Cutting Edge Deep Learning Models for Brain Tumor Classification

Abstract

Accurate differentiation of brain tumor types is essential for effective treatment planning, yet manual interpretation of MRI scans is labor-intensive and prone to variability. This study presents a systematic benchmark of ten state-of-the-art deep learning models for automated brain tumor classification using a public dataset of 3,064 contrast-enhanced MRI scans covering glioma, meningioma, and pituitary tumors. Five advanced Convolutional Neural Networks (CNNs), including Inception v4 and ConvNeXt, are directly compared against five Vision Transformer (ViT) architectures, such as Swin-Base and PiT-Base. Models were evaluated under a unified framework with transfer learning, data augmentation, and macro-averaged metrics (accuracy, precision, recall, F1-score). Results show that Inception v4 achieved the highest accuracy (96.73%) among CNNs, while PiT-Base attained a competitive accuracy of 96.41% with fewer parameters, highlighting the trade-off between multi-scale convolutional processing and efficient transformer designs. Explainable AI analysis with Grad-CAM confirmed that models consistently focused on clinically relevant tumor regions, enhancing interpretability. The findings underscore that both CNNs and ViTs can reach near-expert diagnostic performance, with architectural efficiency rather than parameter count being the decisive factor.

Keywords

• Deep learning
• Magnetic resonance
• Brain tumor classification
• Convolutional neural networks
• Vision transformers

References

1. [1] Verma, A. and Yadav, A.K., “Brain tumor segmentation with deep learning: Current approaches and future perspectives”, Journal of Neuroscience Methods, 110424, (2025). DOI: https://doi.org/10.1016/j.jneumeth.2025.110424
2. [2] Louis, D.N., Perry, A., Wesseling, P., Brat, D.J., Cree, I.A., Figarella-Branger, D., Hawkins, C., Ng, H.K., Pfister, S. M., Reifenberger, G., Soffietti, R., von Deimling, A. and Ellison, D.W., “The 2021 WHO classification of tumors of the central nervous system: a summary”, Neuro-Oncology, 23(8): 1231–1251, (2021). DOI: https://doi.org/10.1093/neuonc/noab106
3. [3] Siegel, R.L., Kratzer, T.B., Giaquinto, A.N., Sung, H. and Jemal, A., “Cancer statistics”, 2025. A Cancer Journal for Clinicians, 75(1): 10, (2025). DOI: https://doi.org/10.3322/caac.218721
4. [4] Waizman, E., Dudnik, E., Lavie, M., Urban, D., Maly, B., Bar, J. and Onn, A., “The impact of brain MRI screening on stage IV NSCLC patients: A real world look at guidelines based care”, Journal of the Neurological Sciences, 470: 123398, (2025). DOI: https://doi.org/10.1016/j.jns.2025.123398
5. [5] Gulshan, V., Peng, L., Coram, M., Stumpe, M.C., Wu, D., Narayanaswamy, A., Venugopalan, S., Widner, K., Madams, T., Cuadros, J., Kim, R., Raman, R., Nelson, P.C., Mega, J.L. and Webster, D. R., “Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs”, Journal of the American Medical Association, 316(22): 2402–2410, (2016). DOI: https://doi.org/10.1001/jama.2016.17216
6. [6] Ardila, D., Kiraly, A.P., Bharadwaj, S., Choi, B., Reicher, J.J., Peng, L., Tse, D., Etemadi, M., Ye, W., Corrado, G., Naidich, D. P. and Shetty, S., “End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography”, Nature Medicine, 25(6): 954–961, (2019). DOI: https://doi.org/10.1038/s41591-019-0447-x
7. [7] Ince, S., Kunduracioglu, I., Algarni, A., Bayram, B. and Pacal, I., “Deep learning for cerebral vascular occlusion segmentation: A novel ConvNeXtV2 and GRN-integrated U-Net framework for diffusion-weighted imaging”, Neuroscience, 574: 42-53, (2025). DOI: https://doi.org/10.1016/j.neuroscience.2025.04.010
8. [8] Ozdemir, B., Sermet, F. and Pacal, I., “Attention-enhanced ConvNeXt for accurate, efficient, and interpretable crack detection”, Expert Systems with Applications, 129165, (2025). DOI: https://doi.org/10.1016/j.eswa.2024.129165

9. [9] Pacal, I., Kilicarslan, S., Ozdemir, B., Deveci, M. and Kadry, S., “Efficient and autonomous detection of olive leaf diseases using AI-enhanced MetaFormer”, Artificial Intelligence Review, 58(10): 303, (2025). DOI: https://doi.org/10.1007/s10462-025-11131-y
10. [10] Alpsalaz, F., Özüpak, Y., Aslan, E. and Uzel, H., “Classification of maize leaf diseases with deep learning: Performance evaluation of the proposed model and use of explicable artificial intelligence”, Chemometrics and Intelligent Laboratory Systems, 105412, (2025). DOI: https://doi.org/10.1016/j.chemolab.2025.105412
11. [11] Özüpak, Y., Alpsalaz, F. and Aslan, E., “Air Quality Forecasting Using Machine Learning: Comparative Analysis and Ensemble Strategies for Enhanced Prediction”, Water, Air, & Soil Pollution, 236(7): 464, (2025). DOI: https://doi.org/10.1007/s11270-025-08122-8
12. [12] Pacal, I. and Attallah, O., “InceptionNeXt-Transformer: A novel multi-scale deep feature learning architecture for multimodal breast cancer diagnosis”, Biomedical Signal Processing and Control, 110: 108116, (2025). DOI: https://doi.org/10.1016/j.bspc.2025.108116
13. [13] Aruk, I., Pacal, I. and Toprak, A.N., “A novel hybrid ConvNeXt-based approach for enhanced skin lesion classification”, Expert Systems with Applications”, 127721, (2025). DOI: https://doi.org/10.1016/j.eswa.2024.127721
14. [14] Pacal, I. and Attallah, O., “Hybrid deep learning model for automated colorectal cancer detection using local and global feature extraction”, Knowledge-Based Systems, 113625, (2025). DOI: https://doi.org/10.1016/j.knosys.2025.113625
15. [15] Pacal, I., Akhan, O., Deveci, R.T. and Deveci, M., “NeXtBrain: Combining local and global feature learning for brain tumor classification”, Brain Research, 149762, (2025). DOI: https://doi.org/10.1016/j.brainres.2025.149762
16. [16] Aslan, E. and Özüpak, Y., “Comparison of machine learning algorithms for automatic prediction of Alzheimer disease”, Journal of the Chinese Medical Association, 88(2): 98-107, (2025). DOI: https://doi.org/10.1097/JCMA.0000000000001188
17. [17] Martucci, M., Russo, R., Schimperna, F., Santoni, M., Panzuto, F. and Cagini, L., “Magnetic resonance imaging of primary adult brain tumors: state of the art and future perspectives”, Biomedicines, 11(2): 364, (2023). DOI: https://doi.org/10.3390/biomedicines11020364
18. [18] Abdusalomov, A.B., Mukhiddinov, M. and Whangbo, T.K., “Brain tumor detection based on deep learning approaches and magnetic resonance imaging”, Cancers, 15(16): 4172, (2023). DOI: https://doi.org/10.3390/cancers15164172
19. [19] Aslan, E., Özüpak, Y., Alpsalaz, F. and Elbarbary, Z.M., “A Hybrid Machine Learning Approach for Predicting Power Transformer Failures Using Internet of Things Based Monitoring and Explainable Artificial Intelligence”, IEEE Access, (2025). DOI: https://doi.org/10.1109/ACCESS.2025.3496033
20. [20] Rasool, N. and Bhat, J.I., “Brain tumour detection using machine and deep learning: a systematic review”, Multimedia Tools and Applications, 84(13): 11551-11604, (2025). DOI: https://doi.org/10.1007/s11042-024-17793-1
21. [21] Musthafa, N., Memon, Q.A. and Masud, M.M., “Advancing Brain Tumor Analysis: Current Trends, Key Challenges, and Perspectives in Deep Learning-Based Brain MRI Tumor Diagnosis”, Engineering, 6(5): 82, (2025). DOI: https://doi.org/10.3390/eng6050082
22. [22] Park, S. and Kim, J., “Explainability of deep neural networks for brain tumor detection”, arXiv preprint arXiv:2410.07613, (2024). DOI: https://doi.org/10.48550/arXiv.2410.07613
23. [23] Zhang, D., Huang, G., Zhang, Q., Han, J., Han, J. and Yu, Y., “Cross-modality deep feature learning for brain tumor segmentation”, Pattern Recognition, 110: 107562, (2021). DOI: https://doi.org/10.1016/j.patcog.2020.107562
24. [24] Nassar, S.E., Yasser, I., Amer, H.M. and Mohamed, M. A., “A robust MRI-based brain tumor classification via a hybrid deep learning technique”, The Journal of Supercomputing, 80(2): 2403-2427, (2024). DOI: https://doi.org/10.1007/s11227-023-05703-x
25. [25] Ullah, M.S., Khan, M.A., Masood, A., Kadry, S. and Rajinikanth, V., “Brain tumor classification from MRI scans: a framework of hybrid deep learning model with Bayesian optimization and quantum theory-based marine predator algorithm”, Frontiers in Oncology, 14: 1335740, (2024). DOI: https://doi.org/10.3389/fonc.2024.1335740
26. [26] Wang, J., Lu, S.Y., Wang, S.H. and Zhang, Y.D., “RanMerFormer: Randomized vision transformer with token merging for brain tumor classification”, Neurocomputing, 573: 127216, (2024). DOI: https://doi.org/10.1016/j.neucom.2024.127216
27. [27] Şahin, E., Özdemir, D. and Temurtaş, H., “Multi-objective optimization of ViT architecture for efficient brain tumor classification”, Biomedical Signal Processing and Control, 91: 105938, (2024). DOI: https://doi.org/10.1016/j.bspc.2024.105938
28. [28] Arumugam, M., Thiyagarajan, A., Adhi, L. and Alagar, S., “Crossover smell agent optimized multilayer perceptron for precise brain tumor classification on MRI images”, Expert Systems with Applications, 238: 121453, (2024). DOI: https://doi.org/10.1016/j.eswa.2023.121453
29. [29] Islam, M.M., Talukder, M.A., Uddin, M.A., and Hasan, M.K., “BrainNet: precision brain tumor classification with optimized EfficientNet architecture”, International Journal of Intelligent Systems, 2024(1): 3583612, (2024). DOI: https://doi.org/10.1155/2024/3583612
30. [30] Pacal, I., Celik, O., Bayram, B. and Cunha, A., “Enhancing EfficientNetv2 with global and efficient channel attention mechanisms for accurate MRI-Based brain tumor classification”, Cluster Computing, 1-26, (2024). DOI: https://doi.org/10.1007/s10586-024-04473-7
31. [31] Pacal, I., “A novel Swin transformer approach utilizing residual multi-layer perceptron for diagnosing brain tumors in MRI images”, International Journal of Machine Learning and Cybernetics, 15(9): 3579-3597, (2024). DOI: https://doi.org/10.1007/s13042-024-02119-w
32. [32] Rajput, I. S., Gupta, A., Jain, V. and Tyagi, S., “A transfer learning-based brain tumor classification using magnetic resonance images”, Multimedia Tools and Applications, 83(7): 20487-20506, (2024). DOI: https://doi.org/10.1007/s11042-023-16209-6
33. [33] Sandhiya, B. and Raja, S. K. S., “Deep learning and optimized learning machine for brain tumor classification”, Biomedical Signal Processing and Control, 89: 105778, (2024). DOI: https://doi.org/10.1016/j.bspc.2024.105778
34. [34] Amin, J., Sharif, M., Haldorai, A., Yasmin, M. and Nayak, S. R., “Brain tumor detection and classification using machine learning: a comprehensive survey”, Complex & Intelligent Systems, 8(4): 3161–3183, (2022). DOI: https://doi.org/10.1007/s40747-021-00561-2
35. [35] Paul, J.S., Plassard, A.J., Landman, B.A. and Fabbri, D., “Deep learning for brain tumor classification”, In Medical Imaging 2017: Biomedical Applications in Molecular, Structural, and Functional Imaging, 10137: 253-268, (2017). DOI: https://doi.org/10.1117/12.2255013
36. [36] Deepak, S. and Ameer, P. M., “Brain tumor classification using deep CNN features via transfer learning”, Computers in Biology and Medicine, 111: 103345, (2019). DOI: https://doi.org/10.1016/j.compbiomed.2019.103345
37. [37] Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J. and Houlsby, N., “An image is worth 16×16 words: Transformers for image recognition at scale”, arXiv preprint arXiv:2010.11929, (2020).
38. [38] Cheng, J., Huang, W., Cao, S., Yang, R., Yang, W., Yun, Z., Wang, Z. and Feng, Q., “Enhanced performance of brain tumor classification via tumor region augmentation and partition”, PLOS ONE, 10(10): e0140381, (2015). DOI: https://doi.org/10.1371/journal.pone.0140381
39. [39] Cheng, J., Yang, W., Huang, M., Huang, W., Jiang, J., Zhou, Y., Wang, Y. and Feng, Q., “Retrieval of brain tumors by adaptive spatial pooling and fisher vector representation”, PLOS ONE, 11(6): e0157112, (2016). DOI: https://doi.org/10.1371/journal.pone.0157112
40. [40] Carreira, J., Madeira, H. and Silva, J.G., “Xception: Software fault injection and monitoring in processor functional units”, Dependable Computing and Fault Tolerant Systems, 10: 245-266, (1998). (NO DOI available)
41. [41] Szegedy, C., Ioffe, S., Vanhoucke, V. and Alemi, A., “Inception-v4, inception-resnet and the impact of residual connections on learning”, In Proceedings of the National Conference on Artificial Intelligence, 31(1): (2017). DOI: https://doi.org/10.1609/aaai.v31i1.11231
42. [42] Woo, S., Debnath, S., Hu, R., Chen, X., Liu, Z., Xie, E., Ding, L. and Van Gool, L., “ConvNeXt V2: Co-designing and scaling ConvNets with masked autoencoders”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 16133–16142, (2023). DOI: https://doi.org/10.1109/CVPR52729.2023.01548
43. [43] Yu, W., Zhou, P., Yan, S. and Wang, X., “Inceptionnext: When inception meets convnext”, In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 5672-5683, (2024). DOI: https://doi.org/10.1109/CVPR52733.2024.00542
44. [44] Tan, M. and Le, Q., “EfficientNetv2: Smaller models and faster training”, In Proceedings of the 38th International Conference on Machine Learning, Proceedings of Machine Learning Research, 139: 10096-10106, (2021). DOI: https://doi.org/10.48550/arXiv.2104.00298
45. [45] Han, K., Wang, Y., Chen, H., Chen, X., Guo, J., Liu, Z., Tang, Y., Xiao, A., Xu, C., Xu, Y. and Wang, Y., “A survey on vision transformer”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(1): 87–110, (2023). DOI: https://doi.org/10.1109/TPAMI.2022.3152247
46. [46] Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S. and Guo, B., “Swin Transformer: Hierarchical vision transformer using shifted windows”, Proceedings of the IEEE/CVF International Conference on Computer Vision, 10012–10022, (2021). DOI: https://doi.org/10.1109/ICCV48922.2021.00986
47. [47] Bao, H., Dong, L., Piao, S. and Wei, F., “Beit: Bert pre-training of image transformers”, arXiv preprint arXiv:2106.08254, (2021). DOI: https://doi.org/10.48550/arXiv.2106.08254
48. [48] Touvron, H., Cord, M. and Jégou, H., “Deit iii: Revenge of the ViT”. In European Conference on Computer Vision, Cham: Springer Nature Switzerland, 516-533, (2022). DOI: https://doi.org/10.1007/978-3-031-20050-2_30
49. [49] Coles, H., Laurent, T., Henard, C., Papadakis, M. and Ventresque, A., “Pit: a practical mutation testing tool for java”, In Proceedings of the 25th International Symposium on Software Testing and Analysis, 449-452, (2016). DOI: https://doi.org/10.1145/2931037.2948707
50. [50] Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D. and Batra, D., “Grad-cam: Visual explanations from deep networks via gradient-based localization”, In Proceedings of the IEEE International Conference on Computer Vision, 618-626, (2017). DOI: https://doi.org/10.1109/ICCV.2017.74