Optimizing the Classification of Brain Tumors Using Ensemble Learning and Gradient-weighted Class Activation Mapping on Multi-section Magnetic Resonance Imaging Images

A brain tumor is a condition in which cells in or around the brain grow abnormally and uncontrollably. Magnetic resonance imaging (MRI) scans are essential for diagnosing brain tumors, where rapid and accurate categorization is key to effective treatment. Automated systems utilizing CNNs provide an effective image classification solution due to their flexibility and architecture. This study proposes an ensemble learning methodology to classify images by combining three CNN architectures, namely Xception, EfficientNetV2S, and ResNet50, to increase classification performance while decreasing overfitting probability. EfficientNetV2S optimizes network components using NAS and progressive learning. Xception is based on the concept of depthwise separable convolution, which uses fewer computational resources while retaining the same discriminative power. ResNet50 relies on residual learning to alleviate the vanishing gradient problem and enhance the representation of deeper features. To provide better explainability, Grad-CAM focuses on critical regions of the MRI scans to assist the experts in confirming the classification outcomes. The ensemble technique generated significant performance metrics, including an accuracy of 99.18%, precision of 99.19%, recall of 99.18%, F1-score of 99.18%, and AUC-ROC of 0.9993, proving minimal false classifications. Combining ensemble learning and Grad-CAM offers the most explainable and accurate model for the classification of brain tumors into four categories: glioma, meningioma, non-tumor, and pituitary tumors. The research outcomes provide further evidence to support the use of AI in smart diagnostic devices, providing improved generalization and reliability for use in the medical field.

Brain tumor classification; Cancer; EfficientNetV2S; Ensemble learning; MRI multi-section

Alsubai, S., Khan, H. U., Alqahtani, A., Sha, M., Abbas, S., & Mohammad, U. G. (2022). Ensemble deep learning for brain tumor detection. Frontiers in Computational Neuroscience, 16, 1–14. https://doi.org/10.3389/fncom.2022.1005617

Alther, B., Mylius, V., Weller, M., & Gantenbein, A. (2020). From first symptoms to diagnosis: Initial clinical presentation of primary brain tumors. Clinical and Translational Neuroscience, 4 (2), 2514183X20968368. https://doi.org/10.1177/2514183x20968368

Amarnath, A., Bataineh, A. A., & Hansen, J. A. (2024). Transfer-learning approach for enhanced brain tumor classification in mri imaging. BioMedInformatics, 4 (3), 1745–1756. https://doi.org/10.3390/biomedinformatics4030095

Aziz, A., Attique, M., Tariq, U., Nam, Y., Nazir, M., Jeong, C. W., Mostafa, R. R., & Sakr, R. H. (2021). An ensemble of optimal deep learning features for brain tumor classification. Computers, Materials & Continua, 69 (2), 2653–2670. https://doi.org/10.32604/cmc.2021.018606 

Basha, S. A. K., Vincent, P. M. D. R., Mohammad, S. I., Vasudevan, A., Soon, E. E. H., Shambour, Q., & Alshurideh, M. T. (2025). Exploring deep learning methods for audio speech emotion detection: An ensemble mfccs, cnns and lstm. Applied Mathematics & Information Sciences, 19 (1), 75–85. https://doi.org/10.18576/amis/190107

C? etin-Kaya, Y., & Kaya, M. (2024). A novel ensemble framework for multi-classification of brain tumors using magnetic resonance imaging. Diagnostics, 14 (4), 383. https://doi.org/10.3390/diagnostics14040383

Dishar, H. K., & Muhammed, L. A. (2023). Detection brain tumor disease using a combination of xception and nasnetmobile. International Journal of Advanced Soft Computing and its Applications, 15 (2), 325–336. https://doi.org/10.15849/IJASCA.230720.22

Diyasa, I. G. S. M., Saputra, W. S. J., Gunawan, A. A. N., Herawati, D., Munir, S., & Humairah, S. (2024). Abnormality determination of spermatozoa motility using gaussian mixture model and matching-based algorithm. Journal of Robotics and Control, 5 (1), 103–116. https://doi.org/10.18196/jrc.v5i1.20686

Gawali, B. S., & Dhongade, V. S. (2024). Enhancing brain tumor classification: A cnn-based approach with inceptionv3 and xception. International Journal of Advanced Research in Science, Communication and Technology, 4 (2), 492–504. https://doi.org/10.48175/ijarsct-18174

Ghaffar, A., Javid, M. A., Arshad, S., & Azeem, W. (2024). Enhanced efficientnet model for multiclass brain tumor prognostication using advanced mr image analysis techniques. Research Square, 1–12. https://doi.org/10.21203/rs.3.rs-4809509/v2

Gharaibeh, N. (2025). Enhancing interpretability in brain tumor detection: Leveraging grad-cam and shap for explainable ai in mri-based cancer diagnosis. Applied Computer Science, 21 (3), 182–197. https://doi.org/10.35784/acs7375

Ghazvini, M., Vahab, D., Arash, P., & Meysam, S. (2024). Diagnosis and classification of brain tumors from mri images using the svm algorithm. Journal of Clinical Research in Paramedicine Sciences, 13 (1), 1–8. https://doi.org/10.5812/jcrps-148703

Gokila, P., Nagarasan, M., Anandhi, R., Manikandan, B., Sharan, V. J., & Daniel, S. S. (2024). Efficientnet transfer learning approach for multi-class brain tumor classification. International Journal of Scientific Research in Engineering and Management, 8 (5), 1–5. https://doi.org/10.55041/ijsrem32835

Guo, X., Liu, T., & Chi, Q. (2024). Brain tumor diagnosis in mri scans images using residual/shuffle network optimized by augmented falcon finch optimization. Scientific Reports, 14 (1), 1–21. https://doi.org/10.1038/s41598-024-77523-2

He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778. https://doi.org/10.1109/CVPR.2016.90

Hosny, K. M., Mohammed, M. A., Salama, R. A., & Elshewey, A. M. (2024). Explainable ensemble deep learning-based model for brain tumor detection and classification. Neural Computing and Applications, 37 (3), 1289–1306. https://doi.org/10.1007/s00521-024-10401-0

Ismail, K. A. A., Dutta, A. K., & Sait, A. R. W. (2024). Ensemble learning-based multiple sclerosis detection technique using magnetic resonance imaging. Journal of Disability Research, 3 (6), 1–8. https://doi.org/10.57197/jdr-2024-0078

Kesuma, L. I., Ermatita, & Erwin. (2023). Elrei: Ensemble learning of resnet, efficientnet, and inception-v3 for lung disease classification based on chest x-ray image. International Journal of Intelligent Engineering and Systems, 16 (5), 149–161. https://doi.org/10.22266/ijies2023.1031.14

Lapointe, S., Perry, A., & Butowski, N. A. (2018). Primary brain tumours in adults. The Lancet, 392 (10145), 432–446. https://doi.org/10.1016/S0140-6736(18)30990-5

Lovell, D., Miller, D., Capra, J., & Bradley, A. (2023). Never mind the metrics – what about the uncertainty? visualising binary confusion matrix metric distributions to put performance in perspective. Proceedings of the 40th International Conference on Machine Learning (ICML), 202, 22702–22757. https://proceedings.mlr.press/v202/lovell23a.html

Lu, G., Zhang, W., & Wang, Z. (2022). Optimizing depthwise separable convolution operations on gpus. IEEE Transactions on Parallel and Distributed Systems, 33 (1), 70–87. https://doi.org/10.1109/TPDS.2021.3084813

Mahdi, H. A., Shujaa, M. I., & Zghair, E. M. (2023). Diagnosis of medical images using fuzzy convolutional neural networks. Mathematical Modelling of Engineering Problems, 10 (4), 1345–1351. https://doi.org/10.18280/mmep.100428

Mathivanan, S. K., Sonaimuthu, S., Murugesan, S., Rajadurai, H., Shivahare, B. D., & Shah, M. A. (2024). Employing deep learning and transfer learning for accurate brain tumor detection. Scientific Reports, 14 (1), 1–15. https://doi.org/10.1038/s41598-024-57970-7

Miko lajczyk, A., & Grochowski, M. (2018). Data augmentation for improving deep learning in image classification problem. 2018 International Interdisciplinary PhD Workshop (IIPhDW), 117–122. https://doi.org/10.1109/IIPHDW.2018.8388338

Muhammad, W., Aramvith, S., & Onoye, T. (2021). Multi-scale xception based depthwise separable convolution for single image superresolution. PLoS One, 16 (8), 1–20. https://doi.org/10.1371/journal.pone.0249278

Mumuni, A., & Mumuni, F. (2022). Data augmentation: A comprehensive survey of modern approaches. Array, 16, 100258. https://doi.org/10.1016/j.array.2022.100258

Murugan, D. V. (2023). Image enhancement of magnetic resonance imaging under clustering environment. In Future trends in computer technology and data science (pp. 118–126, Vol. 2). https://doi.org/10.58532/v2bs18p2ch4

Musa, M. N., Sanusi, M. B., Odion, P., & Shitu, S. S. (2024). Mri-based brain tumor classification using resnet-50 and optimized softmax regression. Jurnal Infotel, 16 (3), 598–614. https://doi.org/10.20895/INFOTEL.V16I3.1175

Nazir, M. I., Akter, A., Wadud, M. A. H., & Uddin, M. A. (2024). Utilizing customized cnn for brain tumor prediction with explainable ai. Heliyon, 10 (20), e38997. https://doi.org/10.1016/j.heliyon.2024.e38997

Nickparvar, M. (2023). Brain tumor mri dataset [Kaggle dataset]. https://www.kaggle.com/datasets/masoudnickparvar/brain-tumor-mri-dataset

Pacal, I., Celik, O., Bayram, B., & Cunha, A. (2024). Enhancing efficientnetv2 with global and efficient channel attention mechanisms for accurate mri-based brain tumor classification. Cluster Computing, 27 (8), 11187–11212. https://doi.org/10.1007/s10586-024-04532-1

Pfaff, L., Hossbach, J., Preuhs, E., Wagner, F., Camejo, S. A., Kannengiesser, S., Nickel, D., Wuerfl, T., & Maier, A. (2023). Self-supervised mri denoising: Leveraging stein’s unbiased risk estimator and spatially resolved noise maps. Scientific Reports, 13 (1), 1–13. https://doi.org/10.1038/s41598-023-49023-2

Priyadarshini, P., Kanungo, P., & Kar, T. (2024). Multigrade brain tumor classification in mri images using fine tuned efficientnet. e-Prime - Advances in Electrical Engineering, Electronics and Energy, 8, 100498. https://doi.org/10.1016/j.prime.2024.100498

Radke, K. L., Kamp, B., Adriaenssens, V., Stabinska, J., Gallinnis, P., Wittsack, H. J., Antoch, G., & M ?uller-Lutz, A. (2023). Deep learning-based denoising of cest mr data: A feasibility study on applying synthetic phantoms in medical imaging. Diagnostics, 13 (21), 3326. https://doi.org/10.3390/diagnostics13213326

Sankar, M., Baiju, B., Preethi, D., Kumar, A. S., Mathivanan, S. K., & Shah, M. A. (2024). Efficient brain tumor grade classification using ensemble deep learning models. BMC Medical Imaging, 24 (1), 297. https://doi.org/10.1186/s12880-024-01476-1

Sharif, R., Azam, M., Ali, A., Hashmi, M. U., & Uzair, M. (2024). Comparative analysis of ensemble learning techniques for brain tumor classification. Informatica, 48 (20), 41–50. https://doi.org/10.31449/inf.v48i20.6714

Shinde, S., Tupe-Waghmare, P., Chougule, T., Saini, J., & Ingalhalikar, M. (2021). Predictive and discriminative localization of pathology using high resolution class activation maps with cnns. PeerJ Computer Science, 7, 1–14. https://doi.org/10.7717/peerj-cs.622

Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6 (1). https://doi.org/10.1186/s40537-019-0197-0

Singh, R., Prabha, C., Malik, M., & Goyal, A. (2025). A robust deep learning model for brain tumor detection and classification using efficient net: A brief meta-analysis. Journal of Advanced Research in Applied Sciences and Engineering Technology, 49 (2), 26–51. https://doi.org/10.37934/araset.49.2.2651

Singh, T., Nair, R. R., Babu, T., Wagh, A., Bhosalea, A., & Duraisamy, P. (2024). Brainnet: A deep learning approach for brain tumor classification. Procedia Computer Science, 235, 3283–3292. https://doi.org/10.1016/j.procs.2024.04.310

Sivaz, O., & Aykut, M. (2024). Combining efficientnet with ml-decoder classification head for multi-label retinal disease classification. Neural Computing and Applications, 36 (23), 14251–14261. https://doi.org/10.1007/s00521-024-09820-w

Sterniczuk, B., & Charytanowicz, M. (2024). An ensemble transfer learning model for brain tumors classification using convolutional neural networks. Advances in Science and Technology Research Journal, 18 (8), 204–216. https://doi.org/10.12913/22998624/193627

Subburaj, T., & Bhavana, S. (2024). Image noise reduction with auto-encoders using tensorflow. International Journal of Advanced Research in Science, Communication and Technology, 86–91. https://doi.org/10.48175/ijarsct-19016

Sung, H., Ferlay, J., Siegel, R. L., Laversanne, M., Soerjomataram, I., Jemal, A., & Bray, F. (2021). Global cancer statistics 2020: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians, 71 (3), 209–249. https://doi.org/10.3322/caac.21660

Tan, M., & Le, Q. V. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the 36th International Conference on Machine Learning, 97, 10691–10700. https://proceedings.mlr.press/v97/tan19a.html

Tandel, G. S., Biswas, M., Kakde, O. G., Tiwari, A., Suri, H. S., Turk, M., Laird, J. R., Asare, C. K., Ankrah, A. A., Khanna, N. N., Madhusudhan, B. K., Saba, L., & Suri, J. S. (2019). A review on a deep learning perspective in brain cancer classification. Cancers, 11 (1), 1–32. https://doi.org/10.3390/cancers11010111

Tatar, A., Haghighi, M., & Zeinijahromi, A. (2024). Experiments on image data augmentation techniques for geological rock type classification with convolutional neural networks. Journal of Rock Mechanics and Geotechnical Engineering. https://doi.org/10.1016/j.jrmge.2024.02.015

Vo, H. T., Thien, N. N., Mui, K. C., & Tien, P. P. (2024). Enhancing confidence in brain tumor classification models with grad-cam and grad-cam++. Indonesian Journal of Electrical Engineering and Informatics, 12 (3), 926–939. https://doi.org/10.52549/ijeei.v12i3.5977

Yoon, S. (2025). Brain tumor classification using a hybrid ensemble of xception and parallel deep cnn models. Informatics in Medicine Unlocked, 54, 101629. https://doi.org/10.1016/j.imu.2025.101629

Younis, A., Qiang, L., Nyatega, C. O., Adamu, M. J., & Kawuwa, H. B. (2022). Brain tumor analysis using deep learning and vgg-16 ensembling learning approaches. Applied Sciences, 12 (14), 7282. https://doi.org/10.3390/app12147282

Zhang, Z., Li, G., Xu, Y., & Tang, X. (2021). Application of artificial intelligence in the mri classification task of human brain neurological and psychiatric diseases: A scoping review. Diagnostics, 11 (8), 1402. https://doi.org/10.3390/diagnostics11081402