Optimization EfficientNetV2 model variant using Grad-CAM for multiple MRI brain tumor classification
DOI:
https://doi.org/10.21107/kursor.v13i3.428Keywords:
Brain tumors, MRI classification, EfficientNetV2, Grad-CAM, Deep learningAbstract
Fast and accurate diagnosis plays a critical role in effectively treating brain tumors. This study optimized and evaluated the EfficientNetV2 architecture through transfer learning, fine-tuning, and data augmentation, using three variants Small, Medium, and Large to classify MRI images into four categories: glioma, meningioma, pituitary tumors, and no tumor. Grad-CAM visualization was employed to enhance interpretability, providing a clear view of the critical regions in the MRI images that influenced the model’s decisions. Grad-CAM was tested across all model variants, and the best results were observed with EfficientNetV2-Large, where the model successfully highlighted the key areas associated with brain tumors. Among the variants, EfficientNetV2-Large achieved the best performance, with 99.85% accuracy, 99.60% precision, 99.65% recall, and 99.50% F1-score. However, this model required the longest computation time of 288 seconds per step, which may not be feasible in resource- constrained environments. Overall, this study underscores the potential of EfficientNetV2 models in revolutionizing brain tumor diagnosis by balancing accuracy, efficiency, and interpretability through advanced optimization techniques.
Key words: Brain tumors, MRI classification, EfficientNetV2, Grad-CAM, Deep learning.
Downloads
References
[1] P. Bansal et al., “We are IntechOpen , the world ’ s leading publisher of Open Access books Built by scientists , for scientists TOP 1 %,” Intech, vol. i, no. tourism, p. 15, 2016, [Online]. Available: https://www.intechopen.com/books/advanced-biometric- technologies/liveness-detection-in- biometrics
[2] B. Alther, V. Mylius, M. Weller, and Gantenbein, “From first symptoms to diagnosis: Initial clinical presentation of primary brain tumors,” Clin. Transl. Neurosci., vol. 4, no. 2, p.2514183X2096836, 2020, doi: 10.1177/2514183x20968368.
[3] Laurent, “Brain Tumor Management: One Day Symposium and Workshop,” no. December, pp. 1–13, 2017.
[4] H. Sung et al., “Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries,” CA. Cancer J. Clin., vol. 71, no. 3, pp. 209–249, 2021, doi: 10.3322/caac.21660.
[5] T. Singh, R. R. Nair, T. Babu, A. Wagh, A. Bhosalea, and P. Duraisamy, “BrainNet: A Deep Learning Approach for Brain Tumor Classification,” Procedia Comput. Sci., vol. 235, pp. 3283–3292, 2024, doi: 10.1016/j.procs.2024.04.310.
[6] X. Guo, T. Liu, and Q. Chi, “Brain tumor diagnosis in MRI scans images using Residual/Shuffle Network optimized by augmented Falcon Finch optimization,” Sci. Rep., vol. 14, no. 1, pp. 1–21, 2024, doi: 10.1038/s41598-024-77523-2.
[7] L. Alzubaidi et al., Review of deep learning: concepts, CNN architectures, challenges, applications, future directions, vol. 8, no. 1. Springer International Publishing, 2021. doi: 10.1186/s40537-021-00444-8.
[8] A. Iqbal, M. A. Jaffar, and R. Jahangir, “Enhancing Brain Tumour Multi- Classification Using Efficient-Net B0- Based Intelligent Diagnosis for Internet of Medical Things (IoMT) Applications,” Inf., vol. 15, no. 8, 2024, doi: 10.3390/info15080489.
[9] M. Tan and Q. V. Le, “EfficientNetV2: Smaller Models and Faster Training,” Proc. Mach. Learn. Res., vol. 139, pp. 10096–10106, 2021.
[10] Y. Anagun, “Smart brain tumor diagnosis system utilizing deep convolutional neural networks,” Multimed. Tools Appl., vol. 82, no. 28, pp. 44527–44553, 2023, doi: 10.1007/s11042-023-15422-w.
[11] M. Al Moteri, T. R. Mahesh, A. Thakur, V. Vinoth Kumar, S. B. Khan, and M. Alojail, “Enhancing accessibility for improved diagnosis with modified EfficientNetV2-S and cyclic learning rate strategy in women with disabilities and breast cancer,” Front. Med., vol. 11, no. March, pp. 1– 15, 2024, doi: 10.3389/fmed.2024.1373244.
[12] Mani Abedini, “Classification of MRI Brain Tumor Images using Deep Learning Segment Anything Model for segmentation and Deep Convolution Neural Network,” World J. Adv. Res. Rev., vol. 23, no. 2, pp. 1153–1161, 2024, doi: 10.30574/wjarr.2024.23.2.2469.
[13] J. H. Lee, J. W. Chae, and H. C. Cho, “Improved Classification of Different Brain Tumors in MRI Scans Using Patterned-GridMask,” IEEE Access, vol. 12, no. March, pp. 40204–40212, 2024, doi: 10.1109/ACCESS.2024.3377105.
[14] 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. 1, 2024, doi: 10.1007/s10586-024-04532-1.
[15] L. I. Kesuma, Ermatita, and Erwin, “ELREI: Ensemble Learning of ResNet, EfficientNet, and Inception- v3 for Lung Disease Classification based on Chest X-Ray Image,” Int. J. Intell. Eng. Syst., vol. 16, no. 5, pp. 149–161, 2023, doi: 10.22266/ijies2023.1031.14.
[16] O. A. Montesinos López, A. Montesinos López, and J. Crossa, Multivariate Statistical Machine Learning Methods for Genomic Prediction, no. January. 2022. doi: 10.1007/978-3-030-89010-0.
[17] Dr. T Subburaj and Bhavana. S, “Image Noise Reduction with Auto- encoders using TensorFlow,” Int. J. Adv. Res. Sci. Commun. Technol., pp. 86–91, 2024, doi: 10.48175/ijarsct-19016.
[18] L. Pfaff et al., “Self-supervised MRI denoising: leveraging Stein’s unbiased risk estimator and spatially resolved noise maps,” Sci. Rep., vol. 13, no. 1, pp. 1–13, 2023, doi: 10.1038/s41598-023-49023-2.
[19] K. L. Radke et al., “Deep Learning- Based Denoising of CEST MR Data: A Feasibility Study on Applying Synthetic Phantoms in Medical Imaging,” Diagnostics, vol. 13, no. 21, 2023, doi: 10.3390/diagnostics13213326.
[20] N. Pudjihartono, T. Fadason, A. W. Kempa-Liehr, and J. M. O’Sullivan, “A Review of Feature Selection Methods for Machine Learning-Based Disease Risk Prediction,” Front. Bioinforma., vol. 2, no. June, pp. 1–17, 2022, doi: 10.3389/fbinf.2022.927312.
[21] Y. Xu and R. Goodacre, “On Splitting Training and Validation Set: A Comparative Study of Cross- Validation, Bootstrap and Systematic Sampling for Estimating the Generalization Performance of Supervised Learning,” J. Anal. Test., vol. 2, no. 3, pp. 249–262, 2018, doi: 10.1007/s41664-018-0068-2.
[22] M. Tan and Q. V. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” 36th Int. Conf. Mach. Learn. ICML 2019, vol. 2019–June, pp. 10691–10700, 2019.
[23] H. Song, “FST-EfficientNetV2: Exceptional Image Classification for Remote Sensing,” Comput. Syst. Sci. Eng., vol. 46, no. 3, pp. 3959–3978, 2023, doi: 10.32604/csse.2023.038429.
[24] J. hyeon Lee, J. woo Chae, and H. chong Cho, “Improved Classification of Brain-Tumor MRI Images Through Data Augmentation and Filter Application,” J. Electr. Eng. Technol., vol. 18, no. 4, pp. 3135–3142, 2023, doi: 10.1007/s42835-023-01542-8.
[25] S. Tummala, V. S. G. Thadikemalla, S. Kadry, M. Sharaf, and H. T. Rauf, “EfficientNetV2 Based Ensemble Model for Quality Estimation of Diabetic Retinopathy Images from DeepDRiD,” Diagnostics, vol. 13, no. 4, 2023, doi: 10.3390/diagnostics13040622.
[26] Y. Sun, L. Ning, B. Zhao, and J. Yan, “Tomato Leaf Disease Classification by Combining EfficientNetv2 and a Swin Transformer,” Appl. Sci., vol. 14, no. 17, 2024, doi: 10.3390/app14177472.
[27] M. M. M, M. T. R, V. K. V, and S. Guluwadi, “Enhancing brain tumor detection in MRI images through explainable AI using Grad-CAM with Resnet 50,” BMC Med. Imaging, vol. 24, no. 1, pp. 1–19, 2024, doi: 10.1186/s12880-024-01292-7.
[28] D. Nova, K. Hardani, and I. Ardiyanto, “Decoding brain tumor insights : Evaluating CAM variants with 3D U- Net for segmentation,” vol. 9, no. 2, pp. 262–273, 2024. https://doi.org/10.21924/cst.9.2.2024.1477
[29] I. G. S. M. Diyasa, W. S. J. Saputra, A. N. Gunawan, D. Herawati, S. Munir, and S. Humairah, “Abnormality Determination of Spermatozoa Motility Using Gaussian Mixture Model and Matching-based Algorithm,” J. Robot. Control, vol. 5, no. 1, pp. 103–116, 2024, doi: 10.18196/jrc.v5i1.20686.
[30] M. M. Taye, “Understanding of Machine Learning with Deep Learning :,” Comput. MDPI, vol. 12, no. 91, pp. 1–26, 2023. https://doi.org/10.3390/computers12050091.
[31] R. Singh, C. Prabha, M. Malik, and A. Goyal, “A Robust Deep Learning Model for Brain Tumor Detection and Classification Using Efficient Net: A Brief Meta-Analysis,” J. Adv. Res. Appl. Sci. Eng. Technol., vol. 49, no. 2, pp. 26–51, 2025, doi: 10.37934/araset.49.2.2651.
[32] M. M. Islam, M. A. Talukder, M. A. Uddin, A. Akhter, and M. Khalid, “BrainNet: Precision Brain Tumor Classification with Optimized EfficientNet Architecture,” Int. J. Intell. Syst., vol. 2024, 2024, doi: 10.1155/2024/3583612.
Downloads
Published
Issue
Section
Citation Check
License
Copyright (c) 2026 Denisa Septalian Alhamda, Wahyu Syaifullah J, Prasetyaning Estu Pratiwi, Surjo Hadi, Wan Suryani Wan Awang, I Gede Susrama Mas Diyasa
This work is licensed under a Creative Commons Attribution 4.0 International License.
+62-858-5000-1918
