AUTHOR=Wang Yang , Zhao Rui , Zhu Dan , Fu Xiuwei , Sun Fengyu , Cai Yuezeng , Ma Juanwei , Guo Xing , Zhang Jing , Xue Yuan TITLE=Voxel- and tensor-based morphometry with machine learning techniques identifying characteristic brain impairment in patients with cervical spondylotic myelopathy JOURNAL=Frontiers in Neurology VOLUME=Volume 15 - 2024 YEAR=2024 URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2024.1267349 DOI=10.3389/fneur.2024.1267349 ISSN=1664-2295 ABSTRACT=The diagnosis of cervical spondylotic myelopathy (CSM) relies on several methods, including X-ray, computed tomography, and magnetic resonance imaging (MRI). Although MRI is the most useful diagnostic tool, strategies to improve the precise and independent diagnosis of CSM using novel MRI imaging are urgently needed. This study aimed to explore potential brain biomarkers to improve the precise diagnosis of CSM by the combination of voxel-based morphometry (VBM) and tensor-based morphometry (TBM) with machine learning.In this retrospective study, 57 patients with CSM and 57 healthy controls (HCs) were enrolled. The structural changes in gray matter volume and white matter volume were determined by VBM. Gray and white matter deformation were measured by TBM. The support vector machine (SVM) was used for the classification of CSM patients from HCs based on the structural features of VBM and TBM.Results: CSM patients had characteristic structural abnormalities in sensorimotor, visual, cognitive, and subcortical regions as well as anterior corona radiata and the corpus callosum (P < 0.05, false discovery rate (FDR) corrected). Multivariate pattern classification analysis revealed that VBM and TBM could successfully identify CSM patients and HCs (classification accuracy: 81.58%, area under the curve (AUC): 0.85; P < 0.005, Bonferroni corrected) through characteristic gray matter and white matter impairment.This study provided a valuable reference for developing novel diagnostic strategies to VBM and TBM with machine learning in CSM identify CSM.