Cargando…

A quantitative SVM approach potentially improves the accuracy of magnetic resonance spectroscopy in the preoperative evaluation of the grades of diffuse gliomas

OBJECTIVES: To investigate the association between proton magnetic resonance spectroscopy ((1)H-MRS) metabolic features and the grade of gliomas, and to establish a machine-learning model to predict the glioma grade. METHODS: This study included 112 glioma patients who were divided into the training...

Descripción completa

Detalles Bibliográficos
Autores principales: Qi, Chong, Li, Yiming, Fan, Xing, Jiang, Yin, Wang, Rui, Yang, Song, Meng, Lanxi, Jiang, Tao, Li, Shaowu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6487359/
https://www.ncbi.nlm.nih.gov/pubmed/31035232
http://dx.doi.org/10.1016/j.nicl.2019.101835
_version_ 1783414485937029120
author Qi, Chong
Li, Yiming
Fan, Xing
Jiang, Yin
Wang, Rui
Yang, Song
Meng, Lanxi
Jiang, Tao
Li, Shaowu
author_facet Qi, Chong
Li, Yiming
Fan, Xing
Jiang, Yin
Wang, Rui
Yang, Song
Meng, Lanxi
Jiang, Tao
Li, Shaowu
author_sort Qi, Chong
collection PubMed
description OBJECTIVES: To investigate the association between proton magnetic resonance spectroscopy ((1)H-MRS) metabolic features and the grade of gliomas, and to establish a machine-learning model to predict the glioma grade. METHODS: This study included 112 glioma patients who were divided into the training (n = 74) and validation (n = 38) sets based on the time of hospitalization. Twenty-six metabolic features were extracted from the preoperative (1)H-MRS image. The Student's t-test was conducted to screen for differentially expressed features between low- and high-grade gliomas (WHO grades II and III/IV, respectively). Next, the minimum Redundancy Maximum Relevance (mRMR) algorithm was performed to further select features for a support vector machine (SVM) classifier building. Performance of the predictive model was evaluated both in the training and validation sets using ROC curve analysis. RESULTS: Among the extracted (1)H-MRS metabolic features, thirteen features were differentially expressed. Four features were further selected as grade-predictive imaging signatures using the mRMR algorithm. The predictive performance of the machine-learning model measured by the AUC was 0.825 and 0.820 in the training and validation sets, respectively. This was better than the predictive performances of individual metabolic features, the best of which was 0.812. CONCLUSIONS: (1)H-MRS metabolic features could help in predicting the grade of gliomas. The machine-learning model achieved a better prediction performance in grading gliomas than individual features, indicating that it could complement the traditionally used metabolic features.
format Online
Article
Text
id pubmed-6487359
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-64873592019-05-06 A quantitative SVM approach potentially improves the accuracy of magnetic resonance spectroscopy in the preoperative evaluation of the grades of diffuse gliomas Qi, Chong Li, Yiming Fan, Xing Jiang, Yin Wang, Rui Yang, Song Meng, Lanxi Jiang, Tao Li, Shaowu Neuroimage Clin Regular Article OBJECTIVES: To investigate the association between proton magnetic resonance spectroscopy ((1)H-MRS) metabolic features and the grade of gliomas, and to establish a machine-learning model to predict the glioma grade. METHODS: This study included 112 glioma patients who were divided into the training (n = 74) and validation (n = 38) sets based on the time of hospitalization. Twenty-six metabolic features were extracted from the preoperative (1)H-MRS image. The Student's t-test was conducted to screen for differentially expressed features between low- and high-grade gliomas (WHO grades II and III/IV, respectively). Next, the minimum Redundancy Maximum Relevance (mRMR) algorithm was performed to further select features for a support vector machine (SVM) classifier building. Performance of the predictive model was evaluated both in the training and validation sets using ROC curve analysis. RESULTS: Among the extracted (1)H-MRS metabolic features, thirteen features were differentially expressed. Four features were further selected as grade-predictive imaging signatures using the mRMR algorithm. The predictive performance of the machine-learning model measured by the AUC was 0.825 and 0.820 in the training and validation sets, respectively. This was better than the predictive performances of individual metabolic features, the best of which was 0.812. CONCLUSIONS: (1)H-MRS metabolic features could help in predicting the grade of gliomas. The machine-learning model achieved a better prediction performance in grading gliomas than individual features, indicating that it could complement the traditionally used metabolic features. Elsevier 2019-04-22 /pmc/articles/PMC6487359/ /pubmed/31035232 http://dx.doi.org/10.1016/j.nicl.2019.101835 Text en © 2019 The Authors http://creativecommons.org/licenses/by-nc-nd/4.0/ This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Regular Article
Qi, Chong
Li, Yiming
Fan, Xing
Jiang, Yin
Wang, Rui
Yang, Song
Meng, Lanxi
Jiang, Tao
Li, Shaowu
A quantitative SVM approach potentially improves the accuracy of magnetic resonance spectroscopy in the preoperative evaluation of the grades of diffuse gliomas
title A quantitative SVM approach potentially improves the accuracy of magnetic resonance spectroscopy in the preoperative evaluation of the grades of diffuse gliomas
title_full A quantitative SVM approach potentially improves the accuracy of magnetic resonance spectroscopy in the preoperative evaluation of the grades of diffuse gliomas
title_fullStr A quantitative SVM approach potentially improves the accuracy of magnetic resonance spectroscopy in the preoperative evaluation of the grades of diffuse gliomas
title_full_unstemmed A quantitative SVM approach potentially improves the accuracy of magnetic resonance spectroscopy in the preoperative evaluation of the grades of diffuse gliomas
title_short A quantitative SVM approach potentially improves the accuracy of magnetic resonance spectroscopy in the preoperative evaluation of the grades of diffuse gliomas
title_sort quantitative svm approach potentially improves the accuracy of magnetic resonance spectroscopy in the preoperative evaluation of the grades of diffuse gliomas
topic Regular Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6487359/
https://www.ncbi.nlm.nih.gov/pubmed/31035232
http://dx.doi.org/10.1016/j.nicl.2019.101835
work_keys_str_mv AT qichong aquantitativesvmapproachpotentiallyimprovestheaccuracyofmagneticresonancespectroscopyinthepreoperativeevaluationofthegradesofdiffusegliomas
AT liyiming aquantitativesvmapproachpotentiallyimprovestheaccuracyofmagneticresonancespectroscopyinthepreoperativeevaluationofthegradesofdiffusegliomas
AT fanxing aquantitativesvmapproachpotentiallyimprovestheaccuracyofmagneticresonancespectroscopyinthepreoperativeevaluationofthegradesofdiffusegliomas
AT jiangyin aquantitativesvmapproachpotentiallyimprovestheaccuracyofmagneticresonancespectroscopyinthepreoperativeevaluationofthegradesofdiffusegliomas
AT wangrui aquantitativesvmapproachpotentiallyimprovestheaccuracyofmagneticresonancespectroscopyinthepreoperativeevaluationofthegradesofdiffusegliomas
AT yangsong aquantitativesvmapproachpotentiallyimprovestheaccuracyofmagneticresonancespectroscopyinthepreoperativeevaluationofthegradesofdiffusegliomas
AT menglanxi aquantitativesvmapproachpotentiallyimprovestheaccuracyofmagneticresonancespectroscopyinthepreoperativeevaluationofthegradesofdiffusegliomas
AT jiangtao aquantitativesvmapproachpotentiallyimprovestheaccuracyofmagneticresonancespectroscopyinthepreoperativeevaluationofthegradesofdiffusegliomas
AT lishaowu aquantitativesvmapproachpotentiallyimprovestheaccuracyofmagneticresonancespectroscopyinthepreoperativeevaluationofthegradesofdiffusegliomas
AT qichong quantitativesvmapproachpotentiallyimprovestheaccuracyofmagneticresonancespectroscopyinthepreoperativeevaluationofthegradesofdiffusegliomas
AT liyiming quantitativesvmapproachpotentiallyimprovestheaccuracyofmagneticresonancespectroscopyinthepreoperativeevaluationofthegradesofdiffusegliomas
AT fanxing quantitativesvmapproachpotentiallyimprovestheaccuracyofmagneticresonancespectroscopyinthepreoperativeevaluationofthegradesofdiffusegliomas
AT jiangyin quantitativesvmapproachpotentiallyimprovestheaccuracyofmagneticresonancespectroscopyinthepreoperativeevaluationofthegradesofdiffusegliomas
AT wangrui quantitativesvmapproachpotentiallyimprovestheaccuracyofmagneticresonancespectroscopyinthepreoperativeevaluationofthegradesofdiffusegliomas
AT yangsong quantitativesvmapproachpotentiallyimprovestheaccuracyofmagneticresonancespectroscopyinthepreoperativeevaluationofthegradesofdiffusegliomas
AT menglanxi quantitativesvmapproachpotentiallyimprovestheaccuracyofmagneticresonancespectroscopyinthepreoperativeevaluationofthegradesofdiffusegliomas
AT jiangtao quantitativesvmapproachpotentiallyimprovestheaccuracyofmagneticresonancespectroscopyinthepreoperativeevaluationofthegradesofdiffusegliomas
AT lishaowu quantitativesvmapproachpotentiallyimprovestheaccuracyofmagneticresonancespectroscopyinthepreoperativeevaluationofthegradesofdiffusegliomas