Analysis of Feature Fusion Strategies of Resting-State Brain Functional Connectivity Network in Patients with Negative Temporal Lobe Epilepsy
Wang Kaiwei1,2,3, Ge Manling2,3, Wang Lina4, Cheng Hao1,2,3, Zhao Xiaohu1,2,3, Chen Shenghua2,3,*, Zhang Qirui5,*
1(School of Health Sciences and Biomedical Engineering, Hebei University of Technology, Tianjin 300130, China); 2(State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin 300130, China); 3(Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province, Hebei University of Technology, Tianjin 300130, China); 4(Sino Medical Science Technology Inc, Tianjin 300130, China); 5(Department of Medical Imaging, General Hospital of Eastern Theater of PLA, Nanjing 210002, China)
Abstract：Resting-state fMRI (rfMRI) can provide abnormal functional indicators by the functional connectivity (FC) analysis, however, the features redundancy would affect the classification precise. To address this issue, a feature fusion strategy combining specificity index model with discriminant correlation analysis (DCA) was proposed in this study to improve the identifying accuracy for patients with MRI-negative temporal lobe epilepsy. Firstly, the rfMRI data of 20 patients and 20 healthy people were preprocessed. Taking the healthy group as a control, two specificity index models were constructed by the conventional FC of pearson correlation and the network FC of graph theory. Secondly, both minimum redundancy maximum relevance (mRMR) and independent sample t test were used to eliminate redundant features, and DCA method was used to fuse feature. Finally, three machine-learning classifiers such as k-nearest neighbor (KNN), support vector machine (SVM) and logistic regression (LR) were used to validate our feature fusion method, and the nested stratification cross validations, such as 10 times 10 fold and 10 times 5 fold were used to evaluate the performance of three classifiers. The fusion feature of DCA could achieve the recognition rate of 91.25%~92.5%, higher than non-fusion strategies. In conclusion, the feature fusion strategy proposed in this paper could effectively deal with the redundant information and enhance feature discrimination. This work may provide new thoughts for the identification for MRI-negative temporal lobe epilepsy.
[1] Akyuz E, Polat AK, Eroglu E, et al.Revisiting the role of neurotransmitters in epilepsy: an updated review[J]. Life Sci, 2021, 265: 118826. [2] Fisher RS, Acevedo C, Arzimanoglou A, et al.ILAE official report: a practical clinical definition of epilepsy[J]. Epilepsia, 2014, 55(4): 475-482. [3] Begley C, Wagner RG, Abraham A, et al.The global cost of epilepsy: A systematic review and extrapolation[J]. Epilepsia, 2022, 63(4): 892-903. [4] Sisodiya SM, Whelan CD, Hatton SN, et al.The ENIGMA-Epilepsy working group: Mapping disease from large data sets[J]. Hum Brain Mapp, 2020, 43(1): 113-128. [5] Consales A, Casciato S, Asioli S, et al.The surgical treatment of epilepsy[J]. Neurol Sci, 2021, 42(6): 2249-2260. [6] Muhlhofer W, Tan YL, Mueller SG, et al.MRI-negative temporal lobe epilepsy-What do we know?[J]. Epilepsia, 2017, 58(5): 727-742. [7] Ogawa S, Lee TM, Kay AR, et al.Brain magnetic resonance imaging with contrast dependent on blood oxygenation[J]. P Natl Acad Sci USA, 1990, 87(24): 9868-9872. [8] Lv Han, Wang Zhenchang, Tong Elizabeth, et al.Resting-state functional MRI: Everything that nonexperts have always wanted to know[J]. Am J Neuroradiol, 2018, 39(8): 1390-1399. [9] Fieller EC, Hartley HO, Pearson ES.Tests for rank correlation coefficients. I[J]. Biometrika, 1957, 44(3/4): 470-481. [10] Luo Cuihua, Li Fali, Li Peiyang, et al.A survey of brain network analysis by electroencephalographic signals[J]. Cogn Neurodyn, 2022, 16(1): 17-41. [11] Fruengel R, Brohl T, Rings T, et al.Reconfiguration of human evolving large-scale epileptic brain networks prior to seizures: An evaluation with node centralities[J]. Sci Rep, 2020, 10(1): 21921. [12] Chang Weiwei, Lv Zongxia, Pang Xiaomin, et al.The local neural markers of MRI in patients with temporal lobe epilepsy presenting ictal panic: A resting resting-state postictal fMRI study[J]. Epilepsy Behav, 2022, 129: 108490. [13] Sidhu MK, Duncan JS, Sander JW.Neuroimaging in epilepsy[J]. Curr Opin Neurol, 2018, 31(4): 371-378. [14] Peng Liling, Liu Xiao, Ma Di, et al.The altered pattern of the functional connectome related to pathological biomarkers in individuals for autism spectrum disorder identification[J]. Front Neurosci, 2022, 16: 913377. [15] Mangai UG, Samanta S, Das S, et al.A survey of decision fusion and feature fusion strategies for pattern classification[J]. IETE Technical Review, 2010, 27(4): 293-307. [16] Li Yang, Liu Jingyu, Gao Xinqiang, et al.Multimodal hyper-connectivity of functional networks using functionally-weighted LASSO for MCI classification[J]. Med Image Anal, 2019, 52: 80-96. [17] Tian Yin, Zhang Huiling, Jiang Yuhao, et al.A fusion feature for enhancing the performance of classification in working memory load with single-trial detection[J]. IEEE Trans Neural Syst Rehabil Eng, 2019, 27(10): 1985-1993. [18] Sun Quanseng, Zeng Shenggen, Liu Yan, et al.A new method of feature fusion and its application in image recognition[J]. Pattern Recogn, 2005, 38(12): 2437-2448. [19] Haghighat M, Abdel-Mottaleb M, Alhalabi W.Discriminant correlation analysis: Real-time feature level fusion for multimodal biometric recognition[J]. IEEE Trans Inf Foren Sec, 2016, 11(9): 1984-1996. [20] Woolrich MW, Jbabdi S, Patenaude B, et al.Bayesian analysis of neuroimaging data in FSL[J]. Neuroimage, 2009, 45(1): S173-S186. [21] Smith SM, Jenkinson M, Woolrich MW, et al.Advances in functional and structural MR image analysis and implementation as FSL[J]. Neuroimage, 2004, 23: S208-S219. [22] Yan Chaogan, Zang Yufeng.DPARSF: a MATLAB toolbox for "Pipeline" data analysis of resting-state fMRI[J]. Front Syst Neurosci, 2010, 4(3): 13. [23] Tzourio-Mazoyer 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. [24] Wang Jinhui, Wang Xindi, Xia Mingrui, et al.GRETNA: A graph theoretical network analysis toolbox for imaging connectomics[J]. Front Hum Neurosci, 2015, 9: 386. [25] Gregorich M, Melograna F, Sunqvist M, et al.Individual-specific networks for prediction modelling - A scoping review of methods[J]. BMC Med Res Methodol, 2022, 22(1): 62. [26] 柯铭, 彭超, 李晓旭, 等.CLM模型在青少年肌阵挛癫痫患者脑网络中应用. 中国临床心理学杂志, 2019, 27(3): 443-447,519. [27] 曹迎新, 葛曼玲, 陈盛华, 等.颞叶癫痫致痫侧静息态脑功能网络拓扑的特异性研究. 中国生物医学工程学报, 2022, 41(1): 10-20. [28] Xia Mingrui, Wang Jinhui, He Yong.BrainNet Viewer: A network visualization tool for human brain connectomics[J]. PLoS ONE, 2013, 8(7): e68910. [29] Alim-Marvasti A, Perez-Garcia F, Dahele K, et al.Machine learning for localizing epileptogenic-zone in the temporal lobe: Quantifying the value of multimodal clinical-semiology and imaging concordance[J]. Front Digit Health, 2021, 3: 559103. [30] Abbasi B, Goldenholz DM.Machine learning applications in epilepsy[J]. Epilepsia, 2019, 60(10): 2037-2047. [31] Sinclair B, Cahill V, Seah J, et al.Machine learning approaches for imaging-based prognostication of the outcome of surgery for mesial temporal lobe epilepsy[J]. Epilepsia, 2022, 63(5): 1081-1092. [32] Varma S, Simon R.Bias in error estimation when using cross-validation for model selection[J]. BMC Bioinformatics, 2006, 7(1): 1-8. [33] Pedregosa F, Varoquaux G, Gramfort A, et al.Scikit-learn: Machine learning in Python[J]. J Mach Learn Res, 2011, 12: 2825-2830. [34] 杨泽坤, 葛曼玲, 付晓璇, 等.脑功能连接模型在机器学习中分类鲁棒性研究——以静息态功能磁共振定位癫痫发作侧为例. 中国生物医学工程学报, 2021, 40(5): 521-530. [35] Ives-Deliperi V, Butler JT.Mechanisms of cognitive impairment in temporal lobe epilepsy: A systematic review of resting-state functional connectivity studies[J]. Epilepsy Behav, 2021, 115: 107686. [36] Ramm M, Sundermann B, Gomes CA, et al.Probing the relevance of the hippocampus for conflict-induced memory improvement[J]. Neuroimage, 2021, 226: 117563. [37] Keller SS, Baker G, Downes JJ, et al.Quantitative MRI of the prefrontal cortex and executive function in patients with temporal lobe epilepsy[J]. Epilepsy Behav, 2009, 15(2): 186-195. [38] Qin L, Jiang WY, Zheng JO, et al.Alterations functional connectivity in temporal lobe epilepsy and their relationships with cognitive function: a longitudinal resting-state fMRI study[J]. Front Neurol, 2020, 11: 625. [39] Herlin B, Navarro V, Dupont S.The temporal pole: From anatomy to function-A literature appraisal[J]. J Chem Neuroanat, 2021, 113: 101925. [40] 辛斐, 谢超, 王丽君, 等.大尺度脑网络交互支持内外部指向认知的研究进展. 中国生物医学工程学报, 2020, 39(6): 736-746. [41] Bharath RD, Panda R, Raj J, et al.Machine learning identifies "rsfMRI epilepsy networks" in temporal lobe epilepsy[J]. Eur Radiol, 2019, 29(7): 3496-3505. [42] Li Zhigang, Dong Aimei, Zhou Jing.Research of low-rank representation and discriminant correlation analysis for Alzheimer's disease diagnosis[J]. Comput Math Methods Med, 2020, 2020:5294840. [43] Wang Zhan, Wang Lizhi, Huang Hua.Sparse additive discriminant canonical correlation analysis for multiple features fusion[J]. Neurocomputing, 2021, 463: 185-197. [44] 周如双, 赵慧琳, 林玮玥, 等.基于深浅特征融合的深度卷积残差网络的脑电情绪识别模型. 中国生物医学工程学报, 2021, 40(6): 641-652. [45] Beheshti I, Sone D, Maikusa N, et al.Accurate lateralization and classification of MRI-negative 18F-FDG-PET-positive temporal lobe epilepsy using double inversion recovery and machine-learning[J]. Comput Biol Med, 2021, 137: 104805. [46] Lai Chunren, Guo Shengwen, Cheng Lina, et al.A comparative study of feature selection methods for the discriminative analysis of temporal lobe epilepsy[J]. Front Neurol, 2017, 8: 633. [47] Gill RS, Lee HM, Caldairou B, et al.Multicenter validation of a deep learning detection algorithm for focal cortical dysplasia[J]. Neurology, 2021, 97(16): e1571-e1582. [48] Sebastiano DR, Tassi L, Duran D, et al.Identifying the epileptogenic zone by four non-invasive imaging techniques versus stereo-EEG in MRI-negative pre-surgery epilepsy patients[J]. Clin Neurophysiol, 2020, 131(8): 1815-1823. [49] Yeo BT, Krienen FM, Sepulcre J, et al.The organization of the human cerebral cortex estimated by intrinsic functional connectivity[J]. J Neurophysiol, 2011, 106(3): 1125-1165. [50] Power JD, Cohen AL, Nelson SM, et al.Functional network organization of the human brain[J]. Neuron, 2011, 72(4): 665-678. [51] Fan Lingzhong, Li Hai, Zhuo Junjie, et al.The human brainnetome atlas: a new brain atlas based on connectional architecture[J]. Cereb Cortex, 2016, 26(8): 3508-3526.
