Keywords
Transformer model
Image processing
Feature fusion
Feature selection
How to Cite
Abstract
Brain tumors are among the diseases that can seriously threaten human life and can be fatal. Early diagnosis of brain tumors plays a crucial role in the treatment process of the disease. However, accurately and quickly diagnosing this disease remains one of the significant challenges of modern medical technologies. Currently, advanced imaging techniques such as magnetic resonance imaging (MRI) are generally used for detecting brain tumors. This study proposes an artificial intelligence-based diagnostic approach using MRI images that include brain tumor types and consist of four classes. The proposed approach includes preprocessing, model training, feature fusion, and selection as final steps. In the preprocessing step, Grad-CAM and LBP techniques are applied to the original dataset, resulting in a total of three datasets, including the original one. These datasets are then trained with the DeiT3 model to obtain three separate feature sets (original, Grad-CAM-based, LBP-based). The feature sets are fused using a feature fusion technique, and the performance of the combined sets is evaluated using SVM methods. Feature selection methods (Chi2, Relief) are applied to the best-performing Grad-CAM & LBP-based feature set to highlight the most efficient features. Experimental analysis results show that a success rate of 99.5% was achieved using the SVM method.
References
Almohamade, A., Kammoun, S., & Alsolami, F. (2025). Local binary pattern–cycle generative adversarial network transfer: Transforming image style from day to night. Journal of Imaging, 11, 108.
Aslan, E. (2024). Classification of brain tumors from MR images using the LSTM-ESA hybrid model. Adıyaman University Journal of Engineering Sciences, 11, 63–81.
Aslan, M. (2022). Deep learning-based automatic brain tumor detection. Fırat University Journal of Engineering Sciences, 34, 399–407.
Attallah, O. (2025). Multi-domain feature incorporation of lightweight convolutional neural networks and handcrafted features for lung and colon cancer diagnosis. Technologies (Basel), 13, 173.
Aydemir, E. (2022). Speaker recognition and speaker verification by comparing MFCC and LBP methods. Turkish Informatics Foundation Journal of Computer Science and Engineering, 15, 104–109.
Bayaral, S., Gül, E., & Avcı, D. (2025). Classification of brain tumors using artificial intelligence. International Journal of Innovative Engineering Applications, 9, 8–22.
Bhuvaji, S. (2025). Brain tumor classification (MRI). Kaggle dataset, accessed 10/15/2025.
Çelik, Ö., & Koç, B. C. (2021). Classification of Turkish news texts using TF-IDF, Word2Vec, and FastText vector model methods. DEU Faculty of Engineering Science and Engineering, 23, 121–127.
Cheng, J. (2024). Brain tumor dataset. Figshare dataset, accessed 10/15/2025.
Das, D., Sarkar, C., & Das, B. (2025). Real-time detection of meningiomas by image segmentation: A very deep transfer learning convolutional neural network approach. Tomography, 11, 50.
Demirel, C., & Soylu, E. (2024). Comparison of transfer-based deep learning algorithms for tumor detection in MRI data. Black Sea Journal of Science, 14, 1322–1339.
Devi, A. G., et al. (2023). An improved chi² feature selection based on a two-stage prediction of comorbid cancer patient survivability. Revue d’Intelligence Artificielle, 37, 83–92.
Ennab, M., & Mcheick, H. (2025). Advancing AI interpretability in medical imaging: A comparative analysis of pixel-level interpretability and Grad-CAM models. Machine Learning and Knowledge Extraction, 7, 12.
Erçelik, Ç., & Hanbay, K. (2023a). Classification of brain tumors using Gaussian filtering and the ResNet50 model. Computer Science.
Erçelik, Ç., & Hanbay, K. (2023b). Effects of histogram equalization method on some deep learning models in brain tumor classification. Computer Science.
Gómez-Guzmán, M. A., et al. (2023). Classifying brain tumors on magnetic resonance imaging by using convolutional neural networks. Electronics (Basel), 12, 955.
Gür, Y. E., Toğaçar, M., & Solak, B. (2025). Integration of CNN models and machine learning methods in credit score classification: 2D image transformation and feature extraction. Computational Economics, 65, 2991–3035.
Haldar, B., Joardar, H., Mondal, A. K., Alrasheedi, N. H., Khan, R., et al. (2025). Machine-learning-driven analysis of wear loss and frictional behavior in magnesium hybrid composites. Crystals (Basel), 15, 452.
Hamada, A. (2020). Br35h: Brain tumor detection. Kaggle dataset, accessed 10/15/2025.
Kuştası, E., & Yağanoğlu, M. (2024). Classification of variable stars using deep learning and transfer learning methods. Batman University Journal of Life Sciences, 14, 81–97.
Livieris, I. E., Pintelas, E., Kiriakidou, N., & Pintelas, P. (2023). Explainable image similarity: Integrating siamese networks and Grad-CAM. Journal of Imaging, 9, 224.
Nickparvar, M. (2021). Brain tumor MRI dataset. Kaggle dataset, accessed 10/15/2025.
Rahman, S., Mursal, S. N. F., Latif, M. A., Mushtaq, Z., Irfan, M., et al. (2023). Enhancing network intrusion detection using effective stacking of ensemble classifiers with multi-pronged feature selection technique. In 2023 2nd International Conference on Emerging Trends in Electrical, Control, and Telecommunication Engineering (ETECTE) (pp. 1–6). IEEE.
Senjoba, L., Ikeda, H., Toriya, H., Adachi, T., & Kawamura, Y. (2024). Enhancing interpretability in drill bit wear analysis through explainable artificial intelligence: A Grad-CAM approach. Applied Sciences, 14, 3621.
Serttaş, S., & Deniz, E. (2023). Disease detection in bean leaves using deep learning. Communications Faculty of Sciences University of Ankara Series A2–A3 Physical Sciences and Engineering, 65, 115–129.
Sevinç, A., Ucan, M., & Kaya, B. (2025). A distillation approach to transformer-based medical image classification with limited data. Diagnostics, 15, 929.
Taşdemir, B., & Barışçı, N. (2024). Brain tumor segmentation with deep learning. Journal of Information Technologies, 17, 159–174.
Toğaçar, M. (2025). Time-frequency imaging for epilepsy seizure detection: Feature fusion with transformer model. Journal of Engineering Sciences and Research, 7, 93–102.
Tubog, M. V., Emsellem, K., & Bouissou, S. (2025). Detection of agricultural terraces platforms using machine learning from orthophotos and LiDAR-based digital terrain model: A case study in Roya Valley of Southeast France. Land (Basel), 14, 962.
Yang, P., Zhang, R., Hu, C., & Guo, B. (2025). GMDNet: Grouped encoder–mixer–decoder architecture based on the role of modalities for brain tumor MRI image segmentation. Electronics (Basel), 14, 1658.
Yenikaya, M. A., & Oktaysoy, O. (2023). The use of artificial intelligence applications in the healthcare sector: Preliminary diagnosis using deep learning methods. Sakarya University Business Institute Journal, 5, 127–131.
Yılmaz, S. (2023). Design of a decision support system based on the YOLOv7 algorithm for brain tumor diagnosis. Kocaeli University Journal of Science, 6, 47–56.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.