International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Deep Learning Techniques for Brain Tumor Classification: A Review of CNNs and Ensemble Models |
|---|---|
| ABSTRACT | The complicated the brain’s anatomy and the variety of tumour kinds, sizes, shapes and locations may brain tumour diagnosis difficult. By enabling the automatic extraction of attributes from MRI images recent advances have significantly advanced in DL the classification of brain tumors. Neural network algorithms and convolution transfer learning can accurately learn complex spatial and textural features. However, overfitting sensitivity to data changes and limited generalization are common issues that individual CNN mortals encounter when trained on small and unbalanced medical data sets. Ensemble DL techniques have garnered attention as a potential solution to these issues by combining multiple CNN architectures to enhance resilience and predictive performance. In particular by combining probabilistic outcomes from several model’s ensemble models based on soft voting improve classification reliability. Additionally, data augmentation using generative adversarial networks has been utilized to address class disparities and data shortages. This study offers a thorough examination of CNN-based models transfer learning and ensemble learning approaches for brain tumour classification, highlighting current breakthroughs, limits, and possible directions for future research. |
| AUTHOR | SHILPA YADAWAD, DR. PARVATHRAJ K M M Assistant Professor, K.L. E’s GH BCA College, Haveri, Karnataka, India & Research Scholar, Srinivasa University, Mukka, Mangaluru, Karnataka, India Professor, Department of Artificial Intelligence & Machine Learning, Srinivas Institute of Technology, Mangaluru, Karnataka, India |
| VOLUME | 183 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1404091 |
| pdf/91_Deep Learning Techniques for Brain Tumor Classification A Review of CNNs and Ensemble Models.pdf | |
| KEYWORDS | |
| References | [1]. M. Markchom, Z. Liang, and J. Ferryman, “Comparative analysis of deep learning models for brain tumor MRI classification,” Computers in Biology and Medicine, vol. 174, pp. 106–120, 2025. [2]. Vure, R.B., Pappala, L.K. Enhanced brain tumor classification framework using deep learning. Sci Rep 15, 35814 (2025). https://doi.org/10.1038/s41598-025-19882-y [3]. R. Kumar, S. Gupta, and A. Sharma, “Brain tumor classification using EfficientNet and DenseNet architectures,” Biomedical Signal Processing and Control, vol. 89, pp. 105–118, 2024. [4]. Z. N. K. Swati, Q. Zhao, M. Kabir, F. Ali, Z. Ali, and J. Ahmad, “Brain tumor classification using transfer learning and convolutional neural networks,” IEEE Access, vol. 11, pp. 11234–11245, 2023. [5]. Alanazi, M. F., Ali, M. U., Hussain, S. J., Zafar, A., Mohatram, M., Irfan, M., et al. (2022). Brain tumor/mass classification framework using magnetic-resonance imaging-based isolated and developed transfer deep-learning model. Sensors 22, 372. doi: 10.3390/s22010372. [6]. Can (2022). Cancer. Available online at: https://www.who.int/news-room/fact sheets/detail/cancer (accessed on 30 June, 2022). [7]. Kumar, T. S., Arun, C., and Ezhumalai, P. (2022). An approach for brain tumor detection using optimal feature selection and optimized deep belief network. Biomed. Signal Process. Control 73, 103440. doi: 10.1016/j.bspc.2021.103440. [8]. M. Khan, M. Ashraf, M. Alhaisoni, R. Damaševičius, R. Scherer, and S. Rehman, “A comprehensive study on deep learning-based brain tumor classification,” Frontiers in Neuroscience, vol. 16, pp. 1–18, 2022. [9]. Rizwan, M., Shabbir, A., Javed, A. R., Shabbir, M., Baker, T., and Obe, D. A.-J. (2022a). Brain tumor and glioma grade classification using gaussian convolutional neural network. IEEE Access 10, 29731–29740. doi: 10.1109/ACCESS.2022.3153108. [10]. Amin, J., Sharif, M., Haldorai, A., Yasmin, M., and Nayak, R. S. (2021). Brain tumor detection and classification using machine learning: a comprehensive survey. Complex Intell. Syst. 8, 3161–3183. doi: 10.1007/s40747-021-00563. [11]. Z. Zhou, J. Liu, and X. Zhang, “Ensemble deep learning for medical image classification,” IEEE Journal of Biomedical and Health Informatics, vol. 25, no. 7, pp. 2316–2325, 2021. [12]. Mewada, H. K., Patel, A. V., Hassaballah, M., Alkinani, M. H., and Mahant, K. (2020). Spectral-spatial features integrated convolution neural network for breast cancer classification. Sensors 20, 4747. doi: 10.3390/s20174747. [13]. A. Rehman, S. Naz, A. Razzak, I. A. Hameed, and M. Imran, “Microscopic brain tumor classification using 3D convolutional neural network and generative adversarial networks,” IEEE Access, vol. 8, pp. 181000–181012, 2020. |
