Qualitative and Quantitative MRI Analysis in IDH1 Genotype Prediction of Lower-Grade Gliomas: A Machine Learning Approach
Purpose. Preoperative prediction of isocitrate dehydrogenase 1 (IDH1) mutation in lower-grade gliomas (LGGs) is crucial for clinical decision-making. This study aimed to examine the predictive value of a machine learning approach using qualitative and quantitative MRI features to identify the IDH1 m...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2021-01-01
|
Series: | BioMed Research International |
Online Access: | http://dx.doi.org/10.1155/2021/1235314 |
id |
doaj-03c12a2be9074506984fb58fdbf08487 |
---|---|
record_format |
Article |
spelling |
doaj-03c12a2be9074506984fb58fdbf084872021-02-15T12:52:45ZengHindawi LimitedBioMed Research International2314-61332314-61412021-01-01202110.1155/2021/12353141235314Qualitative and Quantitative MRI Analysis in IDH1 Genotype Prediction of Lower-Grade Gliomas: A Machine Learning ApproachMengqiu Cao0Shiteng Suo1Xiao Zhang2Xiaoqing Wang3Jianrong Xu4Wei Yang5Yan Zhou6Department of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai 200127, ChinaDepartment of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai 200127, ChinaZhuhai Precision Medical Center, Zhuhai People’s Hospital (Zhuhai Hospital Affiliated with Jinan University), Zhuhai 519000, ChinaDepartment of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai 200127, ChinaDepartment of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai 200127, ChinaGuangdong Provincial Key Laboratory of Medical Image Processing, School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, ChinaDepartment of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai 200127, ChinaPurpose. Preoperative prediction of isocitrate dehydrogenase 1 (IDH1) mutation in lower-grade gliomas (LGGs) is crucial for clinical decision-making. This study aimed to examine the predictive value of a machine learning approach using qualitative and quantitative MRI features to identify the IDH1 mutation in LGGs. Materials and Methods. A total of 102 LGG patients were allocated to training (n=67) and validation (n=35) cohorts and were subject to Visually Accessible Rembrandt Images (VASARI) feature extraction (23 features) from conventional multimodal MRI and radiomics feature extraction (56 features) from apparent diffusion coefficient maps. Feature selection was conducted using the maximum Relevance Minimum Redundancy method and 0.632+ bootstrap method. A machine learning model to predict IDH1 mutation was then established using a random forest classifier. The predictive performance was evaluated using receiver operating characteristic (ROC) curves. Results. After feature selection, the top 5 VASARI features were enhancement quality, deep white matter invasion, tumor location, proportion of necrosis, and T1/FLAIR ratio, and the top 10 radiomics features included 3 histogram features, 3 gray-level run-length matrix features, and 3 gray-level size zone matrix features and one shape feature. Using the optimal VASARI or radiomics feature sets for IDH1 prediction, the trained model achieved an area under the ROC curve (AUC) of 0.779±0.001 or 0.849±0.008 on the validation cohort, respectively. The fusion model that integrated outputs of both optimal VASARI and radiomics models improved the AUC to 0.879. Conclusion. The proposed machine learning approach using VASARI and radiomics features can predict IDH1 mutation in LGGs.http://dx.doi.org/10.1155/2021/1235314 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Mengqiu Cao Shiteng Suo Xiao Zhang Xiaoqing Wang Jianrong Xu Wei Yang Yan Zhou |
spellingShingle |
Mengqiu Cao Shiteng Suo Xiao Zhang Xiaoqing Wang Jianrong Xu Wei Yang Yan Zhou Qualitative and Quantitative MRI Analysis in IDH1 Genotype Prediction of Lower-Grade Gliomas: A Machine Learning Approach BioMed Research International |
author_facet |
Mengqiu Cao Shiteng Suo Xiao Zhang Xiaoqing Wang Jianrong Xu Wei Yang Yan Zhou |
author_sort |
Mengqiu Cao |
title |
Qualitative and Quantitative MRI Analysis in IDH1 Genotype Prediction of Lower-Grade Gliomas: A Machine Learning Approach |
title_short |
Qualitative and Quantitative MRI Analysis in IDH1 Genotype Prediction of Lower-Grade Gliomas: A Machine Learning Approach |
title_full |
Qualitative and Quantitative MRI Analysis in IDH1 Genotype Prediction of Lower-Grade Gliomas: A Machine Learning Approach |
title_fullStr |
Qualitative and Quantitative MRI Analysis in IDH1 Genotype Prediction of Lower-Grade Gliomas: A Machine Learning Approach |
title_full_unstemmed |
Qualitative and Quantitative MRI Analysis in IDH1 Genotype Prediction of Lower-Grade Gliomas: A Machine Learning Approach |
title_sort |
qualitative and quantitative mri analysis in idh1 genotype prediction of lower-grade gliomas: a machine learning approach |
publisher |
Hindawi Limited |
series |
BioMed Research International |
issn |
2314-6133 2314-6141 |
publishDate |
2021-01-01 |
description |
Purpose. Preoperative prediction of isocitrate dehydrogenase 1 (IDH1) mutation in lower-grade gliomas (LGGs) is crucial for clinical decision-making. This study aimed to examine the predictive value of a machine learning approach using qualitative and quantitative MRI features to identify the IDH1 mutation in LGGs. Materials and Methods. A total of 102 LGG patients were allocated to training (n=67) and validation (n=35) cohorts and were subject to Visually Accessible Rembrandt Images (VASARI) feature extraction (23 features) from conventional multimodal MRI and radiomics feature extraction (56 features) from apparent diffusion coefficient maps. Feature selection was conducted using the maximum Relevance Minimum Redundancy method and 0.632+ bootstrap method. A machine learning model to predict IDH1 mutation was then established using a random forest classifier. The predictive performance was evaluated using receiver operating characteristic (ROC) curves. Results. After feature selection, the top 5 VASARI features were enhancement quality, deep white matter invasion, tumor location, proportion of necrosis, and T1/FLAIR ratio, and the top 10 radiomics features included 3 histogram features, 3 gray-level run-length matrix features, and 3 gray-level size zone matrix features and one shape feature. Using the optimal VASARI or radiomics feature sets for IDH1 prediction, the trained model achieved an area under the ROC curve (AUC) of 0.779±0.001 or 0.849±0.008 on the validation cohort, respectively. The fusion model that integrated outputs of both optimal VASARI and radiomics models improved the AUC to 0.879. Conclusion. The proposed machine learning approach using VASARI and radiomics features can predict IDH1 mutation in LGGs. |
url |
http://dx.doi.org/10.1155/2021/1235314 |
work_keys_str_mv |
AT mengqiucao qualitativeandquantitativemrianalysisinidh1genotypepredictionoflowergradegliomasamachinelearningapproach AT shitengsuo qualitativeandquantitativemrianalysisinidh1genotypepredictionoflowergradegliomasamachinelearningapproach AT xiaozhang qualitativeandquantitativemrianalysisinidh1genotypepredictionoflowergradegliomasamachinelearningapproach AT xiaoqingwang qualitativeandquantitativemrianalysisinidh1genotypepredictionoflowergradegliomasamachinelearningapproach AT jianrongxu qualitativeandquantitativemrianalysisinidh1genotypepredictionoflowergradegliomasamachinelearningapproach AT weiyang qualitativeandquantitativemrianalysisinidh1genotypepredictionoflowergradegliomasamachinelearningapproach AT yanzhou qualitativeandquantitativemrianalysisinidh1genotypepredictionoflowergradegliomasamachinelearningapproach |
_version_ |
1714867211689000960 |