Assessing Glioblastoma Treatment Response Using Machine Learning Approach Based on Magnetic Resonance Images Radiomics: An Exploratory Study
ABSTRACT Background and Objectives Assessing treatment response in glioblastoma multiforme (GBM) tumors necessitates developing more objective and quantitative approaches. A machine learning‐based approach is presented in this exploratory study for GBM patients' treatment response assessment ba...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-01-01
|
| Series: | Health Science Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/hsr2.70323 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583145106440192 |
|---|---|
| author | Amirreza Sadeghinasab Jafar Fatahiasl Marziyeh Tahmasbi Sasan Razmjoo Mohammad Yousefipour |
| author_facet | Amirreza Sadeghinasab Jafar Fatahiasl Marziyeh Tahmasbi Sasan Razmjoo Mohammad Yousefipour |
| author_sort | Amirreza Sadeghinasab |
| collection | DOAJ |
| description | ABSTRACT Background and Objectives Assessing treatment response in glioblastoma multiforme (GBM) tumors necessitates developing more objective and quantitative approaches. A machine learning‐based approach is presented in this exploratory study for GBM patients' treatment response assessment based on radiomics extracted from magnetic resonance (MR) images. Methods MR images from 77 GBM patients were acquired at two post‐surgery stages and preprocessed. From these images, 107 radiomics were extracted from the segmented tumoral cavities. The most informative features for training machine learning (ML) classifiers were identified using the Spearman correlation analysis of features retained by the forward sequential and LASSO algorithms. Applied machine learning models included support vector machine (SVM), random forest (RF), K‐nearest neighbors (KNN), AdaBoost, categorical boosting (CatBoost), light gradient boosting machine (LightGBM), extreme gradient boosting (XGBoost), Naïve Bayes (NB) and logistic regression (LR). Ten‐fold cross‐validation was used to validate the models. Statistical analysis was conducted using SPSS version 27; p‐value < 0.05 was considered significant. Results The Naïve Bayes classifier demonstrated the highest performance among the trained models, achieving an AUC (area under the receiver operating characteristic curve) of 0.86 ± 0.13 when trained on the seven features selected by the forward sequential algorithm and an AUC of 0.84 ± 0.14 when trained using the five features chosen by the LASSO algorithm. The second‐best performance was observed with the KNN classifier, which achieved an AUC of 0.80 ± 0.17 when trained on the features selected by the forward sequential algorithm. Conclusion Findings demonstrated that MRI‐based radiomics could be used as distinctive features to train ML models for GBM patients' treatment response assessment. Trained ML classifiers based on these features serve as aiding tools to expedite the quantitative assessment of GBM patients' treatment response besides qualitative evaluations. |
| format | Article |
| id | doaj-art-2b1c94cb26bb4f088a22424127595449 |
| institution | Kabale University |
| issn | 2398-8835 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Health Science Reports |
| spelling | doaj-art-2b1c94cb26bb4f088a224241275954492025-01-29T03:42:40ZengWileyHealth Science Reports2398-88352025-01-0181n/an/a10.1002/hsr2.70323Assessing Glioblastoma Treatment Response Using Machine Learning Approach Based on Magnetic Resonance Images Radiomics: An Exploratory StudyAmirreza Sadeghinasab0Jafar Fatahiasl1Marziyeh Tahmasbi2Sasan Razmjoo3Mohammad Yousefipour4Department of Radiologic Technology, School of Allied Medical Sciences, Ahvaz Jundishapur University of Medical Sciences Ahvaz IranDepartment of Radiologic Technology, School of Allied Medical Sciences, Ahvaz Jundishapur University of Medical Sciences Ahvaz IranDepartment of Radiologic Technology, School of Allied Medical Sciences, Ahvaz Jundishapur University of Medical Sciences Ahvaz IranDepartment of Clinical Oncology and Clinical Research Development Center, Golestan Hospital Ahvaz Jundishapur University of Medical Sciences Ahvaz IranDepartment of Computer Engineering, Faculty of Engineering Shahid Chamran University of Ahvaz Ahvaz IranABSTRACT Background and Objectives Assessing treatment response in glioblastoma multiforme (GBM) tumors necessitates developing more objective and quantitative approaches. A machine learning‐based approach is presented in this exploratory study for GBM patients' treatment response assessment based on radiomics extracted from magnetic resonance (MR) images. Methods MR images from 77 GBM patients were acquired at two post‐surgery stages and preprocessed. From these images, 107 radiomics were extracted from the segmented tumoral cavities. The most informative features for training machine learning (ML) classifiers were identified using the Spearman correlation analysis of features retained by the forward sequential and LASSO algorithms. Applied machine learning models included support vector machine (SVM), random forest (RF), K‐nearest neighbors (KNN), AdaBoost, categorical boosting (CatBoost), light gradient boosting machine (LightGBM), extreme gradient boosting (XGBoost), Naïve Bayes (NB) and logistic regression (LR). Ten‐fold cross‐validation was used to validate the models. Statistical analysis was conducted using SPSS version 27; p‐value < 0.05 was considered significant. Results The Naïve Bayes classifier demonstrated the highest performance among the trained models, achieving an AUC (area under the receiver operating characteristic curve) of 0.86 ± 0.13 when trained on the seven features selected by the forward sequential algorithm and an AUC of 0.84 ± 0.14 when trained using the five features chosen by the LASSO algorithm. The second‐best performance was observed with the KNN classifier, which achieved an AUC of 0.80 ± 0.17 when trained on the features selected by the forward sequential algorithm. Conclusion Findings demonstrated that MRI‐based radiomics could be used as distinctive features to train ML models for GBM patients' treatment response assessment. Trained ML classifiers based on these features serve as aiding tools to expedite the quantitative assessment of GBM patients' treatment response besides qualitative evaluations.https://doi.org/10.1002/hsr2.70323glioblastoma multiformemachine learningmagnetic resonance imagingradiomicstreatment response |
| spellingShingle | Amirreza Sadeghinasab Jafar Fatahiasl Marziyeh Tahmasbi Sasan Razmjoo Mohammad Yousefipour Assessing Glioblastoma Treatment Response Using Machine Learning Approach Based on Magnetic Resonance Images Radiomics: An Exploratory Study Health Science Reports glioblastoma multiforme machine learning magnetic resonance imaging radiomics treatment response |
| title | Assessing Glioblastoma Treatment Response Using Machine Learning Approach Based on Magnetic Resonance Images Radiomics: An Exploratory Study |
| title_full | Assessing Glioblastoma Treatment Response Using Machine Learning Approach Based on Magnetic Resonance Images Radiomics: An Exploratory Study |
| title_fullStr | Assessing Glioblastoma Treatment Response Using Machine Learning Approach Based on Magnetic Resonance Images Radiomics: An Exploratory Study |
| title_full_unstemmed | Assessing Glioblastoma Treatment Response Using Machine Learning Approach Based on Magnetic Resonance Images Radiomics: An Exploratory Study |
| title_short | Assessing Glioblastoma Treatment Response Using Machine Learning Approach Based on Magnetic Resonance Images Radiomics: An Exploratory Study |
| title_sort | assessing glioblastoma treatment response using machine learning approach based on magnetic resonance images radiomics an exploratory study |
| topic | glioblastoma multiforme machine learning magnetic resonance imaging radiomics treatment response |
| url | https://doi.org/10.1002/hsr2.70323 |
| work_keys_str_mv | AT amirrezasadeghinasab assessingglioblastomatreatmentresponseusingmachinelearningapproachbasedonmagneticresonanceimagesradiomicsanexploratorystudy AT jafarfatahiasl assessingglioblastomatreatmentresponseusingmachinelearningapproachbasedonmagneticresonanceimagesradiomicsanexploratorystudy AT marziyehtahmasbi assessingglioblastomatreatmentresponseusingmachinelearningapproachbasedonmagneticresonanceimagesradiomicsanexploratorystudy AT sasanrazmjoo assessingglioblastomatreatmentresponseusingmachinelearningapproachbasedonmagneticresonanceimagesradiomicsanexploratorystudy AT mohammadyousefipour assessingglioblastomatreatmentresponseusingmachinelearningapproachbasedonmagneticresonanceimagesradiomicsanexploratorystudy |