419.

DOI: 10.1093/cercor/bhl149

[4] Costafreda, SG, Chu C, Ashburner J, Fu CH. Prognostic and diagnostic potential of the structural neuroanatomy of depression. PLoS ONE Vol. 7 (2009), pp.6353-1.

DOI: 10.1371/journal.pone.0006353

[5] Fu CHY, Mourao-Miranda J, Costafreda SG, Khanna A, Marquand AF, Williams SCR, et al. Pattern classification of sad facial processing: toward the development of neurobiological markers in depression. Biol. Psychiatry Vol. 63 (2008), pp.656-662.

DOI: 10.1016/j.biopsych.2007.08.020

[6] Gong Q, Wu Q, Scarpazza C, Lui S, Jia Z, Marquand A, et al. Prognostic prediction of therapeutic response in depression using high-field MR imaging. Neuroimage Vol. 55 (2011), pp.1497-503.

DOI: 10.1016/j.neuroimage.2010.11.079

[7] First M, Spitzer R, Gibbon M, Williams J. Structured Clinical Interview for DSM-IV Axis I Disorders. Washington. DC: American Psychiatric Press (1997).

[8] Williams JBW. A Structured Interview Guide for the Hamilton Depression Rating-Scale. Arch Gen Psychiatry Vol. 45 (1988), pp.742-747.

DOI: 10.1001/archpsyc.1988.01800320058007

[9] Tzourio-Mazoyer N, Landeau B, Papathanassiou D, Crivello F, Etard O, Delcroix N, et al. Automated anatomical labeling of activations in SPM using a macroscopic. Neuroimage Vol. 15 (2002), pp.273-289.

DOI: 10.1006/nimg.2001.0978

[10] Pereira F, Mitchell T, Botvinick M. Machine learning classifiers and fMRI: A tutorial overview. Neuroimage Vol. 45(2009), pp.199-209.

DOI: 10.1016/j.neuroimage.2008.11.007

[11] Latora V, Marchiori M. Efficient behavior of small-world networks, Phys Rev Lett, Vol. 87 (2001), p.198701.

DOI: 10.1103/physrevlett.87.198701

[12] Bannerman DM, Rawlins JNP, et al. Regional dissociations within the hippocampus memory and anxiety, Neuroscience and Biobehavioral Reviews Vol. 28 (2004), pp.273-283.

DOI: 10.1016/j.neubiorev.2004.03.004

[13] Devorah SM, Haznedar M, Hazlett EA, et al. Diffusion tensor anisotropy in the cingulate gyrus in schizophrenia, NeuroImage, Vol. 50 (2010), pp.357-365.

DOI: 10.1016/j.neuroimage.2009.12.071

[14] Holzschneider K, Wolbers T, Röder B, et al. Cardiovascular fitness modulates brain activation associated with spatial learning, " NeuroImage Vol. 59 (2012), pp.3003-3014.

DOI: 10.1016/j.neuroimage.2011.10.021

[15] Zhu XL, Wang X, Xiao J, Liao J, et al. Evidence of a Dissociation Pattern in Resting-StateDefault Mode Network Connectivity in First-Episode, Treatment-Naive Major Depression Patients, BI OL PSYCHIATRY Vol. 71 (2012), pp.611-617.

DOI: 10.1016/j.biopsych.2011.10.035

[16] Hua JP, Xiong ZX, Lowey J, Edward S, Edward RD. Optimal number of features as a function of sample size for various classification rules. Bioinformatics Vol. 21 (2005), pp.1509-1515.

DOI: 10.1093/bioinformatics/bti171

[17] Fornito A, Zalesky A, Bullmore ET. Network scaling effects in graph analytic studies of human resting-state FMRI data. Front Syst Neurosci, (2010), pp.4-22. 6.

DOI: 10.3389/fnsys.2010.00022