IRO Journals
Journal of Trends in Computer Science and Smart Technology

Hybrid Channel-Spatial Attention Enhanced EfficientNet for Multi-Class Brain Tumor Classification Using MRI

Open Access
Published: 18 July, 2026
Pages: 703-727
  • Kiran Kumar M. , Kiran Kumar M.
    Assistant Professor, Department of Computer Science and Engineering (Data Science), Madanapalle Institute of Technology and Science (MITS), Deemed to be University, Madanapalle, Andhra Pradesh, India
    Assistant Professor, Department of Computer Science and Engineering (Data Science), Madanapalle Institute of Technology and Science (MITS), Deemed to be University, Madanapalle, Andhra Pradesh, India
  • Dheeraj Kumar K V. , Dheeraj Kumar K V.
    PG Student, Department of Computer Science and Engineering, Madanapalle Institute of Technology and Science (MITS), Deemed to be University, Madanapalle, Andhra Pradesh, India
    PG Student, Department of Computer Science and Engineering, Madanapalle Institute of Technology and Science (MITS), Deemed to be University, Madanapalle, Andhra Pradesh, India
  • Gunji. Sreenivasulu , Gunji. Sreenivasulu
    Assistant Professor, Department of Computer Science and Engineering, Madanapalle Institute of Technology and Science (MITS), Deemed to be University, Madanapalle, Andhra Pradesh, India
    Assistant Professor, Department of Computer Science and Engineering, Madanapalle Institute of Technology and Science (MITS), Deemed to be University, Madanapalle, Andhra Pradesh, India
  • Kusuma S. Kusuma S.
    Assistant Professor, Department of Computer Science and Engineering (Data Science), Madanapalle Institute of Technology and Science (MITS), Deemed to be University, Madanapalle, Andhra Pradesh, India
    Assistant Professor, Department of Computer Science and Engineering (Data Science), Madanapalle Institute of Technology and Science (MITS), Deemed to be University, Madanapalle, Andhra Pradesh, India
view PDF
view PDF

How to Cite

M., Kiran Kumar, Dheeraj Kumar K V., Gunji. Sreenivasulu, and Kusuma S. 2026. “Hybrid Channel-Spatial Attention Enhanced EfficientNet for Multi-Class Brain Tumor Classification Using MRI”. Journal of Trends in Computer Science and Smart Technology 8 (3): 703-27. https://doi.org/10.36548/jtcsst.2026.3.014.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

EfficientNet-B0
Hybrid Attention
Brain Tumor Classification
Grad-CAM; Multi-Class Classification; Attention Mechanism

Abstract

Brain tumor classification from Magnetic Resonance Imaging (MRI) remains challenging because of tumor heterogeneity, the overlapping intensity distribution of tumors, and the limited availability of medical images. This study introduces a lightweight deep learning model by integrating a Hybrid Channel–Spatial Attention (HCSA) module into the EfficientNet-B0 architecture for multi-class brain tumor classification. The HCSA module processes channels and spatial features sequentially to enhance feature representation by focusing on tumor-relevant information and better localizing the tumor region while maintaining computational efficiency. The proposed framework was evaluated on a publicly available Kaggle MRI brain tumor dataset, comprising 5,600 MRI images across 4 classes – glioma, meningioma, pituitary tumor and no-tumor. Comparative experiments were conducted with ResNet50, DenseNet121, EfficientNet-B0, and attention-enhanced EfficientNet models with identical preprocessing, data augmentation and training conditions. The proposed HCSA-EfficientNet-B0 model achieved a classification accuracy of 98.57%, an F1-score of 0.99, and an ROC-AUC value of 0.999 on the internal hold-out test set. Ablation results indicate that the combination of channel attention and spatial attention consistently outperforms each of the two attention mechanisms in isolation. Moreover, the proposed framework effectively captures the tumor-relevant regions, as suggested by Grad-CAM visualizations, which provide qualitative evidence supporting the interpretability of the classification results. The proposed framework is effective for multi-class brain tumor classification using MRI images and is able to improve classification performance while achieving computational efficiency.

References

  1. Sachdeva, Jainy, Deepanshu Sharma, and Chirag Kamal Ahuja. "Comparative Analysis of Different Deep Convolutional Neural Network Architectures for Classification of Brain Tumor on Magnetic Resonance Images." Archives of Computational Methods in Engineering 31, no. 4 (2024): 1959-1978.
  2. Babu Vimala, Baiju, Saravanan Srinivasan, Sandeep Kumar Mathivanan, Mahalakshmi, Prabhu Jayagopal, and Gemmachis Teshite Dalu. "Detection and Classification of Brain Tumor Using Hybrid Deep Learning Models." Scientific reports 13, no. 1 (2023): 23029.
  3. Pedada, Kameswara Rao, Bhujanga Rao, Kiran Kumar Patro, Jaya Prakash Allam, Mona M. Jamjoom, and Nagwan Abdel Samee. "A Novel Approach for Brain Tumour Detection Using Deep Learning Based Technique." Biomedical Signal Processing and Control 82 (2023): 104549.
  4. İncir, Ramazan, and Ferhat Bozkurt. "Improving Brain Tumor Classification with Combined Convolutional Neural Networks and Transfer Learning." Knowledge-Based Systems 299 (2024): 111981.
  5. Amarnath, Amarnath, Ali Al Bataineh, and Jeremy A. Hansen. "Transfer-Learning Approach for Enhanced Brain Tumor Classification in MRI Imaging." BioMedInformatics 4, no. 3 (2024): 1745-1756.
  6. Hassan, Elaheh, and Hamid Ghadiri. "Advancing brain tumor classification: A Robust Framework Using EfficientNetV2 Transfer Learning and Statistical Analysis." Computers in Biology and Medicine 185 (2025): 109542.
  7. Waskita, A. A., Julfa Muhammad Amda, Dwi Seno Kuncoro Sihono, and Heru Prasetio. "EfficientNetV2 based for MRI Brain Tumor Image Classification." In 2023 International Conference on Computer, Control, Informatics and its Applications (IC3INA), IEEE, 2023, 171-176.
  8. Zulfiqar, Fatima, Usama Ijaz Bajwa, and Yasar Mehmood. "Multi-Class Classification of Brain Tumor Types from MR Images Using EfficientNets." Biomedical Signal Processing and Control 84 (2023): 104777.
  9. Ghosh, Arpita, Badal Soni, and Ujwala Baruah. "Transfer Learning-Based Deep Feature Extraction Framework Using Fine-Tuned Efficientnet b7 for Multiclass Brain Tumor Classification." Arabian Journal for Science and Engineering 49, no. 9 (2024): 12027-12048.
  10. Anwar, Raja Waseem, Mohammad Abrar, and Faizan Ullah. "Transformative Transfer Learning for MRI Brain Tumor Precision: Innovative Insights." IEEe Access 13 (2025): 31749-31761.
  11. R. Preetha, M. J. P. Priyadarsini and J. S. Nisha, "Hybrid 3B Net and EfficientNetB2 Model for Multi-Class Brain Tumor Classification," in IEEE Access, vol. 13, 2025, 63465-63485.
  12. Pacal, Ishak, Omer Celik, Bilal Bayram, and Antonio Cunha. "Enhancing EfficientNetv2 with Global and Efficient Channel Attention Mechanisms for Accurate MRI-Based Brain Tumor Classification." Cluster Computing 27, no. 8 (2024): 11187-11212.
  13. Ferdousi, Sanjida, Utsha Das, and Tanvir Mahtab Zihan. "An Explainable Multi-Class Brain Tumor Classifier Using EfficientNetV2 with Hybrid Attention Mechanisms." In 2025 IEEE 2nd International Conference on Computing, Applications and Systems (COMPAS), IEEE, 2025, 1-6.
  14. Panigrahi, Soumyarashmi, Dibya Ranjan Das Adhikary, and Binod Kumar Pattanayak. "Hybrid Transfer Learning and Self-Attention Framework for Robust MRI-Based Brain Tumor Classification." Scientific Reports 15, no. 1 (2025): 21343.
  15. Celik, Fatih, Kemal Celik, and Ayse Celik. "Enhancing Brain Tumor Classification Through Ensemble Attention Mechanism." Scientific Reports 14, no. 1 (2024): 22260.
  16. Rai, Hari Mohan, Joon Yoo, and Serhii Dashkevych. "Two-headed UNetEfficientNets for Parallel Execution of Segmentation and Classification of Brain Tumors: Incorporating Postprocessing Techniques with Connected Component Labelling." Journal of Cancer Research and Clinical Oncology 150, no. 4 (2024): 220.
  17. P. Kumar Tiwary, P. Johri, A. Katiyar and M. K. Chhipa, "Deep Learning-Based MRI Brain Tumor Segmentation with EfficientNet-Enhanced UNet," in IEEE Access, vol. 13, 2025, 54920-54937.
  18. Preetha R, Jasmine Pemeena Priyadarsini M and Nisha J S, “Brain Tumor Segmentation Using Multi-Scale Attention U-Net with EfficientNetB4 Encoder for Enhanced MRI Analysis,” Sci. Rep., vol. 15, no. 1, Mar. 2025, 9914.
  19. Zarenia, Erfan, Amirhossein Akhlaghi Far, and Khosro Rezaee. "Automated Multi-Class MRI Brain Tumor Classification and Segmentation Using Deformable Attention and Saliency Mapping." Scientific Reports 15, no. 1 (2025): 8114.
  20. Priyadarshini, Pallavi, Priyadarshi Kanungo, and Tejaswini Kar. "Multigrade Brain Tumor Classification in MRI Images Using Fine Tuned EfficientNet." e-Prime-Advances in Electrical Engineering, Electronics and Energy 8 (2024): 100498.
  21. Irfani, Muhammad Daffa, and Untari Novia Wisesty. "Brain Tumor Classification Using EfficientNet-Based CNN Architecture in MRI Images." In 2025 International Conference on Data Science and Its Applications (ICoDSA), IEEE, 2025, 200-205.
  22. Isunuri, B. Venkateswarlu, and Jagadeesh Kakarla. "EfficientNet and Multi-Path Convolution with Multi-Head Attention Network for Brain Tumor Grade Classification." Computers and Electrical Engineering 108 (2023): 108700.
  23. Ishfaq, Qurat Ul Ain, Rozi Bibi, Abid Ali, Faisal Jamil, Yousaf Saeed, Rana Othman Alnashwan, Samia Allaoua Chelloug, and Mohammed Saleh Ali Muthanna. "Automatic Smart Brain Tumor Classification and Prediction System Using Deep Learning." Scientific reports 15, no. 1 (2025): 14876.
  24. 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.
  25. M. Nickparvar, “Brain Tumor MRI Dataset,” Kaggle, 2023. Available: https://www.kaggle.com/datasets/masoudnickparvar/brain-tumor-mri-dataset