Signal and Data Processing Journal A scientific journal officially licensed by the Commission for Scientific Publications of the (MSRT). Publisher: Research Ceter for Developmen of Technologies
Volume 22, Issue 4 (3-2026)
JSDP 2026, 22(4): 122-101 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Emami H, Azarnavid B, Abdolhosseinzadeh M. Predicting glioma brain tumor grades using ensemble machine learning. JSDP 2026; 22 (4) : 6
URL: http://jsdp.rcisp.ac.ir/article-1-1484-en.html
URL: http://jsdp.rcisp.ac.ir/article-1-1484-en.html
Associate Professor, Department of Computer Engineering, Faculty of Engineering, University of Bonab, Bonab, Iran
Abstract: (300 Views)
Gliomas, or in other words, aggressive and progressive brain tumors, lead to great complexity in the diagnosis and treatment of patients. While recent machine learning models provided encouraging results in glioma diagnosis and grading, the topic is open, and more efforts are needed. Existing models, despite encouraging results, often fall short of the ideal diagnostic state, highlighting the need for further research to develop robust and high-performing predictive models
.
This study introduces an optimized ensemble machine learning (EML) model designed to maximize classification (grading) performance and mitigate the pervasive issue of overfitting in glioma grading. Our approach employs a two-layer architecture that synergistically combines diverse weak and base learners. In the first layer, a diverse set of learners, including support vector machine (SVM), categorical boosting (CatBoost), extremely randomized trees (ERT), and random forest (RF), is integrated. This initial ensemble aims to capture a broad spectrum of grading patterns and enhance the overall accuracy by leveraging the complementary strengths of each base model. The outputs from this first layer, representing diversified classification probabilities, are then fed into a second-layer logistic regression (LR) model. This layer refines the predictions, performing the ultimate classification while explicitly addressing and eliminating the overfitting problem, thereby promoting better generalization to unseen data.
To rigorously evaluate the performance of the proposed ELM model, a comprehensive comparison was conducted against its constituent base learners and counterpart machine learning models. All models were assessed using a standard, publicly available glioma dataset. To prevent overfitting, examine the robustness of models, and evaluate models fairly, a 5-fold cross-validation strategy is used in experiments. The effectiveness of models was measured using four performance metrics, including accuracy, recall, precision, and F1-score.
The experimental results demonstrate the superior performance of the proposed EML model. Across all evaluated metrics, our model consistently outperformed the individual base learners and other benchmarked algorithms, securing the top rank in terms of accuracy. Specifically, the LR model operating on the first-layer ensemble predictions proved highly effective in both enhancing accuracy and preventing overfitting. Following our proposed model, the standalone LR and RF models demonstrated commendable performance, ranking second and third, respectively
.
The findings of this study underscore the significant potential of an optimized EML model for advancing the field of glioma tumor grading. The proposed model generated promising results and mitigated overfitting through integrating diverse base learners and using an LR model as a meta-model. The results reveal that the proposed model is a reliable and robust tool that can aid Clinical specialists in effectively diagnosing and classifying gliomas, ultimately paving the way for improved patient satisfaction.
.
This study introduces an optimized ensemble machine learning (EML) model designed to maximize classification (grading) performance and mitigate the pervasive issue of overfitting in glioma grading. Our approach employs a two-layer architecture that synergistically combines diverse weak and base learners. In the first layer, a diverse set of learners, including support vector machine (SVM), categorical boosting (CatBoost), extremely randomized trees (ERT), and random forest (RF), is integrated. This initial ensemble aims to capture a broad spectrum of grading patterns and enhance the overall accuracy by leveraging the complementary strengths of each base model. The outputs from this first layer, representing diversified classification probabilities, are then fed into a second-layer logistic regression (LR) model. This layer refines the predictions, performing the ultimate classification while explicitly addressing and eliminating the overfitting problem, thereby promoting better generalization to unseen data.
To rigorously evaluate the performance of the proposed ELM model, a comprehensive comparison was conducted against its constituent base learners and counterpart machine learning models. All models were assessed using a standard, publicly available glioma dataset. To prevent overfitting, examine the robustness of models, and evaluate models fairly, a 5-fold cross-validation strategy is used in experiments. The effectiveness of models was measured using four performance metrics, including accuracy, recall, precision, and F1-score.
The experimental results demonstrate the superior performance of the proposed EML model. Across all evaluated metrics, our model consistently outperformed the individual base learners and other benchmarked algorithms, securing the top rank in terms of accuracy. Specifically, the LR model operating on the first-layer ensemble predictions proved highly effective in both enhancing accuracy and preventing overfitting. Following our proposed model, the standalone LR and RF models demonstrated commendable performance, ranking second and third, respectively
.
The findings of this study underscore the significant potential of an optimized EML model for advancing the field of glioma tumor grading. The proposed model generated promising results and mitigated overfitting through integrating diverse base learners and using an LR model as a meta-model. The results reveal that the proposed model is a reliable and robust tool that can aid Clinical specialists in effectively diagnosing and classifying gliomas, ultimately paving the way for improved patient satisfaction.
Article number: 6
Type of Study: Research |
Subject:
Paper
Received: 2025/08/12 | Accepted: 2025/10/6 | Published: 2026/03/20 | ePublished: 2026/03/20
Received: 2025/08/12 | Accepted: 2025/10/6 | Published: 2026/03/20 | ePublished: 2026/03/20
References
1. D. N. Louis et al., "The 2007 WHO classification of tumours of the central nervous system," Acta Neuropathol, vol. 114, no. 2, pp. 97-109, 2007, doi: 10.1007/s00401-007-0243-4. [DOI:10.1007/s00401-007-0243-4]
2. M. A. Naser and M. J. Deen, "Brain tumor segmentation and grading of lower-grade glioma using deep learning in MRI images," Comput Biol Med, vol. 121, p. 103758, 2020, doi: 10.1016/j.compbiomed.2020.103758. [DOI:10.1016/j.compbiomed.2020.103758]
3. A. Krauze, "Using Artificial Intelligence and Magnetic Resonance Imaging to Address Limitations in Response Assessment in Glioma," Oncology Insights, vol. 1, pp. 1-14, 2022, doi: 10.55085/oi.2022.616. [DOI:10.55085/oi.2022.616]
4. S. Pereira, R. Meier, V. Alves, M. Reyes, and C. A. Silva, "Automatic brain tumor grading from MRI data using convolutional neural networks and quality assessment," in International Workshop on Machine Learning in Clinical Neuroimaging, Cham: Springer International Publishing, 2018, pp. 106-114. [DOI:10.1007/978-3-030-02628-8_12]
5. K. O. Almansory and F. Fraioli, "Combined PET/MRI in brain glioma imaging," Br J Hosp Med, vol. 80, no. 7, pp. 380-386, 2019, doi: 10.12968/hmed.2019.80.7.380. [DOI:10.12968/hmed.2019.80.7.380]
6. J. Tiefenbach et al., "The use of advanced neuroimaging modalities in the evaluation of low-grade glioma in adults: a literature review," Neurosurg Focus, vol. 56, no. 2, 2024, doi: 10.3171/2023.11.FOCUS23649. [DOI:10.3171/2023.11.FOCUS23649]
7. E. Tasci, Y. Zhuge, H. Kaur, K. Camphausen, and A. V. Krauze, "Hierarchical Voting-Based Feature Selection and Ensemble Learning Model Scheme for Glioma Grading with Clinical and Molecular Characteristics," Int J Mol Sci, vol. 23, no. 22, 2022, doi: 10.3390/ijms232214155. [DOI:10.3390/ijms232214155]
8. P. Wesseling and D. Capper, "WHO 2016 Classification of gliomas," Neuropathol Appl Neurobiol, vol. 44, no. 2, pp. 139-150, 2018, doi: 10.1111/nan.12432. [DOI:10.1111/nan.12432]
9. M. Platten and D. A. Reardon, "Concepts for Immunotherapies in Gliomas," Semin Neurol, vol. 38, no. 1, pp. 62-72, 2018, doi: 10.1055/s-0037-1620274. [DOI:10.1055/s-0037-1620274]
10. R. L. Soiza, A. I. C. Donaldson, and P. K. Myint, "Treatment of glioblastoma in adults," Ther Adv Vaccines, vol. 9, no. 6, pp. 259-261, 2018. [DOI:10.1177/2042098618769568]
11. R. Sánchez-Marqués, V. García, and J. S. Sánchez, "A data-centric machine learning approach to improve prediction of glioma grades using low-imbalance TCGA data," Sci Rep, vol. 14, no. 1, pp. 1-16, 2024, doi: 10.1038/s41598-024-68291-0. [DOI:10.1038/s41598-024-68291-0]
12. M. N. Samara and K. D. Harry, "Integrating Boruta , LASSO , and SHAP for Clinically Interpretable Glioma Classification Using Machine Learning," BioMedInformatics, vol. 5, no. 34, pp. 1-26, 2025. [DOI:10.3390/biomedinformatics5030034]
13. S. Deepak and P. M. Ameer, "Brain tumor classification using deep CNN features via transfer learning," Comput Biol Med, vol. 111, p. 103345, 2019, doi: 10.1016/j.compbiomed.2019.103345. [DOI:10.1016/j.compbiomed.2019.103345]
14. A. Alksas et al., "A Novel System for Precise Grading of Glioma," Bioengineering, vol. 9, no. 10, pp. 1-21, 2022, doi: 10.3390/bioengineering9100532. [DOI:10.3390/bioengineering9100532]
15. X. Wang et al., "Machine learning models for multiparametric glioma grading with quantitative result interpretations," Front Neurosci, vol. 13, no. JAN, p. 432416, Jan. 2019, doi: 10.3389/FNINS.2018.01046/BIBTEX. [DOI:10.3389/fnins.2018.01046]
16. L. Wen, H. Sun, G. Liang, and Y. Yu, "A deep ensemble learning framework for glioma segmentation and grading prediction," Sci Rep, vol. 15, no. 1, pp. 1-15, Dec. 2025, doi: 10.1038/S41598-025-87127-Z;SUBJMETA. [DOI:10.1038/s41598-025-87127-z]
17. X. Xia, W. Wu, Q. Tan, and Q. Gou, "Interpretable Machine Learning Models for Differentiating Glioblastoma From Solitary Brain Metastasis Using Radiomics," Acad Radiol, vol. 32, no. 9, pp. 5388-5400, Sep. 2025, doi: 10.1016/J.ACRA.2025.05.016. [DOI:10.1016/j.acra.2025.05.016]
18. R. C. Joshi, R. Mishra, P. Gandhi, V. K. Pathak, R. Burget, and M. K. Dutta, "Ensemble based machine learning approach for prediction of glioma and multi-grade classification," Comput Biol Med, vol. 137, p. 104829, Oct. 2021, doi: 10.1016/J.COMPBIOMED.2021.104829. [DOI:10.1016/j.compbiomed.2021.104829]
19. S. Gutta, J. Acharya, M. S. Shiroishi, D. Hwang, and K. S. Nayak, "Improved Glioma Grading Using Deep Convolutional Neural Networks," American Journal of Neuroradiology, vol. 42, no. 2, pp. 233-239, 2021. [DOI:10.3174/ajnr.A6882]
20. J. Cheng, J. Liu, H. Yue, H. Bai, Y. Pan, and J. Wang, "Prediction of Glioma Grade Using Intratumoral and Peritumoral Radiomic Features From Multiparametric MRI Images," IEEE/ACM Trans Comput Biol Bioinform, vol. 19, no. 2, pp. 1084-1095, 2022, doi: 10.1109/TCBB.2020.3033538. [DOI:10.1109/TCBB.2020.3033538]
21. T. R. Noviandy, G. M. Idroes, and I. Hardi, "Integrating explainable artificial intelligence and light gradient boosting machine for glioma grading," Informatics and Health, vol. 2, no. 1, pp. 1-8, 2025, doi: 10.1016/j.infoh.2024.12.001. [DOI:10.1016/j.infoh.2024.12.001]
22. S. M. Lundberg and S. Lee, "A Unified Approach to Interpreting Model Predictions," in 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA, 2017, pp. 1-10.
23. J. T. Hancock and T. M. Khoshgoftaar, "CatBoost for big data: an interdisciplinary review," J Big Data, vol. 7, no. 94, 2020, doi: 10.1186/s40537-020-00369-8. [DOI:10.1186/s40537-020-00369-8]
24. A. Verikas, A. Gelzinis, and M. Bacauskiene, "Mining data with random forests : A survey and results of new tests," Pattern Recognit, vol. 44, no. 2, pp. 330-349, 2011, doi: 10.1016/j.patcog.2010.08.011. [DOI:10.1016/j.patcog.2010.08.011]
25. P. Geurts, D. Ernst, and L. Wehenkel, "Extremely randomized trees," Mach Learn, vol. 63, no. 1, pp. 3-42, 2006, doi: 10.1007/s10994-006-6226-1. [DOI:10.1007/s10994-006-6226-1]
26. S. Lavanya, S. V. Annlin Jeba, P. Bhuvaneswari, and F. H. Shajin, "Support vector machine classifier optimized with seagull optimization algorithm for brain tumor classification," Concurr Comput, vol. 35, no. 1, pp. 1-13, 2023, doi: 10.1002/cpe.7396. [DOI:10.1002/cpe.7396]
27. M. Maalouf, "Logistic regression in data analysis: An overview," International Journal of Data Analysis Techniques and Strategies, vol. 3, no. 3, pp. 281-299, 2011, doi: 10.1504/IJDATS.2011.041335. [DOI:10.1504/IJDATS.2011.041335]
28. I. M. De Diego, A. R. Redondo, R. R. Fernández, J. Navarro, and J. M. Moguerza, "General Performance Score for classification problems," Applied Intelligence, vol. 52, no. 10, pp. 12049-12063, 2022, doi: 10.1007/s10489-021-03041-7. [DOI:10.1007/s10489-021-03041-7]
29. خدادای، الناز، حسینی، راحیل، مزینانی مهدی، «ارائة مدلهای محاسبات نرم مبتنی بر فازی، تکاملی و هوش جمعی در تحلیل تصاویر ماموگرافی جهت تشخیص تومورهای سینه»، فصلنامة پردازش علائم و داده ها، دورة۱۶، شمارة ۲، صفحات ۱۶۵-۱۴۷، ۱۳۹۸.
29. E. Khodadadi, R. Hosseini, M. Mazinani, "Soft Computing Methods based on Fuzzy, Evolutionary and Swarm Intelligence for Analysis of Digital Mammography Images for Diagnosis of Breast Tumors," Journal of Signal and Data Processing, vol. 16, no. 2, pp. 147-165, 2019, doi: 10.29252/jsdp.16.2.147. [DOI:10.29252/jsdp.16.2.147]
30. آذرنوید، بابک، عبدالحسین زاده، محسن، امامی، حجت، «مدل یادگیری ماشین انباشته برای دستهبندی و پیشبینی بیماریهای کبدی»، فصلنامة پردازش علائم و داده ها، دورة22، شمارة ۲، صفحات 79-96، 1404.
30. B. Azarnavid, M. Abdolhosseinzadeh, H. Emami, "Stacking machine learning model for classification and prediction of liver diseases," Journal of Signal and Data Processing, vol. 22, no. 2, pp. 79-96, 2025, doi: 10.61882/jsdp.22.2.79. [DOI:10.61882/jsdp.22.2.79]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |