This paper proposes a brain tumor detection system using MRI images by integrating transfer learning-based convolutional neural networks for feature extraction with XGBoost for classification. The proposed hybrid model effectively captures deep features and enhances classification accuracy. Experimental results demonstrate improved performance compared to conventional methods.

his paper presents an efficient and automated system for brain tumor detection using MRI images by integrating transfer learning-based CNN feature extraction with XGBoost classification. The proposed hybrid approach effectively combines the strengths of deep learning and machine learning to improve detection accuracy while reducing computational complexity. The preprocessing techniques ensure that MRI images are standardized and noise-free, enabling better feature extraction. The use of pre-trained CNN models such as VGG16 or ResNet50 allows the system to extract meaningful and high-level features without requiring large training datasets. Furthermore, the XGBoost classifier enhances the prediction performance by efficiently handling structured feature data and minimizing overfitting. Experimental results demonstrate that the proposed system achieves reliable and accurate tumor detection compared to traditional methods. The model provides fast and interpretable results, making it suitable for real-time medical applications. Overall, the system reduces manual effort and supports medical professionals in early diagnosis and decision-making.

[1]Mahmud, M. I., Mamun, M., & Abdelgawad, A. (2023).“A Deep Analysis of Brain Tumor Detection from MR Images Using Deep Learning Networks.” Algorithms, 16(4), 176. [2]Shaik, M.K., Kalpana, D., Sesadri, U., Mukherjee, S., Dastagiraiah, C.and Reddy, P.C.S., 2024, May. Brain Tumor Classification Using UNet Deep Neural Networks from 3D MRI Images. In 2024 International Conference on Electronics, Computing, Communication and Control Technology (ICECCC) (pp. 1-6). IEEE. [3]Avigyan Sinha, Aneesh R P, Malavika Suresh, Nitha Mohan R, AbinayaD, Ashwin G Singerji, “Brain Tumour Detection Using Deep Learning”Seventh International Conference on Bio Signals, Images, and Instrumentation(ICBSII), 2021. [4]Md. Ridwan, Tahsin Tabassum Ali, Sheikh Tanzida Tasmim Erin, Rezaul Karim Tushar,Fuyad Mahmud, and Shahnewaz SiddiqueDepartment of Electrical and Computer EngineeringNorth South University, Dhaka- 1229, Bangladesh. [5]”Brain Tumor MRI Dataset,” IEEE Dataport, [Online]. Available: https://ieeedataport. org/documents/brain-tumormri-dataset. [6]Sejuti, Z. A., & Islam, M. S. (2021).“An Efficient Method to Classify Brain Tumor using CNN and SVM.” International Conference on Robotics, Electrical and Signal Processing Techniques (ICREST), IEEE, pp. 644- 648. [7]A. Younis et al., “Abnormal Brain Tumors Classification Using ResNet50 and Its Comprehensive Evaluation,” IEEE Access, vol. 12, pp. 123456–123467, 2024, doi: 10.1109/ACCESS.2024.3403902. [8]Yuanbing et al. (2021) “An improved authentication protocol for smart healthcare system using wireless medical sensor network,” IEEE Access, vol. 11, pp. 1–12. [9]L. A. Abraham, G. Palanisamy, and V. Goutham, “Dilated Convolutionand YOLOv8 Feature Extraction Network: An Improved Method for MRI-Based Brain Tumor Detection,” IEEE Access, vol. 13, pp. 1–1, 2025, doi: 10.1109/ACCESS.2025.3539924. [11]“Design and Implementing Brain Tumor Detection Using Machine Learning Approach.” IEEE Xplore, 2019. [12]K. Neamah et al., “Utilizing Deep Improved ResNet50 for Brain Tumor Classification Based on MRI,” IEEE Open Journal of theComputerSociety,vol.5,pp.446– 456,2024,doi:10.1109/OJCS.2024.3453924.

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close