Hybrid Artificial Intelligence for Brain Tumor Classification Using MRI Images
Article Sidebar
Main Article Content
Abstract
Accurate classification of brain tumors from magnetic resonance images is essential for supporting clinical assessment, although variations in tumor morphology, anatomical location, image orientation, and visual similarity among diagnostic categories can limit the effectiveness of conventional deep learning models. This study proposes a hybrid learning framework that integrates local structural information, global contextual relationships, and frequency domain characteristics for four class brain tumor classification. The model combines an ImageNet pretrained ConvNeXt Tiny branch for local feature extraction, a Swin Transformer Tiny branch for hierarchical contextual representation, and a wavelet convolutional neural network branch based on two level Haar decomposition. The resulting branch features are aligned within a shared representation space and integrated through bidirectional cross attention and adaptive gated fusion before classification. A dataset containing 10,464 brain magnetic resonance images was evaluated at the individual image level, including 2,726 glioma, 2,737 meningioma, 2,300 no tumor, and 2,701 pituitary tumor images. The dataset was divided into 9,417 training images, 653 validation images, and 394 independent testing images. Brain contour cropping, contrast limited adaptive histogram equalization, normalization, and controlled augmentation were applied during preprocessing. On the independent test set, the proposed model correctly classified 389 of 394 images, achieving an accuracy of 98.73% with a 95% confidence interval from 97.06% to 99.46%. It further obtained a macro precision of 98.84%, macro recall of 98.82%, macro F1 score of 98.82%, macro specificity of 99.56%, Matthews correlation coefficient of 0.9830, and macro area under the receiver operating characteristic curve of 0.9995. The proposed framework outperformed the strongest individual backbone, Swin Transformer Tiny, which achieved 96.45% accuracy and a macro F1 score of 96.63%. These findings indicate that coordinated integration of spatial, contextual, and frequency information can improve image level brain tumor classification. However, the absence of patient identifiers and magnetic resonance sequence metadata limits patient level interpretation and sequence specific analysis.
Article Details
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
References
[1] Sharma, A. K., Nandal, A., Dhaka, A., Zhou, L., Alhudhaif, A., Alenezi, F., & Polat, K. (2023). Brain tumor classification using the modified ResNet50 model based on transfer learning. Biomedical Signal Processing and Control, 86, 105299.
[2] Manik, M. M. T. G. (2021). Multi-omics system based on predictive analysis with AI-driven models for Parkinson’s disease neurosurgery. Journal of Medical and Health Studies, 2(1), 42–52. https://doi.org/10.32996/jmhs.2021.2.1.5
[3] Ge, C., Gu, I. Y. H., Jakola, A. S., & Yang, J. (2020). Deep semi-supervised learning for brain tumor classification. BMC Medical Imaging, 20(1), 87.
[4] Chowdhury, M. S. I., Chy, K. S., Islam, M. A., & Chowdhury, M. N. I. (2023). Integrating blockchain and data analytics to strengthen financial traceability and anti-fraud controls. Journal of Computer Science and Technology Studies, 5(3), 189–202. https://doi.org/10.32996/jcsts.2023.5.3.14
[5] Noreen, N., Palaniappan, S., Qayyum, A., Ahmad, I., & Alassafi, M. O. (2021). Brain tumor classification based on fine-tuned models and the ensemble method. Computers, Materials and Continua, 67(3), 3967–3982.
[6] Manik, M. M. T. G., Bhuiyan, M. M. R., Moniruzzaman, M., Islam, M. S., Hossain, S., & Hossain, S. (2018). The future of drug discovery utilizing generative AI and big data analytics for accelerating pharmaceutical innovations. Nanotechnology Perceptions, 14(3), 120–135. https://doi.org/10.62441/nano-ntp.v14i3.4766
[7] Xie, Y., Zaccagna, F., Rundo, L., Testa, C., Agati, R., Lodi, R., Manners, D. N., & Tonon, C. (2022). Convolutional neural network techniques for brain tumor classification from 2015 to 2022: Review, challenges, and future perspectives. Diagnostics, 12(8), 1850.
[8] Chowdhury, M. N. I., Chy, K. S., Chowdhury, M. S. I., & Islam, M. A. (2021). Identifying hidden fraud indicators through longitudinal analysis of U.S. financial misconduct. Journal of Economics, Finance and Accounting Studies, 3(1), 89–99. https://doi.org/10.32996/jefas.2021.3.1.9
[9] Md Abedur Rahman, Md Anwar Hossain, Kallol Chakraborty Shekhor, & Md Sahid Hossain. (2024). A Conditional Positional Encoding and Channel Attention Guided Swin Transformer for Breast Cancer Classification Using MRI and Mammography. Journal of Computer Science and Technology Studies, 6(3), 193-218. https://doi.org/10.32996/jcsts.2024.6.3.16
[11] Abd El Kader, I., Xu, G., Shuai, Z., Saminu, S., Javaid, I., & Ahmad, I. S. (2021). Differential deep convolutional neural network model for brain tumor classification. Brain Sciences, 11(3), 352.
[12] Chy, K. S., Islam, M. A., Chowdhury, M. S. I., Chowdhury, M. N. I., & Islam, M. A. (2022). Enhancing U.S. financial compliance and risk management through data-driven automation and anomaly detection. Journal of Business and Management Studies, 4(3), 231–244. https://doi.org/10.32996/jbms.2022.4.3.22
[13] Park, J. W., Lee, K., Kim, E. E., Kim, S. I., & Park, S. H. (2023). Brain tumor classification by methylation profile. Journal of Korean Medical Science, 38(43).
[14] Manik, M. M. T. G. (2020). Biotech-driven innovation in drug discovery: Strategic models for competitive advantage in the global pharmaceutical market. Journal of Computational Analysis and Applications, 28(6), 41–47. https://eudoxuspress.com/index.php/pub/article/view/2874
[15] Mushtaq, U. (2020). Brain tumor classification in MRI image using convolutional neural network. Mathematical Biosciences and Engineering.
[16] Manik, M. M. T. G., Hossain, S., Ahmed, M. K., Rozario, E., Miah, M. A., Moniruzzaman, M., et al. (2022). Integrating genomic data and machine learning to advance precision oncology and targeted cancer therapies. Nanotechnology Perceptions, 18(2), 219–243. https://doi.org/10.62441/nano-ntp.v18i2.5443
[17] Shaik, N. S., & Cherukuri, T. K. (2022). Multi-level attention network: Application to brain tumor classification. Signal, Image and Video Processing, 16(3), 817–824.
[18] Kumar, S., & Mankame, D. P. (2020). Optimization-driven deep convolutional neural network for brain tumor classification. Biocybernetics and Biomedical Engineering, 40(3), 1190–1204.
[19] Neamah, K., Mohamed, F., Adnan, M. M., Saba, T., Bahaj, S. A., Kadhim, K. A., & Khan, A. R. (2023). Brain tumor classification and detection based on deep learning models: A systematic review. IEEE Access, 12, 2517–2542.
[20] Manik, M. M. T. G. (2022). An analysis of cervical cancer using the application of AI and machine learning. Journal of Medical and Health Studies, 3(2), 67–76. https://doi.org/10.32996/jmhs.2022.3.2.11
[21] Waghmare, V. K., & Kolekar, M. H. (2020). Brain tumor classification using deep learning. In Internet of Things for Healthcare Technologies (pp. 155–175). Springer Singapore.
[22] Manik, M. M. T. G., Moniruzzaman, M., Islam, M. S., Bhuiyan, M. M. R., Rozario, E., Hossain, S., et al. (2020). The role of big data in combatting antibiotic resistance: Predictive models for global surveillance. Nanotechnology Perceptions, 16(3), 361–378. https://doi.org/10.62441/nano-ntp.v16i3.5445
[23] M. J. van den Bent, M. Weller, P. Y. Wen, J. M. Kros, K. Aldape, and S. Chang, “A clinical perspective on the 2016 WHO brain tumor classification and routine molecular diagnostics,” Neuro-Oncology, vol. 19, no. 5, pp. 614–624, 2017. https://doi.org/10.1093/neuonc/now277
[24] M. M. T. G. Manik, A. S. M. Saimon, M. A. Miah, M. K. Ahmed, F. B. Khair, M. Moniruzzaman, et al., “Leveraging AI-powered predictive analytics for early detection of chronic diseases: A data-driven approach to personalized medicine,” Nanotechnology Perceptions, vol. 17, no. 3, pp. 269–288, 2021. https://doi.org/10.62441/nano-ntp.v17i3.5444
[25] M. A. Miah, E. Rozario, F. B. Khair, M. K. Ahmed, M. M. R. Bhuiyan, and M. M. T. G. Manik, “Harnessing wearable health data and deep learning algorithms for real-time cardiovascular disease monitoring and prevention,” Nanotechnology Perceptions, vol. 15, no. 3, pp. 326–349, 2019.
[26] M. I. Faruk, T. Roy, M. J. Hossain, M. Adnan, E. Hossain, M. H. Rijvi, M. M. Bakhsh, and S. M. M. Uddin, “Global health intelligence platforms: Data science infrastructure for real-time epidemiological surveillance and pandemic forecasting,” Spectrum of Engineering Sciences, vol. 2, no. 5, pp. 749–761, 2024.
[27] J. Cheng, W. Huang, S. Cao, R. Yang, W. Yang, Z. Yun, Z. Wang, and Q. Feng, “Enhanced performance of brain tumor classification via tumor region augmentation and partition,” PLOS ONE, vol. 10, no. 10, article e0140381, 2015. https://doi.org/10.1371/journal.pone.0140381
[28] M. R. Ismael and I. Abdel-Qader, “Brain tumor classification via statistical features and back-propagation neural network,” in Proceedings of the 2018 IEEE International Conference on Electro/Information Technology, Rochester, Michigan, USA, 2018, pp. 252–257. https://doi.org/10.1109/EIT.2018.8500308
[29] J. Amin, M. Sharif, M. Raza, T. Saba, and A. Rehman, “Brain tumor classification: Feature fusion,” in Proceedings of the 2019 International Conference on Computer and Information Sciences, Sakaka, Saudi Arabia, 2019, pp. 1–6. https://doi.org/10.1109/ICCISci.2019.8716449
[30] A. Ari and D. Hanbay, “Deep learning based brain tumor classification and detection system,” Turkish Journal of Electrical Engineering and Computer Sciences, vol. 26, no. 5, pp. 2275–2286, 2018. https://doi.org/10.3906/elk-1801-8
[31] J. S. Paul, A. J. Plassard, B. A. Landman, and D. Fabbri, “Deep learning for brain tumor classification,” in Medical Imaging 2017: Biomedical Applications in Molecular, Structural, and Functional Imaging, Proceedings of SPIE, vol. 10137, article 1013710, 2017. https://doi.org/10.1117/12.2254195
[32] J. Seetha and S. Selvakumar Raja, “Brain tumor classification using convolutional neural networks,” Biomedical and Pharmacology Journal, vol. 11, no. 3, pp. 1457–1461, 2018. https://doi.org/10.13005/bpj/1511
[33] N. Abiwinanda, M. Hanif, S. T. Hesaputra, A. Handayani, and T. R. Mengko, “Brain tumor classification using convolutional neural network,” in World Congress on Medical Physics and Biomedical Engineering 2018, IFMBE Proceedings, vol. 68/1, Singapore: Springer, 2019, pp. 183–189. https://doi.org/10.1007/978-981-10-9035-6_33
[34] S. I. Nilima, M. A. Hossain, S. Sharmin, R. Rahman, H. Esa, M. M. T. G. Manik, and R. Hasan, “Advancement of drug discovery using artificial intelligence and machine learning,” in Proceedings of the 2024 IEEE International Conference on Computing, Applications and Systems, Cox’s Bazar, Bangladesh, 2024, pp. 1–7. https://doi.org/10.1109/COMPAS60761.2024.10796748
[35] S. Deepak and P. M. Ameer, “Brain tumor classification using deep CNN features via transfer learning,” Computers in Biology and Medicine, vol. 111, article 103345, 2019. https://doi.org/10.1016/j.compbiomed.2019.103345
[36] Z. N. K. Swati, Q. Zhao, M. Kabir, F. Ali, Z. Ali, S. Ahmed, and J. Lu, “Brain tumor classification for MR images using transfer learning and fine-tuning,” Computerized Medical Imaging and Graphics, vol. 75, pp. 34–46, 2019.
[37] A. Raza, H. Ayub, J. A. Khan, I. Ahmad, A. S. Salama, Y. I. Daradkeh, D. Javeed, A. U. Rehman, and H. Hamam, “A hybrid deep learning-based approach for brain tumor classification,” Electronics, vol. 11, no. 7, article 1146, 2022. https://doi.org/10.3390/electronics11071146
[38] D. R. Nayak, N. Padhy, P. K. Mallick, M. Zymbler, and S. Kumar, “Brain tumor classification using dense EfficientNet,” Axioms, vol. 11, no. 1, article 34, 2022. https://doi.org/10.3390/axioms11010034
[39] M. H. Rahman, M. E. Hossin, M. J. Hossain, S. M. M. Uddin, M. I. Faruk, M. M. Anwar, and F. Hossain, “Harnessing big data and predictive analytics for early detection and cost optimization in cancer care,” Journal of Computer Science and Technology Studies, vol. 6, no. 5, pp. 278–293, 2024. https://doi.org/10.32996/jcsts.2024.6.5.22
[40] G. A. Amran, M. S. Alsharam, A. O. A. Blajam, A. A. Hasan, M. Y. Alfaifi, M. H. Amran, A. Gumaei, and S. M. Eldin, “Brain tumor classification and detection using hybrid deep tumor network,” Electronics, vol. 11, no. 21, article 3457, 2022. https://doi.org/10.3390/electronics11213457
[41] S. Kumar, S. Choudhary, A. Jain, K. Singh, A. Ahmadian, and M. Y. Bajuri, “Brain tumor classification using deep neural network and transfer learning,” Brain Topography, vol. 36, no. 3, pp. 305–318, 2023. https://doi.org/10.1007/s10548-023-00953-0
[42] M. M. Islam, M. A. Talukder, M. A. Uddin, A. Akhter, and M. Khalid, “BrainNet: Precision brain tumor classification with optimized EfficientNet architecture,” International Journal of Intelligent Systems, vol. 2024, article 3583612, 2024. https://doi.org/10.1155/2024/3583612
[43] S. Hossain, M. M. R. Bhuiyan, M. S. Islam, M. Moniruzzaman, M. K. Ahmed, N. Das, A. S. M. Saimon, and M. M. T. G. Manik, “Big data analysis and prediction of COVID-2019 epidemic using machine learning models in healthcare sector,” Journal of Ecohumanism, vol. 3, no. 8, 2024. https://doi.org/10.62754/joe.v3i8.6775
[44] Hossain, Md Sahid, Kallol Chakraborty Shekhor, Md Anwar Hossain, and Md Abedur Rahman. "Diagnosis Everywhere: Lightweight AI That Detects Disease from Scans and Records on Limited Hospital Hardware." Frontiers in Computer Science and Artificial Intelligence 2: 82-94.
[45] Shekhor, K. C., Hossain, M. S., Rahman, M. A., & Hossain, M. A. Multi-Scale Attention-Fusion Classification with an LLM-Driven Clinical Recommendation Assistant for Brain Tumor MRI. Journal of Medical and Health Studies, 4, 121-39.