Application value of a machine learning method based on general linear model in the localization of individual motor function in patient with glioma after blood oxygen level dependent functional magnetic resonance imaging
Ren Yuhan, Zhang Ming, Liang Yuxia, Liu Xiang, Liu Jun, Niu Chen
Department of Radiology, the First Affiliated Hospital of Xi'an Jiaotong University, Xi'an 710061, China
Abstract:Objective The study aimed to evaluate the application value of a machine learning method based on general linear model (GLM) in the localization of individual motor function in patients with glioma after blood oxygen level dependent functional magnetic resonance imaging (BOLD-fMRI). Methods A retrospective study was conducted, and strict clinical screening was performed in the Neurosurgery Department of the First Affiliated Hospital of Xi'an Jiaotong University from November 2017 to November 2021. A total of 38 pathologically confirmed patients with glioma located in the motor area were selected and included in the validation set of the machine learning model (25 males, 13 females; aged 24-69), and 50 healthy volunteers were recruited and included in the training set (26 males, 14 females; aged 22-68). Extracting the resting-state fMRI (rs-fMRI) features from 98 subjects in the Human Connectome Project (HCP) using the independent component analysis (ICA). A machine learning model based on GLM was trained using the correlation between the rs-fMRI and task-based fMRI (tb-fMRI) features of healthy subjects. (1) GLM-predicted activation and actual activation were compared by Pearson correlation coefficient (CC) analysis; (2) the dice coefficient (DC) was used as a quantitative indicator of the prediction efficiency of the model and used in comparing the prediction efficiency of GLM and ICA methods. Results (1) GLM-prediction activation in glioma patients was highly similar to task-state function activation (CC>0.30 in 89.47% [34/38] of patients). (2) GLM was better than ICA in predicting task-state motor function activation. The DC was 0.34 (0.27, 0.42), and 0.26 (0.16, 0.30), respectively, the difference was statistically significant (Z=-3.88; P<0.001). In the tumor-containing hemisphere, GLM was better than ICA in predicting task-state activation, with DCs of 0.36 (0.17, 0.48) and 0.34 (0.04, 0.45), respectively (Z=-2.43, P=0.015). The prediction effects of the two methods in the nontumor hemisphere was significantly higher than that in the tumor hemisphere (Z=-4.33, -3.59; all P values<0.001). Conclusion GLM-based machine learning can predict tb-fMRI motor activation in patients with glioma after rs-fMRI and before surgery and is more efficient than ICA.
任雨寒, 张明, 梁宇霞, 刘翔, 刘军, 牛晨. 基于一般线性模型的机器学习方法在BOLD-fMRI脑胶质瘤患者个体化运动功能区定位中的应用价值[J]. 中华解剖与临床杂志, 2022, 27(8): 533-538.
Ren Yuhan, Zhang Ming, Liang Yuxia, Liu Xiang, Liu Jun, Niu Chen. Application value of a machine learning method based on general linear model in the localization of individual motor function in patient with glioma after blood oxygen level dependent functional magnetic resonance imaging. Chinese Journal of Anatomy and Clinics, 2022, 27(8): 533-538.
Håberg A, Kvistad KA, Unsgård G, et al.Preoperative blood oxygen level-dependent functional magnetic resonance imaging in patients with primary brain tumors: clinical application and outcome[J]. Neurosurgery, 2004,54(4):902-915. DOI: 10.1227/01.neu.0000114510.05922.f8.
[4]
Smith SM, Fox PT, Miller KL, et al.Correspondence of the brain's functional architecture during activation and rest[J]. Proc Natl Acad Sci USA, 2009,106(31):13040-13045.DOI: 10.1073/pnas.0905267106.
[5]
Tavor I, Parker Jones O, Mars RB, et al.Task-free MRI predicts individual differences in brain activity during task performance[J]. Science, 2016,352(6282):216-220. DOI: 10.1126/science.aad8127.
[6]
Oldfield RC.The assessment and analysis of handedness: the Edinburgh inventory[J]. Neuropsychologia, 1971,9(1):97-113. DOI: 10.1016/0028-3932(71)90067-4.
[7]
Jenkinson M, Beckmann CF, Behrens TE, et al.FSL[J]. Neuroimage, 2012,62(2):782-790. DOI: 10.1016/j.neuroimage.2011.09.015.
[8]
Cox RW.AFNI: software for analysis and visualization of functional magnetic resonance neuroimages[J]. Comput Biomed Res, 1996,29(3):162-173. DOI: 10.1006/cbmr.1996.0014.
[9]
Parker Jones O, Voets NL, Adcock JE, et al.Resting connectivity predicts task activation in pre-surgical populations[J]. Neuroimage Clin, 2017,13:378-385. DOI: 10.1016/j.nicl.2016.12.028.
[10]
Niu C, Cohen AD, Wen X, et al.Modeling motor task activation from resting-state fMRI using machine learning in individual subjects[J]. Brain Imaging Behav, 2021,15(1):122-132. DOI: 10.1007/s11682-019-00239-9.
[11]
Glasser MF, Sotiropoulos SN, Wilson JA, et al.The minimal preprocessing pipelines for the Human Connectome Project[J]. Neuroimage, 2013,80:105-124. DOI: 10.1016/j.neuroimage.2013.04.127.
[12]
Filippini N, MacIntosh BJ, Hough MG, et al. Distinct patterns of brain activity in young carriers of the APOE-epsilon4 allele[J]. Proc Natl Acad Sci USA, 2009,106(17):7209-7214. DOI: 10.1073/pnas.0811879106.
[13]
Cole MW, Bassett DS, Power JD, et al.Intrinsic and task-evoked network architectures of the human brain[J]. Neuron, 2014,83(1):238-251. DOI: 10.1016/j.neuron.2014.05.014.
[14]
Cole MW, Anticevic A, Repovs G, et al.Variable global dysconnectivity and individual differences in schizophrenia[J]. Biol Psychiatry, 2011,70(1):43-50. DOI: 10.1016/j.biopsych.2011.02.010.
[15]
Niu C, Wang Y, Cohen AD, et al.Machine learning may predict individual hand motor activation from resting-state fMRI in patients with brain tumors in perirolandic cortex[J]. Eur Radiol, 2021,31(7):5253-5262. DOI: 10.1007/s00330-021-07825-w.
[16]
Pak RW, Hadjiabadi DH, Senarathna J, et al.Implications of neurovascular uncoupling in functional magnetic resonance imaging (fMRI) of brain tumors[J]. J Cereb Blood Flow Metab, 2017,37(11):3475-3487. DOI: 10.1177/0271678X17707398.