A Distance-Based Neurorehabilitation Evaluation Method Using Linear SVM and Resting-State fMRI

Release time:2021-12-25  Hits:

• Impact Factor:4.003
• Impact Factor:4.003
• DOI number:10.3389/fneur.2019.01105
• DOI number:10.3389/fneur.2019.01105
• Journal:Frontiers in Neurology
• Journal:Frontiers in Neurology
• Place of Publication:Switzerland
• Place of Publication:Switzerland
• Key Words:functional connectivity; neurorehabilitation; resting-state fMRI; spinal cord injury; support vector machine.
• Key Words:functional connectivity; neurorehabilitation; resting-state fMRI; spinal cord injury; support vector machine.
• Abstract:During neurorehabilitation, clinical measurements are widely adopted to evaluate behavioral improvements after treatment. However, it is not able to identify or monitor the change of central nervous system (CNS) of each individual patient. Resting-state functional magnetic resonance imaging (rs-fMRI) has been widely used to investigate brain functions in healthy controls (HCs) and patients with neurological diseases, which could find functional changes following neurorehabilitation. In this paper, a distance-based rehabilitation evaluation method based on rs-fMRI was proposed. Specifically, we posit that in the functional connectivity (FC) space, patients and HCs distribute separately. Linear support vector machines (SVM) were trained on the brain networks to firstly separate patients from HCs. Second, the FC similarity between patients and HCs was measured by the L2 distance of each subject's feature vector to the separating hyperplane. Finally, statistical analysis of the distance revealed rehabilitation program induced improvements in patients and predicted rehabilitation outcomes. An rs-fMRI dataset with 22 HCs and 18 spinal cord injury (SCI) patients was utilized to validate our method. We built whole-brain networks using five atlases to test the robustness of the method and search for features under different node resolutions. The classifier successfully separated patients and HCs. Significant improvements in FC after treatment were found for the patients for all five atlases using the proposed method, which was consistent with clinical measurements. Furthermore, distance obtained from individual patient's longitudinal data showed a similar trend with each one's clinical scores, implying the possibility of individual rehabilitation outcome tracking and prediction. Our method not only provides a novel perspective of applying rs-fMRI to neurorehabilitation monitoring but also proves the potential in individualized rehabilitation prediction.
• Abstract:During neurorehabilitation, clinical measurements are widely adopted to evaluate behavioral improvements after treatment. However, it is not able to identify or monitor the change of central nervous system (CNS) of each individual patient. Resting-state functional magnetic resonance imaging (rs-fMRI) has been widely used to investigate brain functions in healthy controls (HCs) and patients with neurological diseases, which could find functional changes following neurorehabilitation. In this paper, a distance-based rehabilitation evaluation method based on rs-fMRI was proposed. Specifically, we posit that in the functional connectivity (FC) space, patients and HCs distribute separately. Linear support vector machines (SVM) were trained on the brain networks to firstly separate patients from HCs. Second, the FC similarity between patients and HCs was measured by the L2 distance of each subject's feature vector to the separating hyperplane. Finally, statistical analysis of the distance revealed rehabilitation program induced improvements in patients and predicted rehabilitation outcomes. An rs-fMRI dataset with 22 HCs and 18 spinal cord injury (SCI) patients was utilized to validate our method. We built whole-brain networks using five atlases to test the robustness of the method and search for features under different node resolutions. The classifier successfully separated patients and HCs. Significant improvements in FC after treatment were found for the patients for all five atlases using the proposed method, which was consistent with clinical measurements. Furthermore, distance obtained from individual patient's longitudinal data showed a similar trend with each one's clinical scores, implying the possibility of individual rehabilitation outcome tracking and prediction. Our method not only provides a novel perspective of applying rs-fMRI to neurorehabilitation monitoring but also proves the potential in individualized rehabilitation prediction.
• Co-author:Yu Pan, Qiong Wu, Jian Xie,Xu Cai, Huan Li, Chun Zeng, Jianfeng Wang, Zhixian Gao, Mingyu Zhang, Weibei Dou, Ning Zhang
• Co-author:Yu Pan, Qiong Wu, Jian Xie,Xu Cai, Huan Li, Chun Zeng, Jianfeng Wang, Zhixian Gao, Mingyu Zhang, Weibei Dou, Ning Zhang
• First Author:YunXiang Ge,Zonggang Hou
• First Author:YunXiang Ge,Zonggang Hou
• Indexed by:Journal paper
• Indexed by:Journal paper
• Correspondence Author:Yu Pan, Weibei Dou,Jian Xie
• Correspondence Author:Yu Pan, Weibei Dou,Jian Xie
• Volume:10
• Volume:10
• Issue:1105
• Issue:1105
• Page Number:1-13
• Page Number:1-13
• ISSN No.:1664-2295
• ISSN No.:1664-2295
• Translation or Not:no
• Translation or Not:no
• Date of Publication:2019-11-01
• Date of Publication:2019-11-01