Brain Tumor Detection In MRI Scans Using Hybrid AI Techniques
DOI:
https://doi.org/10.29284/00wyv075Keywords:
Convolutional Neural Networks (CNNs), Magnetic Resonance Image (MRI), Brain Tumor Detection, Support Vector Machines (SVMs), Generative Adversarial Networks (GANs).Abstract
Better patient outcomes result from early diagnosis and treatment planning, which depends on the identification of brain tumors. By fusing deep learning, machine learning, and feature extraction approaches, this study explores the application of hybrid AI techniques for automated tumor diagnosis in MRI scans. The suggested method improves accuracy, robustness, and efficiency by combining conventional machine learning classifiers with convolutional neural networks (CNNs) for feature extraction. The results of the experiment demonstrate how well hybrid AI models distinguish between areas impacted by tumors and healthy tissues, which makes them an important tool for computer-aided diagnosis in medical imaging. In particular, this technique improves classification accuracy by combining Convolutional Neural Networks (CNNs) with Support Vector Machines (SVMs), and incorporates Generative Adversarial Networks (GANs) with Transfer Learning to refine feature representation in limited datasets. Experimental results indicate that these hybrid AI models achieve an average accuracy of 96.18%, demonstrating their potential for early brain cancer detection. The system enhances image quality, applies edge detection, extracts critical features, and leverages a hybrid AI-based training model, significantly improving diagnostic precision and surpassing previous methods.
References
[1] H. A. Shah, F. Saeed, S. Yun, J. H. Park, A. Paul, and J. M. Kang, “A Robust Approach for Brain Tumor Detection in Magnetic Resonance Images Using Finetuned EfficientNet,” IEEE Access, vol. 10, pp. 65426–65438, 2022, doi: 10.1109/ACCESS.2022.3184113.
[2] M. M. Ahmed et al., “Brain tumor detection and classification in MRI using hybrid ViT and GRU model with explainable AI in Southern Bangladesh,” Sci. Rep., vol. 14, no. 1, p. 22797, 2024, doi: 10.1038/s41598-024-71893-3.
[3] M. J. Zubair Rahman et al., “Advanced AI-driven approach for enhanced brain tumor detection from MRI images utilizing EfficientNetB2 with equalization and homomorphic filtering,” BMC Med. Inform. Decis. Mak., vol. 24, no. 1, pp. 1–19, 2024, doi: 10.1186/s12911-024-02519-x.
[4] M. Arabahmadi and R. Farahbakhsh, “Deep Learning for Smart Healthcare: A Survey on Brain Tumor,” Sensors, vol. 22, pp. 1–27, 2022.
[5] Chaplot, S., Patnaik, L. M., & Jagannathan, N. R. (2006). Classification of MRI brain images using wavelets as input to SVM. Biomedical Signal Processing and Control, 1(1), 86-92.
[6] Khan, M. et al. (2021). U-Net-based brain tumor segmentation model. IEEE Transactions on Medical Imaging, 40(8), 2035-2045.
[7] Chaudhary, A. et al. (2022). CNN-SVM hybrid model for brain tumor classification. Journal of AI in Medical Imaging, 12(3), 150-162.
[8] Bhandari, R. et al. (2022). ResNet and EfficientNet for multiclass tumor classification. Medical AI Research Journal, 10(4), 112-125.
[9] Sharma, R. et al. (2023). GAN-based data augmentation for MRI scans. Neural Networks in Medical Imaging, 15(2), 78-90.
[10] Patel, S. et al. (2023). Transfer learning for MRI-based tumor classification. AI in Medical Diagnostics, 18(1), 45-60.
[11] R. Arunarani, V. Bhenia, T. Abirami, N. Aparna, M. Abul Ala Walid, and K. A. Sharada, “An Improved Cuttlefish Optimization Algorithm Based Faster R-CNN for Brain Tumour Detection,” Proc. 4th Int. Conf. Smart Electron. Commun. ICOSEC 2023, pp. 1336–1341, 2023, doi: 10.1109/ICOSEC58147.2023.10276261.
[12] Pashaei, H. Sajedi, and N. Jazayeri, “Brain tumor classification via convolutional neural network and extreme learning machines,” 2018 8th Int. Conf. Comput. Knowl. Eng. ICCKE 2018, no. December, pp. 314–319, 2018, doi: 10.1109/ICCKE.2018.8566571.
[13] R. Saranya, “Image Analysis of MRI - based Brain Tumor Classification and Segmentation using BSA and RELM Networks,” 2023 2nd Int. Conf. Autom. Comput. Renew. Syst., pp. 523–528, 2023, doi: 10.1109/ICACRS58579.2023.10405052.
[14] A. Rehman, S. Naz, M. I. Razzak, F. Akram, and M. Imran, “A Deep Learning-Based Framework for Automatic Brain Tumors Classification Using Transfer Learning,” Circuits, Syst. Signal Process., vol. 39, no. 2, pp. 757–775, 2020, doi: 10.1007/s00034-019-01246-3.
[15] G. Sreelakshmi, S. Arivarasan, S. V. G. V. A. Prasad, N. Saikumari, K. V. Kumari, and A. Vidya, “Improving Brain Stroke Diagnosis with SHAP- Enhanced Predictive Models,” 2024 Int. Conf. Data Sci. Netw. Secur., pp. 1–6, 2024, doi: 10.1109/ICDSNS62112.2024.10691233.
[16] J. Cheng et al., “Enhanced performance of brain tumor classification via tumor region augmentation and partition,” PLoS One, vol. 10, no. 10, pp. 1–13, 2015, doi: 10.1371/journal.pone.0140381.
[17] P. Afshar, K. N. Plataniotis, and A. Mohammadi, “Capsule Networks for Brain Tumor Classification Based on MRI Images and Coarse Tumor Boundaries,” in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2019, pp. 1368–1372. doi: 10.1109/ICASSP.2019.8683759. “Brain Tumor MRI Dataset.” Accessed: Dec. 18, 2024. [Online]. Available: https://www.kaggle.com/datasets/masoudnickparvar/brain-tumor-mri-dataset.
[18] S. Roy, S. Nag, I. K. Maitra, and S. K. Bandyopadhyay, “A Review on Automated Brain Tumor Detection and Segmentation from MRI of Brain,” pp. 1–41, 2013, [Online]. Available: http://arxiv.org/abs/1312.6150
[19] G. Kumar, P. Kumar, and D. Kumar, “Brain Tumor Detection Using Convolutional Neural Network,” 2021 IEEE Int. Conf. Mob. Networks Wirel. Commun. ICMNWC 2021, no. 9, pp. 83–88, 2021, doi: 10.1109/ICMNWC52512.2021.9688460.
[20] K. Sharma, A. Kaur, and S. Gujral, “Brain Tumor Detection based on Machine Learning Algorithms,” Int. J. Comput. Appl., vol. 103, no. 1, pp. 7–11, 2014, doi: 10.5120/18036-6883.
[21] Y. Feng, H. You, Z. Zhang, R. Ji, and Y. Gao, “Hypergraph Neural Networks,” Proc. AAAI Conf. Artif. Intell., vol. 33, pp. 3558–3565, 2019.
[22] P. B. Kanade and P. P. Gumaste, “Brain Tumor Detection Using MRI Images,” Ijireeice, no. February 2015, pp. 146–150, 2015, doi: 10.17148/ijireeice.2015.3231.
[23] Zakeri, Y., Karasfi, B. & Jalalian, A. A Review of Brain Tumor Segmentation Using MRIs from 2019 to 2023 (Statistical Information, Key Achievements, and Limitations). J. Med. Biol. Eng. 44, 155–180 (2024). https://doi.org/10.1007/s40846-024-00860-0.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
