Brain Lesion Classification With Effincepresv2: A Hybrid Approach Combining Efficientnetv2 And Inception-Resnetv2
DOI:
https://doi.org/10.52783/jns.v14.3472Keywords:
Brain Lesion, Magnetic Resonance Imaging (MRI), Convolutional Neural Networks (CNN), EfficientNetV2, Inception-ResNetV2, EffIncepResV2, Tumor Classification, Deep LearningAbstract
Brain lesion, whether benign or malignant, present significant health risks, making early and precise detection critical for effective treatment. This study explores the use of deep learning for brain lesion classification through MRI imaging, leveraging EfficientNetV2, Inception-ResNetV2, and a hybrid model combining the strengths of both architectures. The dataset comprises MRI scans from patients with gliomas, meningiomas, pituitary tumors, and no-tumors. Pre-processing methods like Channel Standardization, Gaussian blurring, and filtering are used to improve image quality, and data augmentation guarantees that the models will generalize more effectively. Traditional convolutional neural networks (CNNs) are improved by EfficientNetV2 using fused-MBConv layers for increased efficiency, squeeze-and-excitation blocks for adaptive feature scaling, and a progressive training approach that improves accuracy and speed. Inception-ResNetV2, on the other hand, combines ResNet's skip connections with Inception modules for multi-scale feature extraction, enhancing gradient flow and increasing performance on big datasets. The proposed hybrid model EffIncepResV2 maximizes classification accuracy while preserving computational efficiency by combining the efficiency of EfficientNetV2 with the feature extraction capabilities of Inception-ResNetV2.This method is very useful for medical imaging applications since it improves feature extraction and fortifies generalization. The results demonstrate how hybrid deep learning techniques can greatly enhance the classification of brain tumors, ultimately promoting early diagnosis and improved patient outcomes.
With an accuracy of 99.94%, precision of 99.65%, recall of 99.89%, F1-score of 99.65, and dice-coefficient of 99%, the results show that EffIncepResV2 performs better than other models. These encouraging findings demonstrate how well EffIncepResV2 can identify brain tumors from MRI pictures, making it a useful diagnostic tool
Downloads
Metrics
References
] Biswas, A., & Islam, M. S. (2023). A hybrid deep CNN-SVM approach for brain tumor classifi-cation. Journal of Information Systems Engineering and Business Intelligence, 9(1), 1-15. https://doi.org/10.20473/jisebi.9.1.1-15
Kesav N., Jibukumar M. Efficient and low complex architecture for detection and classification of Brain Tumor using RCNN with Two Channel CNN. J. King Saud Univ.-Comput. 2022.
Asiri, A. A., Soomro, T. A., Shah, A. A., Pogrebna, G., Irfan, M., & Alqahtani, S. (2024). Opti-mized brain tumor detection: A dual-module approach for MRI image enhancement and tumor classification. IEEE Access, 12, 42868–42884. https://doi.org/10.1109/ACCESS.2024.3379136
Raza, A., Ayub, H., Khan, J. A., Ahmad, I., Salama, A. S., Daradkeh, Y. I., Javeed, D., Ur Rehman, A., & Hamam, H. (2022). A hybrid deep learning-based approach for brain tumor classi-fication. Electronics, 11(1146). https://doi.org/10.3390/electronics11071146
Kokkalla S., Kakarla J., Venkateswarlu I.B., Singh M. Three- class brain tumor classification us-ing deep dense inception residual network. Soft Comput. 2021.
G. Kumar, P. Kumar and D. Kumar, "Brain tumor detection using convolutional neural network", Proc. IEEE Int. Conf. Mobile Netw. Wireless Commun. (ICMNWC), pp. 1-6, Dec. 2021.
Özlem P., Güngen C. Classification of brain tumors from MR images using deep transfer learn-ing. J. Supercomput. 2021.
Singh, R., Gupta, S., Bharany, S., Almogren, A., Altameem, A., & Rehman, A. U. (2024). En-semble deep learning models for enhanced brain tumor classification by leveraging ResNet50 and EfficientNet-B7 on high-resolution MRI images. IEEE Access. https://doi.org/10.1109/ACCESS.2024.3494232
Ayadi W., Charfi I., Elhamzi W., Atri M. Brain tumor classification based on a hybrid approach. Vis. Comput. 2020.
Khan M.A., Ashraf I., Alhaisoni M., Damaševičius R., Scherer R., Rehman A., Bukhari S.A.C. Multimodal Brain Tumor Classification Using Deep Learning and Robust Feature Selection: A Machine Learning Application for Radiologists. Diagnostics. 2020.
Seetha, J. & Selvakumar Raja, S. (2018), "Brain Tumor Classification Using Convolutional Neural Networks," Biomedical and Pharmacology Journal.
Preetha, R., Priyadarsini, M. J. P., & Nisha, J. S. (2024). Automated brain tumor detection from magnetic resonance images using fine-tuned EfficientNet-B4 convolutional neural net-work. IEEE Access, 12, 112181–112195. https://doi.org/10.1109/ACCESS.2024.3442979
G. Raut, A. Raut, J. Bhagade, J. Bhagade and S. Gavhane, "Deep learning approach for brain tumor detection and segmentation," Proc. Int. Conf. Convergence of Digital World Quo Va-dis (ICCDW), Feb. 2020, pp. 1-5.
Praveen, G. B., & Agrawal, A. (2015). Hybrid approach for brain tumor detection and classi-fication in magnetic resonance images. 2015 International Conference on Communication, Control and Intelligent Systems (CCIS). IEEE. https://doi.org/10.1109/CCIS.2015.1234567
Shah, H. A., Saeed, F., Yun, S., Park, J.-H., Paul, A., & Kang, J.-M. (2022). “A Robust Ap-proach for Brain Tumor Detection in Magnetic Resonance Images Using Finetuned Effi-cientNet” IEEE Access, 10, 65426–65438 https://doi.org/10.1109/ACCESS.2022.3184113
Haitham Alsaif, Ramzi Guesmi, Badr M Alshammari, Tarek Hamrouni, Tawfik Guesmi, Ah-med Alzamil, and Lamia Belguesmi. "A novel data augmentation-based brain tumor detection using convolutional neural network."
Louis D.N., Perry A., Reifenberger G., Von Deimling A., Figarella-Branger D., Cavenee W.K., Ohgaki H., Wiestler O.D., Kleihues P., Ellison D.W., "The 2016 World Health Organi-zation classification of tumors of the central nervous system."
C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, et al., "Going deeper with convolutions," Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Jun. 2015,pp. 1-9.
Jin KH, McCann MT, Froustey E, Unser M (2017), "Deep convolutional neural network for inverse problems in imaging," Pattern Recognition (CVPR), Jun. 2016, pp. 770-778.
Adamu, M. J., Kawuwa, H. B., Qiang, L., Nyatega, C. O., Younis, A., Fahad, M., & Dauya, S. S. (2024). Efficient and accurate brain tumor classification using hybrid MobileNetV2–Support Vector Machine for magnetic resonance imaging diagnostics in neoplasms. Brain Sci-ences, 14(1178). https://doi.org/10.3390/brainsci14121178
Alqudah, Ali Mohammad, et al. "Brain tumor classification using deep learning technique--a comparison between cropped, uncropped, and segmented lesion images with different sizes." arXiv preprint arXiv:2001.08844 (2020).
Saeedi, Soheila, et al. "MRI-based brain tumor detection using convolutional deep learning methods and chosen machine learning techniques." BMC Medical Informatics and Decision Making 23.1 (2023): 16.
Usman, Khalid, and Kashif Rajpoot. "Brain tumor classification from multi-modality MRI us-ing wavelets and machine learning." Pattern Analysis and Applications 20 (2017): 871-881.
Nguyen, L. D., Lin, D., Lin, Z., & Cao, J. “Deep CNNs for microscopic image classification by exploiting transfer learning and feature concatenation.” In 2018 IEEE International Sym-posium on Circuits and Systems (ISCAS) (pp. 1–5). IEEE. https://doi.org/10.1109/ISCAS.2018.8351550
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
