Using machine learning to develop a stacking ensemble learning model for the CT radiomics classification of brain metastases

Abstract The objective of this study was to explore the potential of machine-learning techniques in the automatic identification and classification of brain metastases from a radiomic perspective, aiming to improve the accuracy of tumor volume assessment for radiotherapy. By using various machine-le...

Full description

Saved in:
Bibliographic Details
Main Authors: Huai-wen Zhang, Yi-ren Wang, Bo Hu, Bo Song, Zhong-jian Wen, Lei Su, Xiao-man Chen, Xi Wang, Ping Zhou, Xiao-ming Zhong, Hao-wen Pang, You-hua Wang
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-80210-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850163094893887488
author Huai-wen Zhang
Yi-ren Wang
Bo Hu
Bo Song
Zhong-jian Wen
Lei Su
Xiao-man Chen
Xi Wang
Ping Zhou
Xiao-ming Zhong
Hao-wen Pang
You-hua Wang
author_facet Huai-wen Zhang
Yi-ren Wang
Bo Hu
Bo Song
Zhong-jian Wen
Lei Su
Xiao-man Chen
Xi Wang
Ping Zhou
Xiao-ming Zhong
Hao-wen Pang
You-hua Wang
author_sort Huai-wen Zhang
collection DOAJ
description Abstract The objective of this study was to explore the potential of machine-learning techniques in the automatic identification and classification of brain metastases from a radiomic perspective, aiming to improve the accuracy of tumor volume assessment for radiotherapy. By using various machine-learning algorithms, including random forest, support vector machine, gradient boosting machine, XGBoost, decision tree, artificial neural network, k-nearest neighbors, LightGBM, and CatBoost algorithms, a stacking ensemble model was developed to classify gross tumor volume (GTV), brainstem, and normal brain tissue based on radiomic features. Multiple evaluation metrics, including the specificity, sensitivity, negative predictive value, positive predictive value, accuracy, Matthews correlation coefficient, and the Youden index, were used to assess the model’s performance. The stacked ensemble model integrated the strengths of the nine base models and consistently outperformed individual base models in classifying GTV (area under the curve [AUC] = 0.928), brainstem (AUC = 0.932), and normal brain tissue (AUC = 0.942). Among the base models, the support vector machine model demonstrated the best performance in the three classifications (AUC = 0.922, 0.909, and 0.928). The higher performance of the stacked ensemble model highlighted the low performance of other models, including the decision tree (AUC = 0.709, 0.706, 0.804) and k-nearest neighbors (AUC = 0.721, 0.663, 0.729) models in certain contexts, such as when faced with high-dimensional feature spaces. While machine learning shows significant promise in medical image analysis, relying solely on a single model may lead to suboptimal results. By combining the strengths of various algorithms, the stacking ensemble model offers a better solution for the classification of brain metastases based on radiomic features.
format Article
id doaj-art-727ddab7dd2c46b3843d06cc3f9873a8
institution OA Journals
issn 2045-2322
language English
publishDate 2024-11-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-727ddab7dd2c46b3843d06cc3f9873a82025-08-20T02:22:21ZengNature PortfolioScientific Reports2045-23222024-11-0114111110.1038/s41598-024-80210-xUsing machine learning to develop a stacking ensemble learning model for the CT radiomics classification of brain metastasesHuai-wen Zhang0Yi-ren Wang1Bo Hu2Bo Song3Zhong-jian Wen4Lei Su5Xiao-man Chen6Xi Wang7Ping Zhou8Xiao-ming Zhong9Hao-wen Pang10You-hua Wang11Department of Radiotherapy, The Second Affiliated Hospital of Nanchang Medical College, Jiangxi Clinical Research Center for Cancer, Jiangxi Cancer HospitalSchool of Nursing, Southwest Medical UniversityKey Laboratory of Nondestructive Testing (Ministry of Education), Nanchang Hang Kong UniversityDepartment of Neurosurgery, Jingdezhen No.1 People’s HospitalSchool of Nursing, Southwest Medical UniversitySchool of Medical Information and Engineering, Southwest Medical UniversitySchool of Nursing, Southwest Medical UniversityDepartment of Radiotherapy, The Second Affiliated Hospital of Nanchang Medical College, Jiangxi Clinical Research Center for Cancer, Jiangxi Cancer HospitalDepartment of Nursing, The Affiliated Hospital of Southwest Medical UniversityDepartment of Radiotherapy, The Second Affiliated Hospital of Nanchang Medical College, Jiangxi Clinical Research Center for Cancer, Jiangxi Cancer HospitalDepartment of Oncology, The Affiliated Hospital of Southwest Medical UniversityDepartment of Oncology, Gulin County People’s HospitalAbstract The objective of this study was to explore the potential of machine-learning techniques in the automatic identification and classification of brain metastases from a radiomic perspective, aiming to improve the accuracy of tumor volume assessment for radiotherapy. By using various machine-learning algorithms, including random forest, support vector machine, gradient boosting machine, XGBoost, decision tree, artificial neural network, k-nearest neighbors, LightGBM, and CatBoost algorithms, a stacking ensemble model was developed to classify gross tumor volume (GTV), brainstem, and normal brain tissue based on radiomic features. Multiple evaluation metrics, including the specificity, sensitivity, negative predictive value, positive predictive value, accuracy, Matthews correlation coefficient, and the Youden index, were used to assess the model’s performance. The stacked ensemble model integrated the strengths of the nine base models and consistently outperformed individual base models in classifying GTV (area under the curve [AUC] = 0.928), brainstem (AUC = 0.932), and normal brain tissue (AUC = 0.942). Among the base models, the support vector machine model demonstrated the best performance in the three classifications (AUC = 0.922, 0.909, and 0.928). The higher performance of the stacked ensemble model highlighted the low performance of other models, including the decision tree (AUC = 0.709, 0.706, 0.804) and k-nearest neighbors (AUC = 0.721, 0.663, 0.729) models in certain contexts, such as when faced with high-dimensional feature spaces. While machine learning shows significant promise in medical image analysis, relying solely on a single model may lead to suboptimal results. By combining the strengths of various algorithms, the stacking ensemble model offers a better solution for the classification of brain metastases based on radiomic features.https://doi.org/10.1038/s41598-024-80210-xArtificial intelligenceMachine learningPrediction modelRadiomicsStacking ensemble learning
spellingShingle Huai-wen Zhang
Yi-ren Wang
Bo Hu
Bo Song
Zhong-jian Wen
Lei Su
Xiao-man Chen
Xi Wang
Ping Zhou
Xiao-ming Zhong
Hao-wen Pang
You-hua Wang
Using machine learning to develop a stacking ensemble learning model for the CT radiomics classification of brain metastases
Scientific Reports
Artificial intelligence
Machine learning
Prediction model
Radiomics
Stacking ensemble learning
title Using machine learning to develop a stacking ensemble learning model for the CT radiomics classification of brain metastases
title_full Using machine learning to develop a stacking ensemble learning model for the CT radiomics classification of brain metastases
title_fullStr Using machine learning to develop a stacking ensemble learning model for the CT radiomics classification of brain metastases
title_full_unstemmed Using machine learning to develop a stacking ensemble learning model for the CT radiomics classification of brain metastases
title_short Using machine learning to develop a stacking ensemble learning model for the CT radiomics classification of brain metastases
title_sort using machine learning to develop a stacking ensemble learning model for the ct radiomics classification of brain metastases
topic Artificial intelligence
Machine learning
Prediction model
Radiomics
Stacking ensemble learning
url https://doi.org/10.1038/s41598-024-80210-x
work_keys_str_mv AT huaiwenzhang usingmachinelearningtodevelopastackingensemblelearningmodelforthectradiomicsclassificationofbrainmetastases
AT yirenwang usingmachinelearningtodevelopastackingensemblelearningmodelforthectradiomicsclassificationofbrainmetastases
AT bohu usingmachinelearningtodevelopastackingensemblelearningmodelforthectradiomicsclassificationofbrainmetastases
AT bosong usingmachinelearningtodevelopastackingensemblelearningmodelforthectradiomicsclassificationofbrainmetastases
AT zhongjianwen usingmachinelearningtodevelopastackingensemblelearningmodelforthectradiomicsclassificationofbrainmetastases
AT leisu usingmachinelearningtodevelopastackingensemblelearningmodelforthectradiomicsclassificationofbrainmetastases
AT xiaomanchen usingmachinelearningtodevelopastackingensemblelearningmodelforthectradiomicsclassificationofbrainmetastases
AT xiwang usingmachinelearningtodevelopastackingensemblelearningmodelforthectradiomicsclassificationofbrainmetastases
AT pingzhou usingmachinelearningtodevelopastackingensemblelearningmodelforthectradiomicsclassificationofbrainmetastases
AT xiaomingzhong usingmachinelearningtodevelopastackingensemblelearningmodelforthectradiomicsclassificationofbrainmetastases
AT haowenpang usingmachinelearningtodevelopastackingensemblelearningmodelforthectradiomicsclassificationofbrainmetastases
AT youhuawang usingmachinelearningtodevelopastackingensemblelearningmodelforthectradiomicsclassificationofbrainmetastases