Cargando…

Machine Learning Based on Diffusion Kurtosis Imaging Histogram Parameters for Glioma Grading

Glioma grading plays an important role in surgical resection. We investigated the ability of different feature reduction methods in support vector machine (SVM)-based diffusion kurtosis imaging (DKI) histogram parameters to distinguish glioma grades. A total of 161 glioma patients who underwent magn...

Descripción completa

Detalles Bibliográficos
Autores principales: Jiang, Liang, Zhou, Leilei, Ai, Zhongping, Xiao, Chaoyong, Liu, Wen, Geng, Wen, Chen, Huiyou, Xiong, Zhenyu, Yin, Xindao, Chen, Yu-Chen
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9105194/
https://www.ncbi.nlm.nih.gov/pubmed/35566437
http://dx.doi.org/10.3390/jcm11092310
_version_ 1784707980767264768
author Jiang, Liang
Zhou, Leilei
Ai, Zhongping
Xiao, Chaoyong
Liu, Wen
Geng, Wen
Chen, Huiyou
Xiong, Zhenyu
Yin, Xindao
Chen, Yu-Chen
author_facet Jiang, Liang
Zhou, Leilei
Ai, Zhongping
Xiao, Chaoyong
Liu, Wen
Geng, Wen
Chen, Huiyou
Xiong, Zhenyu
Yin, Xindao
Chen, Yu-Chen
author_sort Jiang, Liang
collection PubMed
description Glioma grading plays an important role in surgical resection. We investigated the ability of different feature reduction methods in support vector machine (SVM)-based diffusion kurtosis imaging (DKI) histogram parameters to distinguish glioma grades. A total of 161 glioma patients who underwent magnetic resonance imaging (MRI) from January 2017 to January 2020 were included retrospectively. The patients were divided into low-grade (n = 61) and high-grade (n = 100) groups. Parametric DKI maps were derived, and 45 features from the DKI maps were extracted semi-automatically for analysis. Three feature selection methods [principal component analysis (PCA), recursive feature elimination (RFE) and least absolute shrinkage and selection operator (LASSO)] were used to establish the glioma grading model with an SVM classifier. To evaluate the performance of SVM models, the receiver operating characteristic (ROC) curves of SVM models for distinguishing glioma grades were compared with those of conventional statistical methods. The conventional ROC analysis showed that mean diffusivity (MD) variance, MD skewness and mean kurtosis (MK) C50 could effectively distinguish glioma grades, particularly MD variance. The highest classification distinguishing AUC was found using LASSO at 0.904 ± 0.069. In comparison, classification AUC by PCA was 0.866 ± 0.061, and 0.899 ± 0.079 by RFE. The SVM-PCA model with the lowest AUC among the SVM models was significantly better than the conventional ROC analysis (z = 1.947, p = 0.013). These findings demonstrate the superiority of DKI histogram parameters by LASSO analysis and SVM for distinguishing glioma grades.
format Online
Article
Text
id pubmed-9105194
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-91051942022-05-14 Machine Learning Based on Diffusion Kurtosis Imaging Histogram Parameters for Glioma Grading Jiang, Liang Zhou, Leilei Ai, Zhongping Xiao, Chaoyong Liu, Wen Geng, Wen Chen, Huiyou Xiong, Zhenyu Yin, Xindao Chen, Yu-Chen J Clin Med Article Glioma grading plays an important role in surgical resection. We investigated the ability of different feature reduction methods in support vector machine (SVM)-based diffusion kurtosis imaging (DKI) histogram parameters to distinguish glioma grades. A total of 161 glioma patients who underwent magnetic resonance imaging (MRI) from January 2017 to January 2020 were included retrospectively. The patients were divided into low-grade (n = 61) and high-grade (n = 100) groups. Parametric DKI maps were derived, and 45 features from the DKI maps were extracted semi-automatically for analysis. Three feature selection methods [principal component analysis (PCA), recursive feature elimination (RFE) and least absolute shrinkage and selection operator (LASSO)] were used to establish the glioma grading model with an SVM classifier. To evaluate the performance of SVM models, the receiver operating characteristic (ROC) curves of SVM models for distinguishing glioma grades were compared with those of conventional statistical methods. The conventional ROC analysis showed that mean diffusivity (MD) variance, MD skewness and mean kurtosis (MK) C50 could effectively distinguish glioma grades, particularly MD variance. The highest classification distinguishing AUC was found using LASSO at 0.904 ± 0.069. In comparison, classification AUC by PCA was 0.866 ± 0.061, and 0.899 ± 0.079 by RFE. The SVM-PCA model with the lowest AUC among the SVM models was significantly better than the conventional ROC analysis (z = 1.947, p = 0.013). These findings demonstrate the superiority of DKI histogram parameters by LASSO analysis and SVM for distinguishing glioma grades. MDPI 2022-04-21 /pmc/articles/PMC9105194/ /pubmed/35566437 http://dx.doi.org/10.3390/jcm11092310 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Jiang, Liang
Zhou, Leilei
Ai, Zhongping
Xiao, Chaoyong
Liu, Wen
Geng, Wen
Chen, Huiyou
Xiong, Zhenyu
Yin, Xindao
Chen, Yu-Chen
Machine Learning Based on Diffusion Kurtosis Imaging Histogram Parameters for Glioma Grading
title Machine Learning Based on Diffusion Kurtosis Imaging Histogram Parameters for Glioma Grading
title_full Machine Learning Based on Diffusion Kurtosis Imaging Histogram Parameters for Glioma Grading
title_fullStr Machine Learning Based on Diffusion Kurtosis Imaging Histogram Parameters for Glioma Grading
title_full_unstemmed Machine Learning Based on Diffusion Kurtosis Imaging Histogram Parameters for Glioma Grading
title_short Machine Learning Based on Diffusion Kurtosis Imaging Histogram Parameters for Glioma Grading
title_sort machine learning based on diffusion kurtosis imaging histogram parameters for glioma grading
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9105194/
https://www.ncbi.nlm.nih.gov/pubmed/35566437
http://dx.doi.org/10.3390/jcm11092310
work_keys_str_mv AT jiangliang machinelearningbasedondiffusionkurtosisimaginghistogramparametersforgliomagrading
AT zhouleilei machinelearningbasedondiffusionkurtosisimaginghistogramparametersforgliomagrading
AT aizhongping machinelearningbasedondiffusionkurtosisimaginghistogramparametersforgliomagrading
AT xiaochaoyong machinelearningbasedondiffusionkurtosisimaginghistogramparametersforgliomagrading
AT liuwen machinelearningbasedondiffusionkurtosisimaginghistogramparametersforgliomagrading
AT gengwen machinelearningbasedondiffusionkurtosisimaginghistogramparametersforgliomagrading
AT chenhuiyou machinelearningbasedondiffusionkurtosisimaginghistogramparametersforgliomagrading
AT xiongzhenyu machinelearningbasedondiffusionkurtosisimaginghistogramparametersforgliomagrading
AT yinxindao machinelearningbasedondiffusionkurtosisimaginghistogramparametersforgliomagrading
AT chenyuchen machinelearningbasedondiffusionkurtosisimaginghistogramparametersforgliomagrading