EFFICIENT MRI-BASED BRAIN TUMOR CLASSIFICATION USING PRUNED SQUEEZENET ARCHITECTURE
DOI:
https://doi.org/10.33480/jitk.v12i1.7963Keywords:
Brain Tumor Classification, Model Compression, MRI, Pruning, SqueezeNet.Abstract
Brain tumors are among the most serious neurological diseases, requiring accurate diagnosis to support effective treatment. Magnetic Resonance Imaging (MRI) is widely used for brain tumor detection because it provides detailed visualization of brain structures. However, manual MRI interpretation is time-consuming and highly dependent on radiologists' expertise, potentially leading to inconsistent diagnoses. This study evaluates the performance of several deep learning architectures, including VGG16, DenseNet121, Custom CNN, and SqueezeNet, for multiclass brain tumor classification using MRI images. To address the computational limitations of deep neural networks in resource-constrained medical environments, a structured pruning approach based on polynomial decay sparsity scheduling was applied to the SqueezeNet model to reduce model complexity while preserving predictive performance. Experiments were conducted on a multiclass MRI dataset consisting of glioma, meningioma, pituitary tumor, and non-tumor images. The proposed pruned SqueezeNet achieved a classification accuracy of 98.70% and an AUC of 0.998, while reducing the model size to 2,970 KB and achieving an inference time of 105.40 ms. These results demonstrate that structured pruning effectively improves computational efficiency without significantly compromising classification accuracy, making the model suitable for deployment in resource-limited medical settings. Nevertheless, further validation using larger and multi-institutional MRI datasets is required before clinical implementation
Downloads
References
[1] R. Preetha, M. J. P. Priyadarsini, and J. S. Nisha, “Automated Brain Tumor Detection From Magnetic Resonance Images Using Fine-Tuned EfficientNet-B4 Convolutional Neural Network,” IEEE Access, vol. 12, no. July, pp. 112181–112195, 2024, doi: 10.1109/ACCESS.2024.3442979.
[2] W. Chen, P. Sun, and Y. Zhang, “A brain tumor diagnosis approach based on deep separable convolutional networks and attention mechanisms,” Appl. Comput. Eng., vol. 67, no. 1, pp. 60–69, Jul. 2024, doi: 10.54254/2755-2721/67/20240629.
[3] J. Kang, Z. Ullah, and J. Gwak, “MRI-Based Brain Tumor Classification Using Ensemble of Deep Features and Machine Learning Classifiers,” Sensors, vol. 21, no. 2222, pp. 1–21, Mar. 2021, doi: 10.3390/s21062222.
[4] Y. E. Almalki et al., “Isolated Convolutional-Neural-Network-Based Deep-Feature Extraction for Brain Tumor Classification Using Shallow Classifier,” Diagnostics, vol. 12, no. 8, p. 1793, Jul. 2022, doi: 10.3390/diagnostics12081793.
[5] M. Aamir et al., “Brain Tumor Detection and Classification Using an Optimized Convolutional Neural Network,” Diagnostics, vol. 14, no. 1714, pp. 1–19, Aug. 2024, doi: 10.3390/diagnostics14161714.
[6] I. Pacal, O. Celik, B. Bayram, and A. Cunha, “Enhancing EfficientNetv2 with global and efficient channel attention mechanisms for accurate MRI-Based brain tumor classification,” Cluster Comput., vol. 27, no. 8, pp. 11187–11212, Nov. 2024, doi: 10.1007/s10586-024-04532-1.
[7] N. Zheng, G. Zhang, Y. Zhang, and F. R. Sheykhahmad, “Brain tumor diagnosis based on Zernike moments and support vector machine optimized by chaotic arithmetic optimization algorithm,” Biomedical Signal Processing and Control, vol. 82, p. 104543, Apr. 2023, doi: 10.1016/j.bspc.2022.104543.1
[8] M. A. Purnama Wibowo, Muhammad Bima Al Fayyadl, Yufis Azhar, and Zamah Sari, “Classification of Brain Tumors on MRI Images Using Convolutional Neural Network Model EfficientNet,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 6, no. 4, pp. 538–547, Aug. 2022, doi: 10.29207/resti.v6i4.4119.
[9] S. Agarwal, D. Jain, S. Gupta, S. Sawhney, and Y. Mittal, “Brain Tumor Detection and Classification Using Deep Learning,” in 2023 5th International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), 2023, pp. 635–640. doi: 10.1109/ICAC3N60023.2023.10541584.
[10] A. B. Abdusalomov, M. Mukhiddinov, and T. K. Whangbo, “Brain Tumor Detection Based on Deep Learning Approaches and Magnetic Resonance Imaging,” Cancers (Basel)., vol. 15, no. 4172, pp. 1–29, Aug. 2023, doi: 10.3390/cancers15164172.
[11] M. T. C. Seng and N. H. bt Rashidi, “Enhanced Brain Tumor Classification using Modified ResNet50 Architecture,” Borneo J. Sci. Technol., vol. 6, no. 1, pp. 11–18, Jan. 2024, doi: 10.35370/bjost.2024.6.1-02.
[12] Q. T. Lu, T. M. Nguyen, and H. Le Lam, “Improving Brain Tumor MRI Image Classification Prediction based on Fine-tuned MobileNet,” Int. J. Adv. Comput. Sci. Appl., vol. 15, no. 1, pp. 540–550, 2024, doi: 10.14569/IJACSA.2024.0150152.
[13] A. Agrawal, “Classification and Detection of Brain Tumors by Aquila Optimizer Hybrid Deep Learning Based Latent Features with Extreme Learner,” ITM Web Conf., no. 02008, p. 02008, Jun. 2023, doi: 10.1051/itmconf/20235302008.
[14] N. Elazab, W. Gab Allah, and M. Elmogy, “Computer-aided diagnosis system for grading brain tumor using histopathology images based on color and texture features,” BMC Med. Imaging, vol. 24, no. 1, pp. 1–22, 2024, doi: 10.1186/s12880-024-01355-9.
[15] I. Akbari, D. Hartama, and A. Wanto, “OPTIMIZATION OF EFFICIENTNET-B0 ARCHITECTURE TO IMPROVE THE ACCURACY OF GLAUCOMA DISEASE CLASSIFICATION,” JITK (Jurnal Ilmu Pengetah. dan Teknol. Komputer), vol. 11, no. 2, pp. 342–352, Nov. 2025, doi: 10.33480/jitk.v11i2.7140.
[16] M. Güler and E. Namlı, “Brain Tumor Detection with Deep Learning Methods’ Classifier Optimization Using Medical Images,” Appl. Sci., vol. 14, no. 642, pp. 1–25, Jan. 2024, doi: 10.3390/app14020642.
[17] P. K. Ramtekkar, A. Pandey, and M. K. Pawar, “Accurate detection of brain tumor using optimized feature selection based on deep learning techniques,” Multimed. Tools Appl., vol. 82, no. 29, pp. 44623–44653, Dec. 2023, doi: 10.1007/s11042-023-15239-7.
[18] A. Z. Al Wafi, F. P. Rochim, and A. Fathimah, “Deep Learning Approach for Pneumonia Prediction from X-Rays using A Pretrained Densenet Model,” J. ELTIKOM, vol. 9, no. 1, pp. 98–106, Jun. 2025, doi: 10.31961/eltikom.v9i1.1457.
[19] Solikhun, A. P. Windarto, and P. Alkhairi, “Bone fracture classification using convolutional neural network architecture for high-accuracy image classification,” Int. J. Electr. Comput. Eng., vol. 14, no. 6, pp. 6466–6477, 2024, doi: 10.11591/ijece.v14i6.pp6466-6477.
[20] A. I. R. H. Barat, W. S. Astuti, D. Hartama, A. P. Windarto, and A. Wanto, “ENHANCED FLOWER IMAGE CLASSIFICATION USING MOBILENETV2 WITH OPTIMIZED PERFORMANCE,” JITK (Jurnal Ilmu Pengetah. dan Teknol. Komputer), vol. 11, no. 1, pp. 180–191, Aug. 2025, doi: 10.33480/jitk.v11i1.6497.
[21] M. O. Khairandish, M. Sharma, V. Jain, J. M. Chatterjee, and N. Z. Jhanjhi, “A Hybrid CNN-SVM Threshold Segmentation Approach for Tumor Detection and Classification of MRI Brain Images,” Irbm, vol. 43, no. 4, pp. 290–299, 2022, doi: 10.1016/j.irbm.2021.06.003.
[22] O. Özkaraca et al., “Multiple Brain Tumor Classification with Dense CNN Architecture Using Brain MRI Images,” Life, vol. 13, no. 2, p. 349, Jan. 2023, doi: 10.3390/life13020349.
[23] S. Chitnis, R. Hosseini, and P. Xie, “Brain tumor classification based on neural architecture search,” Sci. Rep., vol. 12, no. 1, p. 19206, Nov. 2022, doi: 10.1038/s41598-022-22172-6.
[24] I. Oztel, “Ensemble Deep Learning Approach for Brain Tumor Classi fi cation Using Vision Transformer and Convolutional Neural Network,” vol. 2500393, pp. 1–10, 2025, doi: 10.1002/aisy.202500393.
[25] P. Kanchanamala, R. Karnati, and R. K. Tammineni, “Brain tumor classification from MRI images using exponential-Walruses hunting optimization driven SqueezeNet,” Expert Syst. Appl., vol. 271, no. 5, p. 126633, May 2025, doi: 10.1016/j.eswa.2025.126633.
[26] M. Sivakumar and S. T. Padmapriya, “Improving Efficiency of Brain Tumor Classification Models Using Pruning Techniques,” Curr. Med. Imaging Former. Curr. Med. Imaging Rev., vol. 20, pp. 1–12, Aug. 2024, doi: 10.2174/0115734056303076240614113525.
[27] K. R. Reddy and R. Dhuli, “A Novel Lightweight CNN Architecture for the Diagnosis of Brain Tumors Using MR Images,” Diagnostics, vol. 13, no. 312, pp. 1–21, Jan. 2023, doi: 10.3390/diagnostics13020312.
[28] M. Rasool, N. A. Ismail, A. Al-Dhaqm, W. M. S. Yafooz, and A. Alsaeedi, “A Novel Approach for Classifying Brain Tumours Combining a SqueezeNet Model with SVM and Fine-Tuning,” Electron., vol. 12, no. 1, 2023, doi: 10.3390/electronics12010149.
[29] L. Li, Y. Kong, and Q. Zhang, “Lightweight Malicious Code Classification Method Based on Improved SqueezeNet,” Comput. Mater. Contin., vol. 78, no. 1, pp. 551–567, 2024, doi: 10.32604/cmc.2023.045512.
[30] L. Narayanan, “A Hybrid Deep Learning Based Assist System for Detection and Classification of Breast Cancer from Mammogram Images,” Int. Arab J. Inf. Technol., vol. 19, no. 6, pp. 965–974, 2022, doi: 10.34028/iajit/19/6/15.
[31] A. Bin Naeem et al., “Lightweight CNN for accurate brain tumor detection from MRI with limited training data,” Frontiers in Medicine, vol. 12, Aug. 2025, doi: 10.3389/fmed.2025.1636059.
[32] M. Zabin, A. N. Binte Kabir, M. K. Kabir, H. J. Choi, and J. Uddin, “Machine Fault Diagnosis Using EMD-Gammatone Texture Representation and A Lightweight Self-Attention SqueezeNet,” 2024 IEEE International Conference on Big Data and Smart Computing (BigComp), pp. 32–39, Feb. 2024, doi: 10.1109/bigcomp60711.2024.00015.
[33] C. Xie et al., “A Novel Fusion Pruning-Processed Lightweight CNN for Local Object Recognition on Resource-Constrained Devices,” IEEE Trans. Consum. Electron., vol. 70, no. 4, pp. 6713–6724, Nov. 2024, doi: 10.1109/TCE.2024.3475517.
[34] M. Hao, Q. Sun, C. Xuan, X. Zhang, and M. Zhao, “SqueezeNet: An Improved Lightweight Neural Network for Sheep Facial Recognition,” Appl. Sci., vol. 14, no. 4, pp. 1–13, Feb. 2024, doi: 10.3390/app14041399.
[35] J. Tmamna, E. Ben Ayed, R. Fourati, A. Hussain, and M. Ben Ayed, “A CNN pruning approach using constrained binary particle swarm optimization with a reduced search space for image classification,” Appl. Soft Comput., vol. 164, p. 111978, Oct. 2024, doi: 10.1016/j.asoc.2024.111978.
[36] M. Xia, Z. Zhong, and D. Chen, “Structured Pruning Learns Compact and Accurate Models,” Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1513–1528, 2022, doi: 10.18653/v1/2022.acl-long.107.
[37] M. Nickparvar, Brain Tumor. 2021. [Online]. Available: https://www.kaggle.com/datasets/masoudnickparvar/brain-tumor-mri-dataset
[38] K. N. A. Nur, A. Wanto, and P. Poningsih, “OPTIMIZATION OF SVM ALGORITHM FOR OBESITY CLASSIFICATION WITH SMOTE TECHNIQUE AND HYPERPARAMETER TUNING,” JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer), vol. 11, no. 2, pp. 291–303, Nov. 2025, doi: 10.33480/jitk.v11i2.6878.
[39] O. Nurdiawan, H. Susana, and A. Faqih, “Deep Learning for Polycystic Ovarian Syndrome Classification Using Convolutional Neural Network,” JITK (Jurnal Ilmu Pengetah. dan Teknol. Komputer), vol. 9, no. 2, pp. 218–226, 2024, doi: 10.33480/jitk.v9i2.4575.
[40] S. Makenali, B. Rokh, and A. Azarpeyvand, "Integrating Pruning with Quantization for Efficient Deep Neural Networks Compression," arXiv preprint arXiv:2509.04244, 2025. [Online]. Available: https://arxiv.org/abs/2509.04244.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Ade Ismiaty Ramadhona Ht Barat, Poningsih Poningsih, Anjar Wanto
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
-a.jpg)
-b.jpg)
