A Automated Brain Tumor Classification using Deep Convolutional and Transfer Learning
Main Article Content
Abstract
Brain cancers are some of the fastest growing and most deadly types of neurological disease. Early detection with accuracy is very important to improve survival of patients. Manually reading MRI scans is a slow process. It requires special skills and can differ from one observer to another. It is in this context that the automatic computer-aided diagnosis has emerged as a vital research area. In this work we use deep learning based methods for classified various types of brain tumors using MRI. We developed a baseline convolutional neural network and compared it with four transfer-learning models: MobileNetV2, VGG16, VGG19, and ResNet50V2. To ensure data diversity and robustness, we merged two publicly available MRI tumor datasets and normalized, balanced, and pre-processed the data to a constant 224 × 224 pixel size for each image of the four categories: glioma, meningioma, pituitary tumor, and no tumor. The experimental results show that transfer learning performs significantly superior to the CNN baseline. ResNet50V2 became highly effective provided 97.2% accuracy, high precision, and excellent recall. These findings demonstrate that combining pre-trained neural networks with integrated datasets can provide better result, scalable framework for automated brain tumor identification.
Article Details
How to Cite
VIN, V., Vaidya, A. S., & Patil, M. S. (2026). A Automated Brain Tumor Classification using Deep Convolutional and Transfer Learning . JTRISTE, 13(1), 34-48. https://doi.org/10.55645/jtriste.v13i1.628
Section
Articles
References
[1] Louis DN, Perry A, Wesseling P, et al. The 2021 WHO classification of tumors of the central nervous system: a summary. Neuro-Oncology. 2021; 23(8): 1231-1251.
[2] Bauer S, Wiest R, Nolte L, Reyes M. A survey of MRI-based medical image analysis for brain tumor studies. Phys Med Biol. 2013; 58(13): R97-R129.
[3] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015; 521(7553): 436-444.
[4] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. IEEE Conf Comput Vis Pattern Recognit (CVPR). Las Vegas. 2016; 770-778.
[5] Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst (NeurIPS). 2012; 1097-1105.
[6] Litjens G, Kooi T, Bejnordi BE, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017; 42: 60-88.
[7] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint. 2015; arXiv: 1409.1556.
[8] Howard A, Sandler M, Chu G, et al. Searching for MobileNetV2. IEEE Conf Comput Vis Pattern Recognit (CVPR). 2019; 1314-1324.
[9] Pereira S, Pinto A, Alves V, Silva CA. Brain tumor segmentation using convolutional neural networks in MRI images. IEEE Trans Med Imaging. 2016; 35(5): 1240-1251.
[10] Sajjad H, Khan M, Maqsood A. VGG-based deep transfer learning for brain tumor classification. IEEE Access. 2021; 9: 15876-15885.
[11] Rehman S, Tahir M, Iqbal S. Brain tumor classification using ResNet and transfer learning. Comput Electr Eng. 2020; 88: 106839.
[12] Li Z, Wang X, Zhang Y. DenseNet-based deep learning for brain tumor detection. Neurocomputing. 2021; 437: 197-205.
[13] Sharif AN, Khan Z, Ullah H. MobileNetV2 for efficient brain MRI classification. Biomed Signal Process Control. 2021; 70: 103016.
[14] Deepak K, Raj PS. Comparative analysis of CNN architectures for brain MRI classification. IEEE Access. 2022; 10: 9456-9468.
[15] Sajjad M, Khan MH, Aftab M. Multi-grade brain tumor classification using deep CNN with extensive data augmentation. J Comput Sci. 2019; 30: 174-182.
[16] Brown TB, Mann B, Ryder N, et al. Language models are few-shot learners. Adv Neural Inf Process Syst. 2020; 33: 1877-1901.
[17] Dosovitskiy J, Beyer L, Kolesnikov A, et al. An image is worth 16x16 words: Transformers for image recognition at scale. Int Conf Learn Represent (ICLR). 2021.
[18] Chen Z, Hu Y. Attention-guided CNN for brain tumor classification. Pattern Recognit. 2022; 128: 108669.
[19] Kaur M, Garg S. Brain MRI classification using ensemble deep learning. Neurocomputing. 2022; 507: 112-124.
[20] Abdel-Halim A. Brain tumor classification CNN 97%. Kaggle Notebook. 2023.
[21] Menze B, Jakab A, Bauer S, et al. The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS). IEEE Trans Med Imaging. 2015; 34(10): 1993-2024.
[22] Islam A, Khan R, Rahman M. Glioma detection with hybrid deep networks. Comput Biol Med. 2023; 153: 106417.
[23] Li T, Wang S. Few-shot learning for MRI classification. IEEE J Biomed Health Inform. 2023; 27(1): 42-51.
[24] Park S, Kim H, Lee J. Lightweight CNNs for mobile health applications. IEEE Access. 2022; 10: 88590-88602.
[25] Chen H, Borle A, Tong L. Uncertainty estimation in medical image classifiers. Med Image Anal. 2023; 82: 102608.
[26] Minaee S, Mehdipour Ghazi R, Yang Z, et al. Image segmentation using deep learning: A review. IEEE Trans Pattern Anal Mach Intell. 2022; 44(7): 3523-3541.
[27] Wu X, Li R. Federated learning for brain MRI. IEEE Trans Neural Netw Learn Syst. 2023; 34(12): 10456-10468.
[28] Singh P, Gupta A, Sharma R. Multi-modal MRI fusion using deep networks. IEEE Access. 2023; 11: 120934-120946.
[29] Banerjee S, Sen R. EfficientNet for brain tumor detection. Pattern Recognit Lett. 2023; 165: 93-101.
[30] Yang Z, Huang K, Li P. Explainable residual networks in medical imaging. Med Phys. 2022; 49(10): 6567-6580.
[31] Luo M, Tan J, Zhou Y. Knowledge distillation for medical image classification. IEEE Access. 2023; 11: 13921-13933.
[32] Javed SR, Ghafoor A. Transfer learning strategies for small medical datasets. Biomed Signal Process Control. 2022; 78: 103955.
[33] 33. Patil VR, Kale A. Merged MRI datasets for brain tumor classification. Data Brief. 2024; 51: 109770.
[34] Dutta S, Roy P. Optimizing CNN hyperparameters for MRI. Comput Electr Eng. 2023; 109: 108716.
[35] Chen H, Zhang Z, Li R. Graph neural networks for medical image analysis. IEEE Trans Med Imaging. 2022; 41(9): 2240-2252.
[36] Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Commun ACM. 2017; 60(6): 84-90.
[37] Chen H, Liu M, Wang Y. Contrastive learning for medical imaging. IEEE Trans Med Imaging. 2023; 42(7): 1973-1985.
[38] Alam SS, Khan MK, Rashid A. Lightweight MRI classification models for low-resource settings. IEEE Access. 2023; 11: 13021-13033.
[39] Zhang K, Li H, Zhou M. Domain adaptation in medical imaging. IEEE Trans Med Imaging. 2023; 42(4): 987-1002.
[40] Wang Y, Li F, Luo S. Explainable AI in radiology. Radiology. 2023; 308(2): 345-359.
[41] Kaur R, Garg S. Ensemble deep learning for brain MRI classification. Neurocomputing. 2022; 507: 112-124.
[42] Li T, Wang S. Few-shot learning for MRI classification. IEEE J Biomed Health Inform. 2023; 27(1): 42-51.
[43] Minaee S, Mehdipour Ghazi R, et al. Image segmentation using deep learning: A review. IEEE Trans Pattern Anal Mach Intell. 2022; 44(7): 3523-3541.
[44] Ahmed M, Khan AK, Smith J. Hybrid Vision Transformer and GRU for brain tumor classification. Sci Rep. 2024; s41598-024-71893-3.
[45] https://www.kaggle.com/datasets/masoudnickparvar/brain-tumor-mri-dataset. 2023.
[46] Gupta RK. Automated brain tumor classification using transfer learning: a survey. IEEE Rev Biomed Eng. 2022; 3141606.
[47] Işın A, Direkoglu H, Şah MŞ. Review of MRI-based brain tumor image segmentation using deep learning methods. Procedia Comput Sci. 2016; 102: 317-324.
[48] Gull S, Ahmed AK. Automated detection of brain tumor through magnetic resonance images: a deep learning approach. IEEE Access. 2021; 3123456.
[49] Patil RK, Patil VR, et al. Architecture of proposed convolutional neural network model for brain tumor classification. Internal Report. 2024.
[50] Park S, et al. Lightweight CNNs for mobile health applications. IEEE Access. 2022; 10: 88590-88602.
[2] Bauer S, Wiest R, Nolte L, Reyes M. A survey of MRI-based medical image analysis for brain tumor studies. Phys Med Biol. 2013; 58(13): R97-R129.
[3] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015; 521(7553): 436-444.
[4] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. IEEE Conf Comput Vis Pattern Recognit (CVPR). Las Vegas. 2016; 770-778.
[5] Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst (NeurIPS). 2012; 1097-1105.
[6] Litjens G, Kooi T, Bejnordi BE, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017; 42: 60-88.
[7] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint. 2015; arXiv: 1409.1556.
[8] Howard A, Sandler M, Chu G, et al. Searching for MobileNetV2. IEEE Conf Comput Vis Pattern Recognit (CVPR). 2019; 1314-1324.
[9] Pereira S, Pinto A, Alves V, Silva CA. Brain tumor segmentation using convolutional neural networks in MRI images. IEEE Trans Med Imaging. 2016; 35(5): 1240-1251.
[10] Sajjad H, Khan M, Maqsood A. VGG-based deep transfer learning for brain tumor classification. IEEE Access. 2021; 9: 15876-15885.
[11] Rehman S, Tahir M, Iqbal S. Brain tumor classification using ResNet and transfer learning. Comput Electr Eng. 2020; 88: 106839.
[12] Li Z, Wang X, Zhang Y. DenseNet-based deep learning for brain tumor detection. Neurocomputing. 2021; 437: 197-205.
[13] Sharif AN, Khan Z, Ullah H. MobileNetV2 for efficient brain MRI classification. Biomed Signal Process Control. 2021; 70: 103016.
[14] Deepak K, Raj PS. Comparative analysis of CNN architectures for brain MRI classification. IEEE Access. 2022; 10: 9456-9468.
[15] Sajjad M, Khan MH, Aftab M. Multi-grade brain tumor classification using deep CNN with extensive data augmentation. J Comput Sci. 2019; 30: 174-182.
[16] Brown TB, Mann B, Ryder N, et al. Language models are few-shot learners. Adv Neural Inf Process Syst. 2020; 33: 1877-1901.
[17] Dosovitskiy J, Beyer L, Kolesnikov A, et al. An image is worth 16x16 words: Transformers for image recognition at scale. Int Conf Learn Represent (ICLR). 2021.
[18] Chen Z, Hu Y. Attention-guided CNN for brain tumor classification. Pattern Recognit. 2022; 128: 108669.
[19] Kaur M, Garg S. Brain MRI classification using ensemble deep learning. Neurocomputing. 2022; 507: 112-124.
[20] Abdel-Halim A. Brain tumor classification CNN 97%. Kaggle Notebook. 2023.
[21] Menze B, Jakab A, Bauer S, et al. The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS). IEEE Trans Med Imaging. 2015; 34(10): 1993-2024.
[22] Islam A, Khan R, Rahman M. Glioma detection with hybrid deep networks. Comput Biol Med. 2023; 153: 106417.
[23] Li T, Wang S. Few-shot learning for MRI classification. IEEE J Biomed Health Inform. 2023; 27(1): 42-51.
[24] Park S, Kim H, Lee J. Lightweight CNNs for mobile health applications. IEEE Access. 2022; 10: 88590-88602.
[25] Chen H, Borle A, Tong L. Uncertainty estimation in medical image classifiers. Med Image Anal. 2023; 82: 102608.
[26] Minaee S, Mehdipour Ghazi R, Yang Z, et al. Image segmentation using deep learning: A review. IEEE Trans Pattern Anal Mach Intell. 2022; 44(7): 3523-3541.
[27] Wu X, Li R. Federated learning for brain MRI. IEEE Trans Neural Netw Learn Syst. 2023; 34(12): 10456-10468.
[28] Singh P, Gupta A, Sharma R. Multi-modal MRI fusion using deep networks. IEEE Access. 2023; 11: 120934-120946.
[29] Banerjee S, Sen R. EfficientNet for brain tumor detection. Pattern Recognit Lett. 2023; 165: 93-101.
[30] Yang Z, Huang K, Li P. Explainable residual networks in medical imaging. Med Phys. 2022; 49(10): 6567-6580.
[31] Luo M, Tan J, Zhou Y. Knowledge distillation for medical image classification. IEEE Access. 2023; 11: 13921-13933.
[32] Javed SR, Ghafoor A. Transfer learning strategies for small medical datasets. Biomed Signal Process Control. 2022; 78: 103955.
[33] 33. Patil VR, Kale A. Merged MRI datasets for brain tumor classification. Data Brief. 2024; 51: 109770.
[34] Dutta S, Roy P. Optimizing CNN hyperparameters for MRI. Comput Electr Eng. 2023; 109: 108716.
[35] Chen H, Zhang Z, Li R. Graph neural networks for medical image analysis. IEEE Trans Med Imaging. 2022; 41(9): 2240-2252.
[36] Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Commun ACM. 2017; 60(6): 84-90.
[37] Chen H, Liu M, Wang Y. Contrastive learning for medical imaging. IEEE Trans Med Imaging. 2023; 42(7): 1973-1985.
[38] Alam SS, Khan MK, Rashid A. Lightweight MRI classification models for low-resource settings. IEEE Access. 2023; 11: 13021-13033.
[39] Zhang K, Li H, Zhou M. Domain adaptation in medical imaging. IEEE Trans Med Imaging. 2023; 42(4): 987-1002.
[40] Wang Y, Li F, Luo S. Explainable AI in radiology. Radiology. 2023; 308(2): 345-359.
[41] Kaur R, Garg S. Ensemble deep learning for brain MRI classification. Neurocomputing. 2022; 507: 112-124.
[42] Li T, Wang S. Few-shot learning for MRI classification. IEEE J Biomed Health Inform. 2023; 27(1): 42-51.
[43] Minaee S, Mehdipour Ghazi R, et al. Image segmentation using deep learning: A review. IEEE Trans Pattern Anal Mach Intell. 2022; 44(7): 3523-3541.
[44] Ahmed M, Khan AK, Smith J. Hybrid Vision Transformer and GRU for brain tumor classification. Sci Rep. 2024; s41598-024-71893-3.
[45] https://www.kaggle.com/datasets/masoudnickparvar/brain-tumor-mri-dataset. 2023.
[46] Gupta RK. Automated brain tumor classification using transfer learning: a survey. IEEE Rev Biomed Eng. 2022; 3141606.
[47] Işın A, Direkoglu H, Şah MŞ. Review of MRI-based brain tumor image segmentation using deep learning methods. Procedia Comput Sci. 2016; 102: 317-324.
[48] Gull S, Ahmed AK. Automated detection of brain tumor through magnetic resonance images: a deep learning approach. IEEE Access. 2021; 3123456.
[49] Patil RK, Patil VR, et al. Architecture of proposed convolutional neural network model for brain tumor classification. Internal Report. 2024.
[50] Park S, et al. Lightweight CNNs for mobile health applications. IEEE Access. 2022; 10: 88590-88602.