Brain function network feature selection and classification based on multi-level template
WU Hao1, WANG Xincan2, LI Xinyun1, LIU Zhifen3, CHEN Junjie1, GUO Hao1
1. College of Information and Computer Science, Taiyuan University of Technology, Jinzhong Shanxi 030600, China;
2. College of Art, Taiyuan University of Technology, Jinzhong Shanxi 030600, China;
3. Department of Mental Health, First Hospital of Shanxi Medical University, Taiyuan Shanxi 030000, China
The feature representation extracted from the functional connection network based on single brain map template is not sufficient to reveal complex topological differences between patient group and Normal Control (NC) group. However, the traditional multi-template-based functional brain network definitions mostly use independent templates, ignoring the potential topological association information in functional brain networks built with each template. Aiming at the above problems, a multi-level brain map template and a method of Relationship Induced Sparse (RIS) feature selection model were proposed. Firstly, an associated multi-level brain map template was defined, and the potential relationship between templates and network structure differences between groups were mined. Then, the RIS feature selection model was used to optimize the parameters and extract the differences between groups. Finally, the Support Vector Machine (SVM) method was used to construct classification model and was applied to the diagnosis of patients with depression. The experimental results on the clinical diagnosis database of depression in the First Hospital of Shanxi University show that the functional brain network based on multi-level template achieves 91.7% classification accuracy by using the RIS feature selection method, which is 3 percentage points higher than that of traditional multi-template method.
[1] SACCHET M D, PRASAD G, FOLANDROSSL C, et al. Elucidating brain connectivity networks in major depressive disorder using classification-based scoring[C]//Proceedings of the 2014 IEEE International Symposium on Biomedical Imaging. Piscataway, NJ:IEEE, 2014:246-249.
[2] NIXON N L, LIDDLE P F, NIXON E, et al. Biological vulnerability to depression:linked structural and functional brain network findings[J]. British Journal of Psychiatry, 2014, 204(4):283-289.
[3] PEREIRA F, MITCHELL T, BOTVINICK M. Machine learning classifiers and fMRI:a tutorial overview[J]. Neuroimage, 2009, 45(1):S199-S209.
[4] HAHN T, MARQUAND A F, EHLIS A C, et al. Integrating neurobiological markers of depression[J]. Archives of General Psychiatry, 2011, 68(4):361-368.
[5] MULDERS P C, van EIJNDHOVEN P F, SCHENE A H, et al. Resting-state functional connectivity in major depressive disorder:A review[J]. Neuroscience and Biobehavioral Reviews, 2015, 56:330-344.
[6] ANAND A, LI Y, WANG Y, et al. Activity and connectivity of brain mood regulating circuit in depression:a functional magnetic resonance study[J]. Biological Psychiatry, 2005, 57(10):1079-1088.
[7] CRADDOCK R C, HOLTZHEIMER R P, HU X P, et al. Disease state prediction from resting state functional connectivity[J]. Magnetic Resonance in Medicine, 2010, 62(6):1619-1628.
[8] GREICIUS M D, FLORES B H, MENON V, et al. Resting-state functional connectivity in major depression:abnormally increased contributions from subgenual cingulate cortex and thalamus[J]. Biological Psychiatry, 2007, 62(5):429-437.
[9] 温洪,郭浩,李越,等.重度抑郁症患者脑功能网络的分类研究[J].计算机应用研究,2013,30(8):2304-2307.(WEN H, GUO H, LI Y, et al. Classification of brain function networks in patients with major depression[J]. Application Research of Computers, 2013, 30(8):2304-2307.)
[10] FORNITO A, ZALESKY A, BULLMORE E T. Network scaling effects in graph analytic studies of human resting-state fMRI data[J]. Frontiers in Systems Neuroscience, 2010, 4:22-25.
[11] MIN R, WU G, CHENG J, et al. Multi-atlas based representations for Alzheimer's disease diagnosis[J]. Human Brain Mapping, 2015, 35(10):5052-5070.
[12] OTA K, OISHI N, ITO K, et al. A comparison of three brain atlases for MCI prediction[J]. Journal of Neuroscience Methods, 2014, 221:139-150.
[13] JING B, LONG Z, LIU H, et al. Identifying current and remitted major depressive disorder with the Hurst exponent:a comparative study on two automated anatomical labeling atlases[J]. Oncotarget, 2017, 8(52):90452-90464.
[14] LIU M, ZHANG D, SHEN D. Relationship induced multi-tem-plate learning for diagnosis of Alzheimer's disease and mild cognitive impairment[J]. IEEE Transactions on Medical Imaging, 2016, 35(6):1463-1474.
[15] TZOURIOMAZOYER N, LANDEAU B, PAPATHANASSIOU D, et al. Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain[J]. Neuroimage, 2002, 15(1):273-289.
[16] 牛会兰.局部信息方法在功能脑网络建模中的应用研究[D].太原:太原理工大学,2016:10-13.(NIU H L. Application research of local information method in functional brain network modeling[D]. Taiyuan:Taiyuan University of Technology, 2016:10-13.)
[17] KHAZAEE A, EBRAHIMZADEH A, BABAJANI-FEREMI A. Identifying patients with Alzheimer's disease using resting-state fMRI and graph theory[J]. Clinical Neurophysiology, 2015, 126(11):2132-2141.
[18] LANGER N, PEDRONI A, JÄNCKE L. The problem of thresholding in small-world network analysis[J]. PLoS One, 2013, 8:e53199.
[19] KHAZAEE A, EBRAHIMZADEH A, BABAJANI-FEREMI A. Application of advanced machine learning methods on resting-state fMRI network for identification of mild cognitive impairment and Alzheimer's disease[J]. Brain Imaging and Behavior, 2016, 10(3):799-817.
[20] 郭浩.抑郁症静息态功能脑网络异常拓扑属性分析及分类研究[D].太原:太原理工大学,2013:5-10.(GUO H. Analysis and classification of abnormal topological attributes of resting brain function in depression[D]. Taiyuan:Taiyuan University of Technology, 2013:5-10.)
[21] ZHANG J, WANG J, WU Q, et al. Disrupted brain connectivity networks in drug-naive, first-episode major depressive disorder[J]. Biological Psychiatry, 2011, 70(4):334-342.
[22] GUO H, LIU L, CHEN J, et al. Alzheimer classification using a minimum spanning tree of high-order functional network on fMRI dataset[J]. Frontiers in Neuroscience, 2017, 11:639.
[23] GUO H, ZHANG F, CHEN J, et al. Machine learning classification combining multiple features of a hyper-network of fMRI data in Alzheimer's disease[J]. Frontiers in Neuroscience, 2017, 11:615.
[24] CAO L, GUO S, XUE Z, et al. Aberrant functional connectivity for diagnosis of major depressive disorder:a discriminant analysis[J]. Psychiatry and Clinical Neurosciences, 2014, 68(2):110-119.
[25] MEIER T B, DESPHANDE A S, VERGUN S, et al. Support vector machine classification and characterization of age-related reorganization of functional brain networks[J]. Neuroimage, 2012, 60(1):601-613.
[26] HESTERMAN J Y, CAUCCI L, KUPINSKI M A, et al. Maximum-likelihood estimation with a contracting-grid search algorithm[J]. IEEE Transactions on Nuclear Science, 2010, 57(3):1077-1084.
[27] BERGSTRA J, BENGIO Y. Random search for hyper-parameter optimization[J]. Journal of Machine Learning Research, 2012, 13(1):281-305.
[28] BECSEY J C, BERKE L, CALLAN J R. Nonlinear least squares methods:a direct grid search approach[J]. Journal of Chemical Education, 1968, 45(11):728.
[29] CHANG C C, LIN C J. LIBSVM:a library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2:1-27.
[30] YE F, LOU X Y, SUN L F. An improved chaotic fruit fly optimization based on a mutation strategy for simultaneous feature selection and parameter optimization for SVM and its applications[J]. PLoS One, 2017, 12(4):e0173516.
2019, Vol. 39 
