An Efficient Transfer Learning Hybrid Model for Multiclass Brain Tumor Classification
DOI:
https://doi.org/10.47839/ijc.24.2.4022Keywords:
Brain Tumor, Transfer Learning, Residual CNN, EfficientNetV2B3, ResNetV2, Multiclass Tumor, Confusion Matrix, Accuracy, CLAHEAbstract
Brain tumors are the most dangerous diseases today. Brain tumors have come second among the diseases that cause the most deaths in the world. Conventional techniques used to diagnose brain tumors are time-consuming and prone to error. Transfer learning algorithms have also been used to detect brain tumors and are still being used extensively. After studying the previous research paper, we found two shortcomings. First of all, in most of the work, researchers modified a particular Convolutional Neural Network, which found only the features of that Convolutional Neural Network, and the second one mostly worked on a single-class detection, which means that the model will detect whether the given input image is tumorous or not. However, these models are not able to identify the multiclass tumors. Keeping both these things in mind, in this research paper, we have introduced a hybrid multilabel classifier model in which ResNetV2 and EfficientNetV2B3 have been combined to get their best features with ImageNet weights. Combining ResNetV2 (the best Residual Convolutional Network for multilayer and multiclass classification) and EfficientNetV2B3 (the best Convolutional network for faster calculation) helped us to deploy a faster multilayered classifier model. The last 30 layers of both have been trained accordingly, and 16 custom layers have been included. The dataset contains 3 types of tumor images (glioma, meningioma, and pituitary) and non-tumor images. The model was trained with 4569 human Brain MRI images and then validated with 1143 images. The model was tested on 1311 images, and its performance was measured for multiclass tumors. The overall accuracy of the presented model was measured at 100% during training and 99.1% during testing, which shows that our model works very accurately. As a multiclass classifier, it achieved maximum accuracy value, maximum recall value, maximum precision value, and maximum F-1 score value of 99.1% (all classes), 100.00% (Pituitary and No tumor classes), 100.00% (No Tumor class), and 100.00% (No Tumor Class), respectively.
References
N. Simhadri and T.N.V.R Swami, “Awareness among teaching on AI and ML applications based on fuzzy in education sector at USA,” Soft Comput (2023). https://doi.org/10.1007/s00500-023-08329-z.
S. Chen, J. Yu, S. Chamouni, et al., “Integrating machine learning and artificial intelligence in life-course epidemiology: pathways to innovative public health solutions,” BMC Med, vol. 22, 354, 2024. https://doi.org/10.1186/s12916-024-03566-x.
M. Rana, M. Bhushan, “Machine learning and deep learning approach for medical image analysis: Diagnosis to detection,” Multimed Tools Appl, vol. 82, pp. 26731–26769, 2023. https://doi.org/10.1007/s11042-022-14305-w.
G. M. Rao, D. Ramesh, V. Sharma, et al., “AttGRU-HMSI: enhancing heart disease diagnosis using hybrid deep learning approach,” Sci Rep, vol. 14, 7833, 2024. https://doi.org/10.1038/s41598-024-56931-4.
B. F. Wee, S. Sivakumar, K. H. Lim, et al., “Diabetes detection based on machine learning and deep learning approaches,” Multimed Tools Appl, vol. 83, pp. 24153–24185, 2024. https://doi.org/10.1007/s11042-023-16407-5.
Ö.F. Akmeşe, “Data privacy-aware machine learning approach in pancreatic cancer diagnosis,” BMC Med Inform Decis Mak, vol. 24, 248, 2024. https://doi.org/10.1186/s12911-024-02657-2.
K. K. Joshi, K. Gupta, & J. Agrawal, “An efficient transfer learning approach for prediction and classification of SARS – COVID-19,” Multimed Tools Appl, vol. 83, pp. 39435–39457, 2024. https://doi.org/10.1007/s11042-023-17086-y.
Q. Xiang, D. Li, Z. Hu, et al., “Quantum classical hybrid convolutional neural networks for breast cancer diagnosis,” Sci Rep, vol. 14, 24699 (2024). https://doi.org/10.1038/s41598-024-74778-7.
L. Van Dieren, J. Z. Amar, N. Geurs, et al., “Unveiling the power of convolutional neural networks in melanoma diagnosis,” Eur J Dermatol, vol. 33, pp. 495–505, 2023. https://doi.org/10.1684/ejd.2023.4559.
F. Hoseini, S. Shamlou, & M. Ahmadi-Gharehtoragh, “Segmentation of MR images for brain tumor detection using autoencoder neural network,” Discov Artif Intell, vol. 4, 71, 2024. https://doi.org/10.1007/s44163-024-00180-x.
K. Kumar, K. Jyoti, & K. Kumar, “Machine learning for brain tumor classification: evaluating feature extraction and algorithm efficiency,” Discov Artif Intell, vol. 4, 112, 2024. https://doi.org/10.1007/s44163-024-00214-4.
M. Ahmed, M. Nadeem, U. B. Shahzad, et al., “A comprehensive approach to lateral ventricular tumor resection: Techniques, technologies, and outcomes,” Neurosurg Rev, vol. 47, 489, 2024. https://doi.org/10.1007/s10143-024-02745-x.
N. Elazab, W. Gab Allah, & M. Elmogy, “Computer-aided diagnosis system for grading brain tumor using histopathology images based on color and texture features,” BMC Med Imaging, vol. 24, 177, 2024. https://doi.org/10.1186/s12880-024-01355-9.
M. Reichenbach, S. Richter, R. Galli, et al., “Clinical confocal laser endomicroscopy for imaging of autofluorescence signals of human brain tumors and non-tumor brain,” J Cancer Res Clin Oncol, vol. 151, 19, 2025. https://doi.org/10.1007/s00432-024-06052-2.
Z. Mansur, J. Talukdar, T. P. Singh, et al., “Deep learning-based brain tumor image analysis for segmentation,” SN COMPUT. SCI., vol. 6, 42, 2025. https://doi.org/10.1007/s42979-024-03558-x.
R. Ahsan, I. Shahzadi, F. Najeeb, et al., “Brain tumor detection and segmentation using deep learning,” Magn Reson Mater Phy, vol. 38, pp. 13-22, 2024. https://doi.org/10.1007/s10334-024-01203-5.
S. Ganapathy, V. Thoidingjam, & A. Sen, “A brain tumor prediction system for detecting the tumor disease using mini batch K-Means clustering and CNN,” Multimed Tools Appl, vol. 83, pp. 83053–83091, 2024. https://doi.org/10.1007/s11042-024-18790-z.
D. Black, D. Byrne, A. Walke, et al., “Towards machine learning-based quantitative hyperspectral image guidance for brain tumor resection,” Commun Med, vol. 4, 131, 2024. https://doi.org/10.1038/s43856-024-00562-3.
Chakrapani, S. Kumar, S. Semantic segmentation of brain tumor images using attention-based residual light u-net model. Multimed Tools Appl, vol. 84, pp. 7425-7441, 2024. https://doi.org/10.1007/s11042-024-19224-6.
S. K. Natarajan, S. J.ayanthi, S. K. Mathivanan, et al., “Exploring fetal brain tumor glioblastoma symptom verification with self organizing maps and vulnerability data analysis,” Sci Rep, vol. 14, 8738, 2024. https://doi.org/10.1038/s41598-024-59111-6.
T. K. Dutta, D. R. Nayak, & R. B. Pachori, “GT-Net: global transformer network for multiclass brain tumor classification using MR images,” Biomed. Eng. Lett., vol. 14, pp. 1069–1077, 2024. https://doi.org/10.1007/s13534-024-00393-0.
C. Tao, D. Gu, R. Huang, et al., “Hippocampus segmentation after brain tumor resection via postoperative region synthesis,” BMC Med Imaging, vol. 23, 142, 2023. https://doi.org/10.1186/s12880-023-01087-2.
Y. Abdelrahman Ali, T. Kamani, S. K. Patel, et al., “Design and investigation of machine learning–optimized surface plasmon resonance biosensor for early brain tumor detection,” Plasmonics, 2024. https://doi.org/10.1007/s11468-024-02635-4.
A. Kaur, Y. Singh, & B. Chinagundi, “ResUNet + + : a comprehensive improved UNet + + framework for volumetric semantic segmentation of brain tumor MR images,” Evolving Systems, vol. 15, pp. 1567–1585, 2024. https://doi.org/10.1007/s12530-024-09579-4.
S. Poornam, J.J.R. Angelina, “BrainNeuroNet: advancing brain tumor detection with hierarchical transformers and multiscale attention,” Int. J. Inf. Tecnol., vol. 16, pp. 4749–4756, 2024. https://doi.org/10.1007/s41870-024-02216-y.
M. M. Gomaa, A. G. Zain elabdeen, A. Elnashar, et al., “Brain tumor X-ray images enhancement and classification using anisotropic diffusion filter and transfer learning models,” Int. J. Inf. Tecnol., vol. 16, pp. 3771–3779, 2024. https://doi.org/10.1007/s41870-024-01830-0.
M. Basthikodi, M. Chaithrashree, B. M. Ahamed Shafeeq, et al., “Enhancing multiclass brain tumor diagnosis using SVM and innovative feature extraction techniques,” Sci Rep, vol. 14, 26023, 2024. https://doi.org/10.1038/s41598-024-77243-7.
A. H. Tiple, A. B. Kakade, “Modified mask R-CNN with KNN algorithm based segmentation and classification for prediction of brain tumor types,” Optoelectron. Instrument. Proc., vol. 60, pp. 11–30, 2024. https://doi.org/10.3103/S8756699024700146.
B. Swathi, S. S. Kolisetty, G.V. Sivanarayana, et al., “Efficientnetv2-RegNet: an effective deep learning framework for secure SDN based IOT network,” Cluster Comput, vol. 27, pp. 10653–10670, 2024. https://doi.org/10.1007/s10586-024-04498-0.
P. V. Sabique, G. Pasupathy, S. Kalaimagal, et al., “A stereovision-based approach for retrieving variable force feedback in robotic-assisted surgery using modified inception ResNet V2 networks,” J Intell Robot Syst, vol. 110, 81, 2024. https://doi.org/10.1007/s10846-024-02100-8.
K. Faber, D. Zurek, M. Pietron, et al., “From MNIST to ImageNet and back: benchmarking continual curriculum learning,” Mach Learn, vol. 113, pp. 8137–8164, 2024. https://doi.org/10.1007/s10994-024-06524-z.
N. Boudouh, B. Mokhtari, & S. Foufou, “Enhancing deep learning image classification using data augmentation and genetic algorithm-based optimization,” Int J Multimed Info Retr, vol. 13, 36, 2024. https://doi.org/10.1007/s13735-024-00345-5.
K. Alomar, H. I. Aysel, X. Cai, “Data augmentation in classification and segmentation: A survey and new strategies,” J. Imaging, vol. 9, 46, 2023. https://doi.org/10.3390/jimaging9020046.
V. Werner de Vargas, J. A. Schneider Aranda, R. dos Santos Costa, et al., “Imbalanced data preprocessing techniques for machine learning: a systematic mapping study,” Knowl Inf Syst, vol. 65, pp. 31–57, 2023. https://doi.org/10.1007/s10115-022-01772-8.
D.J.J. Seeli, K.K. Thanammal, “A comparative review and analysis of medical image encryption and compression techniques,” Multimed Tools Appl, 2024. https://doi.org/10.1007/s11042-024-18745-4.
E. Irmak, “Multi-classification of brain tumor MRI images using deep convolutional neural network with fully optimized framework,” Iran J Sci Technol Trans Electr Eng, vol. 45, pp. 1015–1036, 2021. https://doi.org/10.1007/s40998-021-00426-9.
S M. Rasa et al., “Brain tumor classification using fine-tuned transfer learning models on magnetic resonance imaging (MRI) images,” Digital Health, 2024. https://doi.org/10.1177/20552076241286140.
E. Albalawi, T. R. Manesh, A. Thakur, et al., “Integrated approach of federated learning with transfer learning for classification and diagnosis of brain tumor,” BMC Med Imaging, vol. 24, 110, 2024. https://doi.org/10.1186/s12880-024-01261-0.
B. Babu Vimala, S. Srinivasan, S. K. Mathivanan, et al., “Detection and classification of brain tumor using hybrid deep learning models,” Sci Rep, vol. 13, 23029, 2023. https://doi.org/10.1038/s41598-023-50505-6.
K. V. Archana, and G. Komarasamy, “A novel deep learning-based brain tumor detection using the Bagging ensemble with K-nearest neighbor,” Journal of Intelligent Systems, vol. 32, no. 1, 20220206, 2023. https://doi.org/10.1515/jisys-2022-0206.
M. Yurtsever, Y. Atay, B. Arslan, et al., “Development of brain tumor radiogenomic classification using GAN-based augmentation of MRI slices in the newly released gazi brains dataset,” BMC Med Inform Decis Mak, vol. 24, 285, 2024. https://doi.org/10.1186/s12911-024-02699-6.
G. Bogacsovics, B. Harangi, & A. Hajdu, “Developing diverse ensemble architectures for automatic brain tumor classification,” Multimed Tools Appl, 2024. https://doi.org/10.1007/s11042-024-19657-z.
S. Saeedi, S. Rezayi, H. Keshavarz, et al., “MRI-based brain tumor detection using convolutional deep learning methods and chosen machine learning techniques,” BMC Med Inform Decis Mak, vol. 23, 16, 2023. https://doi.org/10.1186/s12911-023-02114-6.
N. Ullah, J.A. Khan, M.S. Khan, W. Khan, I. Hassan, M. Obayya, N. Negm, A.S. Salama, “An effective approach to detect and identify brain tumors using transfer learning,” Appl. Sci., vol. 12, 5645, 2022. https://doi.org/10.3390/app12115645.
M.Z. Khaliki, M.S. Başarslan, “Brain tumor detection from images and comparison with transfer learning methods and 3-layer CNN,” Sci Rep, vol. 14, 2664, 2024. https://doi.org/10.1038/s41598-024-52823-9.
M.I. Mahmud, M. Mamun, A. Abdelgawad, “A deep analysis of brain tumor detection from MR images using deep learning networks,” Algorithms, vol. 16, 176, 2023. https://doi.org/10.3390/a16040176.
A. Alshammari, “Construction of VGG16 convolution neural network (VGG16_CNN) classifier with NestNet-based segmentation paradigm for brain metastasis classification,” Sensors, vol. 22, 8076, 2022. https://doi.org/10.3390/s22208076.
M. Islam, M.T. Reza, M. Kaosar, et al., “Effectiveness of federated learning and CNN ensemble architectures for identifying brain tumors using MRI images,” Neural Process Lett, vol. 55, pp. 3779–3809, 2023. https://doi.org/10.1007/s11063-022-11014-1.
Downloads
Published
How to Cite
Issue
Section
License
International Journal of Computing is an open access journal. Authors who publish with this journal agree to the following terms:• Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
• Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
• Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
