TRANSFORMING BRAIN TUMOR DETECTION EMPOWERING MULTI-CLASS CLASSIFICATION WITH VISION TRANSFORMERS AND EFFICIENT NET V2
DOI:
https://doi.org/10.5281/zenodo.21377371Keywords:
Efficient netv2, Convolutional Neural Network (CNN), Brain Tumor Vision Transformers (ViT), Magnetic Resonance Imaging (MRI), Multilayer Perceptron (MLP)Abstract
Brain tumor detection is a crucial medical imaging task. In MRI images, accurate classification and detection of tumor sites in MRI play a crucial role in diagnosis and treatment success. In this study, we used the Brain Tumor MRI dataset for multi-class classification and detection. For classification we used advanced transfer learning models, such as EfficientNetV2, Vision Transformer ViT-B16, DenseNet121, and Xception. We also used ensemble averaging (average, weighted average, geometric mean) to improve prediction accuracy. We used several versions of YOLO (YOLOv5, YOLOv8, YOLOv9, and YOLOv11) with bounding box annotations in YOLO format to detect and localise tumors. We also applied explainable AI techniques such as Grad-CAM to generate heat maps of discriminative location of tumors that influence the model's predictions. Our experimental results indicate that DenseNet121 and Xception-based models had the highest accuracy (99.54%) for the classification of tumors among all the classifiers. YOLO v8 had the best detection accuracy, with a Map of 95.1%. This shows that the combination of the classification and detection models with interpretability methods is a good approach to achieve a robust and accurate brain tumor diagnosis. We also developed a web app using Flask to use the models. This allows users to upload MRI images and get information about the tumor location, class, and confidence through a user-friendly interface.
References
I. 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.
II. Ishaq, A., Ullah, F. U. M., Hamandawana, P., Cho, D. J., & Chung, T. S. (2025). Improved Efficient Net architecture for multi-grade brain tumor detection. Electronics, 14(4), 710.
III. Priyadarshini, P., Kanungo, P., & Kar, T. (2024). Multigrade brain tumor classification in MRI images using Fine tuned efficient net. e-Prime-Advances in Electrical Engineering, Electronics and Energy, 8, 100498.
IV. Asif, R. N., Naseem, M. T., Ahmad, M., Mazhar, T., Khan, M. A., Khan, A., & Hamam, H. (2025). Brain tumor detection empowered with ensemble deep learning approaches from MRI scan images. Scientific Reports, 15(1), 15002.
V. Vamsidhar, D., Desai, P., Joshi, S., Kolhar, S., Deshpande, N., & Gite, S. (2025). Hybrid model integration with explainable AI for brain tumor diagnosis: a unified approach to MRI analysis and prediction. Scientific Reports, 15(1), 20542.
VI. Lah, T. T., Novak, M., & Breznik, B. (2020). Brain malignancies: Glioblastoma and brain metastases. Seminars in Cancer Biology, 60, 262–273.
VII. Ahmmed, S., Podder, P., Mondal, M., Rahman, S., Kannan, S., Hasan, M., Rohan, A., & Prosvirin, A. (2023). Enhancing brain tumor classification with transfer learning across multiple classes: An in-depth analysis. Bio Med Informatics,3(4),1124–1144.
VIII. Alzahrani, S. M. (2023). Conv Atten Mixer: Brain tumor detection and type classification using convolutional mixer with external and self-attention mechanisms. Journal of King Saud University – Computer and Information Sciences,35(10), 101810.
IX. Hussain, T., & Shouno, H. (2023). Explainable deep learning approach for multi-class brain magnetic resonance imaging tumor classification and localization using gradient-weighted class activation mapping. Information, 14(12), 642.
X. Jun, E., Jeong, S., Heo, D.-W., &Suk, H.-I. (2021). Medical transformer: Universal brain encoder for 3D MRI analysis. arXiv:2104.13633.
XI. Li, M., Wei, R., Zhang, Z., Zhang, P., Xu, G., & Liao, W. (2023). CVT-based asynchronous BCI for brain-controlled robot navigation. Cyborg and Bionic Systems, 4, 0024.
XII. Si, X., He, H., Yu, J., & Ming, D. (2023). Cross-subject emotion recognition brain–computer interface based on NIR Sand DBJ Net. Cyborg and Bionic Systems, 4, 0045.
XIII. Kumar, R. L., Kakarla, J., Isunuri, B. V., & Singh, M. (2021). Multi-class brain tumor classification using residual network and global average pooling. Multimedia Tools and Applications, 80(9), 13429–13438.
XIV. Meshram, P. A., Joshi, S., & Mahajan, D. (2023). Brain tumor detection using Swin transformers. arXiv:2305.06025.
XV. Ramakrishnan, A. B., Sridevi, M., Vasudevan, S. K., Manikandan, R., & Gandomi, A. H. (2024). Optimizing brain tumor classification with hybrid CNN architecture: Balancing accuracy and efficiency through one API optimization. Informatics in Medicine Unlocked, 44, 101436.
XVI. Rastogi, D., Johri, P., Tiwari, V., & Elngar, A. A. (2024). Multi-class classification of brain tumour magnetic resonance images using multi-branch network with inception block and five-fold cross validation deep learning framework. Biomedical Signal Processing and Control, 88, 105602.
XVII. Liu, Z., Chen, L., Cheng, H., Ao, J., Xiong, J., Liu, X., Chen, Y., Mao, Y., & Ji, M. (2024). Virtual formalin-fixed and paraffin-embedded staining of fresh brain tissue via stimulated Raman Cycle GAN model. Science Advances, 10(13), 3426.
XVIII. Tandel, G. S., Balestrieri, A., Jujaray, T., Khanna, N. N., Saba, L., & Suri, J. S. (2020). Multiclass magnetic resonance imaging brain tumor classification using artificial intelligence paradigm. Computers in Biology and Medicine, 122, 103804.
XIX. Zhou, M., Wagner, M. W., Tabori, U., Hawkins, C., Ertl-Wagner, B. B., & Khalvati, F. (2023). Generating 3D brain tumor regions in MRI using vector quantization generative adversarial networks. arXiv:2310.01251.
XX. Parshapa, P., & Rani, P. I. (2023). A survey on an effective identification and analysis for brain tumour diagnosis using machine learning technique. International Journal of Recent Innovations Trends
Computer and Communication, 11(3), 68–78.
XXI. Irmak, E. (2021). Multi-classification of brain tumor MRI images using deep convolutional neural network with fully optimized framework. Iranian Journal of Science and Technology, Transactions of ElectricalEngineering,45(3),1015–1036.
XXII. Sadad, T., Rehman, A., Munir, A., Saba, T., Tariq, U., Ayesha, N., & Abbasi, R. (2021). Brain tumor detection and multi-classification using advanced deep learning techniques. Microscopy Research and Technique, 84(6), 1296–1308.
XXIII. Ben Naceur, M., Akil, M., Saouli, R., & Kachouri, R. (2020). Fully automatic brain tumor segmentation with deep learning-based selective attention using overlapping patches and multi-class weighted cross-entropy. Medical Image Analysis,63, 101692.
XXIV. Muhammad, K., Khan, S., Ser, J. D., & Albuquerque, V. H. C. D. (2021). Deep learning for multigrade brain tumor classification in smart healthcare systems: A prospective survey. IEEE Transactions on Neural Networks and Learning Systems, 32(2), 507–522.
XXV. Kumar, S., & Mankame, D. P. (2020). Optimization driven deep convolution neural network for brain tumor classification. Biocybernetics and Biomedical Engineering, 40(3), 1190–1204.
XXVI. Asiri, A. A., Shaf, A., Ali, T., Aamir, M., Irfan, M., & Alqahtani, S. (2024). Enhancing brain tumor diagnosis: An optimized CNN hyperparameter model for improved accuracy and reliability. PeerJ Computer Science, 10, e1878.
XXVII. Asiri, A. A., Shaf, A., Ali, T., Pasha, A., Aamir, M., Irfan, M., Alqahtani, S., Alghamdi, A. J., Alghamdi, A. H., Alshamrani, A. F. A., Alelyani, M., & Alamri, S. (2023). Advancing brain tumor classification through fine-tuned vision transformers: A comparative study of pre-trained models. Sensors, 23(18), 7913.
XXVIII. Asiri, A. A., Aamir, M., Ali, T., Shaf, A., Irfan, M., Mehdar, K. M., Alqhani, S. M., Alghamdi, A. H., Alshamrani, A. F. A., & Alshehri, O. (2023). Next-gen brain tumor classification: Pioneering with deep learning and fine-tuned conditional generative adversarial networks. PeerJ Computer Science, 9, e1667.
XXIX. Gürsoy, E., & Kaya, Y. (2024). Brain-GCN-net: Graph-convolutional neural network for brain tumor identification. Computers in Biology and Medicine, 180, 108971.
XXX. Wang, T.-W., Shiao, Y.-C., Hong, J.-S., Lee, W.-K., Hsu, M.-S., Cheng, H.-M., Yang, H.-C., Lee, C.-C., Pan, H.-C., You, W. C., Lirng, J.-F., Guo, W.-Y., & Wu, Y.-T. (2024). Artificial intelligence detection and segmentation models: A systematic review and meta-analysis of brain tumors in magnetic resonance imaging. Mayo Clinic Proceedings: Digital Health, 2(1), 75–91.
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Educational Journal of Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
