Optimized Lightweight Convolutional Neural Network Architecture for Multi-Class Brain Tumor Classification from Magnetic Resonance Imaging
DOI:
https://doi.org/10.31185/wjps.1001Keywords:
Brain tumor classification, convolutional neural networks, MRI image analysis, deep learning, lightweight architecture, attention mechanisms, medical image processingAbstract
Brain tumor classification from Magnetic Resonance Imaging (MRI) is a vital clinical task in modern neuroradiology that requires high diagnostic accuracy to enable appropriate treatment and prognosis. We propose an optimized deep learning architecture with three architectural novelties—the Micro Adaptive Feature Extractor, Micro Multi-Scale Processor, and Context-Aware Intelligent Pooling—and present the world-lightest ultra-efficient brain tumor classifier. Our optimized model achieves 99.22% classification accuracy on the largest brain tumor MRI dataset to date (Mendeley), comprising 12,064 high-resolution images across 4 tumor classes (glioma, meningioma, pituitary adenoma, no tumor) using only 659,228 trainable parameters. Our system is thoroughly ablated and systemically validated with every architectural novelty validated individually and in combination, intelligent pooling providing the greatest 2.18% accuracy uplift. Our optimized architecture is extensively validated on cross-dataset independent test sets, surpassing domain adaptation baselines and achieving state-of-the-art generalization (Kaggle test: 99.24%, Br35H test: 98.33%). Our system uses 47x fewer parameters than state-of-the-art U-Net approaches while achieving top classification accuracy using only 12ms inference latency and 2.6 MB model size, making our solution perfect for deployment on underpowered mobile medical edge devices. These findings demonstrate that architectural innovation substantially outweighs brute-force parameter accumulation in medical image classification tasks.
References
[1] H. S. Alhakeem, M. A. Badr, M. Almalki, and R. A. Khattab, "3D convolutional neural networks for medical image segmentation," IEEE Transactions on Biomedical Engineering, vol. 69, no. 1, pp. 185-196, 2022.
[2] S. Albawi, T. A. Mohammed, and S. Al-Zawi, "Understanding of a convolutional neural network," in 2018 International Conference on Engineering and Technology (ICET), 2018, pp. 1-6. DOI: https://doi.org/10.1109/ICEngTechnol.2017.8308186
[3] M. A. Al-Masni, M. A. Al-Antari, M. T. Choi, S. M. Han, and T. S. Kim, "Classification of lung nodules in CT scans using three-dimensional deep convolutional neural networks," Journal of Healthcare Engineering, vol. 2017, p. 5652608, 2017.
[4] T. Çinar and M. Yildirim, "Detection of tumors on brain MRI images using the hybrid convolutional neural network architecture," Medical Hypotheses, vol. 139, p. 109684, 2020. DOI: https://doi.org/10.1016/j.mehy.2020.109684
[5] S. Deepak and A. M. Ameer, "Brain tumor classification using deep learning and convolutional neural networks," International Journal of Advances in Scientific Research, vol. 3, no. 9, pp. 37-42, 2016.
[6] F. Chollet, "Xception: Deep learning with depthwise separable convolutions," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 1251-1258. DOI: https://doi.org/10.1109/CVPR.2017.195
[7] J. Cheng, W. Huang, S. Cao, R. Yang, W. Yang, Z. Yun, Z. Wang, and Q. Feng, "Enhanced performance of brain tumor classification with multiscale entropies and support vector machines," Brain Topography, vol. 28, pp. 236-246, 2015.
[8] B. Hariharan, P. Arbeláez, R. Girshick, and J. Malik, "Hypercolumns for object segmentation and fine-grained localization," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 447-456. DOI: https://doi.org/10.1109/CVPR.2015.7298642
[9] G. Huang, Z. Liu, L. van der Maaten, and K. Q. Weinberger, "Densely connected convolutional networks," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 4700-4708. DOI: https://doi.org/10.1109/CVPR.2017.243
[10] A. Işin, C. Direkoğlu, and M. Şah, "Review of MRI-based brain tumor image segmentation using deep learning techniques," Procedia Computer Science, vol. 102, pp. 317-324, 2016. DOI: https://doi.org/10.1016/j.procs.2016.09.407
[11] H. Ö. Iliş, D. Kaya, and E. Kalkan, "Brain tumor classification using improved convolutional neural networks," Computers & Electrical Engineering, vol. 90, p. 107003, 2021.
[12] S. Ioffe and C. Szegedy, "Batch normalization: Accelerating deep network training by reducing internal covariate shift," in International Conference on Machine Learning (ICML), 2015, pp. 448-456.
[13] S. Khan, M. Aamir, M. Balas, M. Biswas, and N. Abdulaziz, "Hybrid deep learning framework for multi-class brain tumor classification using CE-EEN-B0-ResGANet," Medical Image Analysis, vol. 98, p. 103252, 2025.
[14] A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet classification with deep convolutional neural networks," in Advances in Neural Information Processing Systems (NIPS), 2012, pp. 1097-1105.
[15] S. Kumar, M. Singh, P. Kumar, and S. Kumar, "Diagnosis of brain tumors using hybrid deep neural networks," Applied Soft Computing, vol. 123, p. 108955, 2022.
[16] D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," in International Conference on Learning Representations (ICLR), 2015, arXiv:1412.6980.
[17] D. Kingma and M. Welling, "Auto-encoding variational Bayes," in International Conference on Learning Representations (ICLR), 2014, arXiv:1312.6114.
[18] S. Kong, C. C. Fowlkes, and D. Hoiem, "Recurrent scene parsing with perspective understanding in the loop," in European Conference on Computer Vision (ECCV), 2016, pp. 395-412.
[19] G. Litjens, T. Kooi, B. E. Bejnordi, A. A. A. Setio, F. Ciompi, M. Ghafoorian, et al., "A survey on deep learning in medical image analysis," IEEE Transactions on Medical Imaging, vol. 42, no. 4, pp. 860-902, 2021.
[20] J. Long, E. Shelhamer, and T. Darrell, "Fully convolutional networks for semantic segmentation," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 3431-3440. DOI: https://doi.org/10.1109/CVPR.2015.7298965
[21] Y. Qiang, W. Youbing, and C. Yanning, "Multi-scale convolutional neural networks for lung nodule classification," in Information Processing in Medical Imaging, 2016, pp. 588-599. DOI: https://doi.org/10.1007/978-3-319-19992-4_46
[22] T. Loshchilov and F. Hutter, "SGDR: Stochastic gradient descent with warm restarts," in International Conference on Learning Representations (ICLR), 2017, arXiv:1608.03983.
[23] Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp. 436-444, 2015.
[24] A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, et al., "MobileNets: Efficient convolutional neural networks for mobile vision applications," arXiv preprint arXiv:1704.04861, 2017.
[25] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, "Dropout: A simple way to prevent neural networks from overfitting," The Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929-1958, 2014.
[26] N. Srivastava, E. Mansimov, and R. Salakhudinov, "Unsupervised learning of visual representations using videos," in International Conference on Machine Learning (ICML), 2015, pp. 837-845.
[27] A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, et al., "PyTorch: An imperative style, high-performance deep learning library," in Advances in Neural Information Processing Systems (NIPS), 2019, pp. 8024-8035.
[28] R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and B. Batra, "Grad-CAM: Visual explanations from deep networks via gradient-based localization," in IEEE International Conference on Computer Vision (ICCV), 2017, pp. 618-626. DOI: https://doi.org/10.1109/ICCV.2017.74
[29] A. Sadeghi and Y. Zhang, "Convolutional neural networks for automated image analysis in magnetic resonance imaging," Journal of Biomedical Engineering, vol. 38, no. 4, pp. 445-456, 2022.
[30] D. Shen, G. Wu, and H. I. Suk, "Deep learning in medical image analysis," Annual Review of Biomedical Engineering, vol. 19, pp. 221-248, 2017. DOI: https://doi.org/10.1146/annurev-bioeng-071516-044442
[31] J. Feng, H. Xu, S. Mannor, and Y. Yan, "Robust loss minimization under label noise for deep neural networks," arXiv preprint arXiv:1406.2080, 2014.
[32] D. Rumelhart, G. Hinton, and R. Williams, "Learning representations by back-propagating errors," Nature, vol. 323, no. 6088, pp. 533-536, 1986. DOI: https://doi.org/10.1038/323533a0
[33] Y. Gal and Z. Ghahramani, "Dropout as a Bayesian approximation: Representing model uncertainty in deep learning," in International Conference on Machine Learning (ICML), 2016, pp. 1050-1059.
[34] V. Gulshan, L. Peng, G. Coram, M. V. Stumpe, D. Wu, A. Narayanaswamy, et al., "Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs," JAMA, vol. 316, no. 22, pp. 2402-2410, 2016. DOI: https://doi.org/10.1001/jama.2016.17216
[35] Y. Zhou, J. He, and Q. Zou, "Learning efficient convolutional networks through network slimming," in IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2755-2763.
[36] Y. Zhou, Z. Wu, and G. Liu, "Optimizing deep learning for medical image segmentation," IEEE Transactions on Medical Imaging, vol. 39, no. 4, pp. 1234-1245, 2020.
[37] A. Zahoor, S. Khan, K. Malik, A. Ahmed, and S. Ahmad, "Res-BRNet: Residual and region-boundary aware CNN for brain tumor classification," Biomedicines, vol. 12, no. 7, p. 1395, 2024.
[38] T. Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, "Feature pyramid networks for object detection," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 936-944.
[39] T. Fawcett, "An introduction to ROC analysis," Pattern Recognition Letters, vol. 27, no. 8, pp. 861-874, 2006. DOI: https://doi.org/10.1016/j.patrec.2005.10.010
[40] O. Ronneberger, P. Fischer, and T. Brox, "U-Net: Convolutional networks for biomedical image segmentation," in Medical Image Computing and Computer-Assisted Intervention (MICCAI), Springer International Publishing, 2015, pp. 234-241. DOI: https://doi.org/10.1007/978-3-319-24574-4_28
[41] J. Özbay, "Deep learning and multi-class brain tumor classification," International Journal of Advanced Computer Science and Applications, vol. 11, no. 3, pp. 133-139, 2020.
[42] D. Bahdanau, K. Cho, and Y. Bengio, "Neural machine translation by jointly learning to align and translate," in International Conference on Learning Representations (ICLR), 2015, arXiv:1409.0473.
[43] S. Woo, J. Park, J. Y. Lee, and I. S. Kweon, "CBAM: Convolutional block attention module," in European Conference on Computer Vision (ECCV), 2018, pp. 3-19. DOI: https://doi.org/10.1007/978-3-030-01234-2_1
[44] T. Murphy, "Evaluate open source risks," http://www.ftponline.com/wss/2002_10/online/tmurphy/, retrieved, vol. 19, p. 2012, 2001.
[45] M. Ilani, S. Malik, K. Ahmad, and R. Hassan, "U-Net based convolutional neural network on T1-weighted MRI for brain tumor detection," Scientific Reports, vol. 15, p. 2847, 2025.
[46] A. Vaswani, N. Shazeer, P. N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, et al., "Attention is all you need," in Advances in Neural Information Processing Systems (NIPS), 2017, pp. 5998-6008.
[47] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. C. Chen, "MobileNetV2: Inverted residuals and linear bottlenecks," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 4510-4520.
[48] L. Wang, D. Lin, J. Hoi, and W. Yang, "A closer look at few-shot classification," in International Conference on Learning Representations (ICLR), 2020.
[49] D. Spinellis and C. Szyperski, "How is open source affecting software development?," IEEE Software, vol. 21, no. 1, pp. 28-33, 2004. DOI: https://doi.org/10.1109/MS.2004.1259204
[50] Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp. 436-444, 2015. DOI: https://doi.org/10.1038/nature14539
[51] A. Dosovitsky and T. Brox, "Inverting visual representations with convolutional networks," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 4829-4837. DOI: https://doi.org/10.1109/CVPR.2016.522
[52] Y. Gal and Z. Ghahramani, "Dropout as a Bayesian approximation: Representing model uncertainty in deep learning," in International Conference on Machine Learning (ICML), 2016, pp. 1050-1059.
[53] J. Hu, L. Shen, and G. Sun, "Squeeze-and-excitation networks," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 7132-7141. DOI: https://doi.org/10.1109/CVPR.2018.00745
[54] T. Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, "Feature pyramid networks for object detection," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 936-944. DOI: https://doi.org/10.1109/CVPR.2017.106
[55] S. Xie, R. Girshick, P. Dollár, Z. Tu, and K. He, "Aggregated residual transformations for deep neural networks," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 1492-1500. DOI: https://doi.org/10.1109/CVPR.2017.634
[56] A. G. Roy, S. Navab, and C. Wachinger, "Recalibrating fully convolutional networks with spatial and channel 'squeeze and excitation' blocks," IEEE Transactions on Medical Imaging, vol. 38, no. 2, pp. 540-549, 2019. DOI: https://doi.org/10.1109/TMI.2018.2867261
[57] K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770-778. DOI: https://doi.org/10.1109/CVPR.2016.90
[58] T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer, 2009. DOI: https://doi.org/10.1007/978-0-387-84858-7
[59] C. M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006.
[60] A. Zahoor, S. Khan, K. Malik, A. Ahmed, and S. Ahmad, "Res-BRNet: Residual and region-boundary aware CNN for brain tumor classification," Biomedicines, vol. 12, no. 7, p. 1395, 2024. DOI: https://doi.org/10.3390/biomedicines12071395
[61] Y. Zhou, J. He, and Q. Zou, "Learning efficient convolutional networks through network slimming," in IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2755-2763. DOI: https://doi.org/10.1109/ICCV.2017.298
[62] Y. Zhou, Z. Wu, and G. Liu, "Optimizing deep learning for medical image segmentation," IEEE Transactions on Medical Imaging, vol. 39, no. 4, pp. 1234-1245, 2020.
[63] M. Tan and Q. V. Le, "EfficientNet: Rethinking model scaling for convolutional neural networks," in International Conference on Machine Learning (ICML), 2019, pp. 6105-6114.
[64] A. Vaswani, N. Shazeer, P. N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, et al., "Attention is all you need," in Advances in Neural Information Processing Systems (NIPS), 2017, pp. 5998-6008.
[65] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. C. Chen, "MobileNetV2: Inverted residuals and linear bottlenecks," in IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 4510-4520. DOI: https://doi.org/10.1109/CVPR.2018.00474
[66] J. Feng, H. Xu, S. Mannor, and Y. Yan, "Robust loss minimization under label noise for deep neural networks," arXiv preprint arXiv:1406.2080, 2014.
[67] M. Ilani, S. Malik, K. Ahmad, and R. Hassan, "U-Net based convolutional neural network on T1-weighted MRI for brain tumor detection," Scientific Reports, vol. 15, p. 2847, 2025. DOI: https://doi.org/10.1038/s41598-025-92020-w
[68] S. Khan, M. Aamir, M. Balas, M. Biswas, and N. Abdulaziz, "Hybrid deep learning framework for multi-class brain tumor classification using CE-EEN-B0-ResGANet," Medical Image Analysis, vol. 98, p. 103252, 2025.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Mahmoud Shamran, Baraa I. Farhan
This work is licensed under a Creative Commons Attribution 4.0 International License.
