IRO Journals
Journal of Innovative Image Processing

ASO‑Optimized EfficientNet‑B2 with CBAM for Brain Tumor MRI Classification

Open Access
Published: 06 July, 2026
Pages: 844-869
  • Ramisetty Balaji , Ramisetty Balaji
    Department of Computer Science and Engineering, School of Computing, Mohan Babu University, Tirupati, Andhra Pradesh, India
    Department of Computer Science and Engineering, School of Computing, Mohan Babu University, Tirupati, Andhra Pradesh, India
  • Anantha Natarajan V. Anantha Natarajan V.
    Department of Computer Science and Engineering, School of Computing, Mohan Babu University, Tirupati, Andhra Pradesh, India
    Department of Computer Science and Engineering, School of Computing, Mohan Babu University, Tirupati, Andhra Pradesh, India
view PDF
view PDF

How to Cite

Balaji, Ramisetty, and Anantha Natarajan V. 2026. “ASO‑Optimized EfficientNet‑B2 With CBAM for Brain Tumor MRI Classification”. Journal of Innovative Image Processing 8 (3): 844-69. https://doi.org/10.36548/jiip.2026.3.006.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Brain Tumor Classification
Atom Search Optimization
Metaheuristic Optimization
EfficientNet
Convolutional Block Attention Module
Population-Based Training

Abstract

Magnetic resonance imaging (MRI) plays a critical role in brain tumor diagnosis; however, accurate classification remains a challenging task in medical image analysis. Gradient-based optimizers form the foundation of deep learning models; however, they are susceptible to suboptimal local minima and hyperparameter sensitivity. This paper proposes a hybrid model in which the CBAM attention module, the classifier head, and the final two convolutional blocks of EfficientNet-B2 are optimized using Atom Search Optimization (ASO), while the remaining backbone layers are retained as fixed feature extractors. ASO generates a population of candidate solutions by simulating atomic motion using Lennard-Jones and bond-length potentials, without relying on gradient information, and is used to search the high-dimensional parameter space. Experiments on the Figshare brain tumor dataset (3,064 T1-weighted MRI images of glioma, meningioma, and pituitary tumors) demonstrate that the ASO-optimized EfficientNet-B2+CBAM model has an accuracy of 99.35% and F1-score of 99.38%, outperforming Adam (98.76%) and SGD (98.12%). Statistically significant improvements (p < 0.01) are observed, and convergence analysis indicates ASO is less susceptible to plateaus of loss, and the variance is reduced by 44.7% across runs. The effectiveness of ASO is further evaluated through ablation studies, ROC analysis, and Grad-CAM visualizations, demonstrating its potential as an alternative optimizer for brain tumor MRI classification. Further validation on multi-center clinical datasets is required to assess generalizability and clinical applicability.

References

  1. Miller, Kimberly D., Quinn T. Ostrom, Carol Kruchko, Nirav Patil, Tarik Tihan, Gino Cioffi, Hannah E. Fuchs et al. "Brain and Other Central Nervous System Tumor Statistics, 2021." CA: a cancer journal for clinicians 71, no. 5 (2021): 381-406.
  2. Santos, Milton, and Nelson Pacheco Rocha. "Medical Imaging Repository Contributions for Radiation Protection Key Performance Indicators." Procedia Computer Science 196 (2022): 590-597.
  3. Dutta, Tapas Kumar, Deepak Ranjan Nayak, and Yu-Dong Zhang. "Arm-Net: Attention-Guided Residual Multiscale Cnn for Multiclass Brain Tumor Classification Using Mr Images." Biomedical Signal Processing and Control 87 (2024): 105421.
  4. Li, Xinyuan, Xiang Chen, Liuyi He, Yi Wu, Lei Du, and Wen He. "An Improved Efficientnet-B0 Approach for Brain Tumor MRI Image Classification." In 2025 IEEE 8th Information Technology and Mechatronics Engineering Conference (ITOEC), vol. 8, IEEE, 2025, 1598-1602.
  5. Khushi, Hafiz Muhammad Tayyab, Tehreem Masood, Arfan Jaffar, Muhammad Rashid, and Sheeraz Akram. "Improved Multiclass Brain Tumor Detection via Customized Pretrained Efficientnetb7 Model." IEEE Access 11 (2023): 117210-117230.
  6. Geetha, M., V. Srinadh, J. Janet, and S. Sumathi. "Hybrid Archimedes Sine Cosine Optimization Enabled Deep Learning for Multilevel Brain Tumor Classification Using Mri Images." Biomedical Signal Processing and Control 87 (2024): 105419.
  7. Tanner, Irene L., Ken Ye, Miles S. Moore, Albert J. Rechenmacher, Michelle M. Ramirez, Steven Z. George, Michael P. Bolognesi, and Maggie E. Horn. "Developing a Computer Vision Model to Automate Quantitative Measurement of Hip-Knee-Ankle Angle in Total Hip and Knee Arthroplasty Patients." The Journal of Arthroplasty 39, no. 9 (2024): 2225-2233.
  8. Saifullah, Shoffan, Rafał Dreżewski, Anton Yudhana, Wahyu Caesarendra, and Nurul Huda. "Bio-Inspired Metaheuristics in Deep Learning for Brain Tumor Segmentation: A Decade of Advances and Future Directions." Information 16, no. 6 (2025): 456.
  9. Aamir, Muhammad, Ziaur Rahman, Uzair Aslam Bhatti, Waheed Ahmed Abro, Jameel Ahmed Bhutto, and Zhonglin He. "An Automated Deep Learning Framework for Brain Tumor Classification Using MRI Imagery." Scientific reports 15, no. 1 (2025): 17593.
  10. Khushi, Hafiz Muhammad Tayyab, Tehreem Masood, and Iftikhar Naseer. "Optimizer-Aware Deep Learning for Brain Tumor Classification: A Study Using AlexNet to EfficientNetB0." Research Square. 2025.
  11. Gencer, Kerem. "A Comparative Analysis of EfficientNetB0 and EfficientNetV2 Variants for Brain Tumor Classification Using MRI Images." International Journal of Innovative Engineering Applications 9, no. 1 (2025): 1-7.
  12. Binish, M. C., Swarun Raj RS, and Vinu Thomas. "CBAM–SMK: Integrating Convolution Block Attention Module with Separable Multi-Resolution Kernels in Deep Neural Networks for Brain Tumor Classification." Biomedical Signal Processing and Control 112 (2026): 108483.
  13. Hamza, Ameer, and Robertas Damaševičius. "Deep Learning for Brain Tumor Segmentation and Classification: A Systematic Review of Methods and Trends." Computers, materials and continua. 86, no. 1 (2026): 1-41.
  14. Pabitha, C., Mr Law Kumar Singh, and Mrs TR Vijaya Lakshmi. "Enhanced Brain Tumor Classification via Efficient Predefined Time Adaptive Neural Network Optimized with High-Level Target Navigation Pigeon-Inspired Optimization." Knowledge-Based Systems (2025): 114658.
  15. Woo, Sanghyun, Jongchan Park, Joon-Young Lee, and In So Kweon. "Cbam: Convolutional Block Attention Module." In Proceedings of the European conference on computer vision (ECCV), 2018, 3-19.
  16. Abdulsattar, Nadia Shamsulddin, and Fatimah S. Abdulsattar. "Brain-Tumor Classification Using Resnet50 Enhanced with SE and CBAM Attention MechaniSMS." Jordanian Journal of Computers & Information Technology 12, no. 1 (2026): 98.
  17. Wubineh, Betelhem Zewdu, Andrzej Rusiecki, Krzysztof Halawa, and Eyerus Zewdu Wubineh. "Classification of Brain Tumor Using MobileNet and CBAM-Based Deep Learning Approach from MRI Images." In 2025 International Conference on Information and Communication Technology for Development for Africa (ICT4DA), IEEE, 2025, 72-77.
  18. Guo, Xiaohang, Tianyi Liu, and Qinglong Chi. "Brain Tumor Diagnosis in MRI Scans Images Using Residual/Shuffle Network Optimized by Augmented Falcon Finch Optimization." Scientific Reports 14, no. 1 (2024): 27911.
  19. Ghosh, Akhilbaran, and Rama Sai Adithya Kalidindi. "Enhancing CNN Classification with Lamarckian Memetic Algorithms and Local Search." In 2024 International Conference on Signal Processing and Advance Research in Computing (SPARC), vol. 1, IEEE, 2024, 1-7.
  20. Zhao, Weiguo, Liying Wang, and Zhenxing Zhang. "A Novel Atom Search Optimization for Dispersion Coefficient Estimation in Groundwater." Future Generation Computer Systems 91 (2019): 601-610.
  21. He, Qingling, Yifan Feng, Yongsheng Qian, Xiaojuan Lu, Junwei Zeng, Xu Wei, Kaiyang Li, and Yao Peng. "A Hybrid Improved Atom Search Optimization Algorithm Optimizes BiGRU for Bus Travel Speed Prediction." Mathematics 14, no. 5 (2026): 856.
  22. Cheng, J. (2017). Brain Tumor Dataset [Data set]. Figshare. https://figshare.com/
  23. Panigrahi, Soumyarashmi, Dibya Ranjan Das Adhikary, Bishal Biswal, Bhumika Jena, Kamal Nayan Mohapatra, and Upasana Patnaik. "Vision Transformers for Brain Tumor Classification: A Novel Deep Learning Approach." In 2025 International Conference on Innovations in Intelligent Systems: Advancements in Computing, Communication, and Cybersecurity (ISAC3), IEEE, 2025, 1-6.
  24. Lavanya, B., A. Praveen Kumar Reddy, T. Ananth, M. Upendra Reddy, and K. Siva Rama Chandra Sarma. "Swin Transformer-Based Brain Tumor Type Classification with Multilingual Medical Summarization." In 2025 2nd International Conference on Artificial Intelligence for Innovations in Healthcare Industries (ICAIIHI), IEEE, 2025, 1-6.
  25. Joy, Abdullah Al Mahmud, Md Faizer Islam, and Md Mamun Hossain. "Ensemble Deep Learning for Brain Tumor Classification Using MRI: A Comparative Study of CNN Architectures." In 2025 IEEE 2nd International Conference on Computing, Applications and Systems (COMPAS), IEEE, 2025, 1-6.