BRAIN-TUMOR CLASSIFICATION USING RESNET50 ENHANCED WITH SE AND CBAM ATTENTION MECHANISMS

(Received: 5-Dec.-2025, Revised: 15-Feb.-2026 , Accepted: 9-Mar.-2026)

Authors Nadia Shamsulddin Abdulsattar, Fatimah S. Abdulsattar,

Keywords #Brain Tumor #MRI #ResNet50 #Squeeze-and-Excitation (SE) #CBAM

Abstract MRI image classification of brain tumors is critical for accurate and early diagnosis. New developments in deep learning have revealed that inserting attention mechanisms into convolutional neural networks can greatly improve classification performance. The ECA attention mechanism is also introduced in this study. This work assesses the effectiveness of Squeeze-and-Excitation (SE) and Convolutional Block Attention Module (CBAM) sequentially integrated with the ResNet50 model, which increases classification accuracy, precision and recall when compared to the basic model, according to experimental results on two datasets for brain tumors. The suggested model employs attention mechanisms to focus valuable information selectively and suppress irrelevant information. The experiments are conducted on two datasets (Brain Tumor MRI and Brisc). The first dataset displays great improvements over basic CNN models, with precision, recall, accuracy, F1 score and AUC at 0.9914, 0.9903, 0.9945, 0.9908 and 0.9989, respectively. The second dataset gives the results for precision, recall, accuracy, F1 score and AUC at 0.9860, 0.9857, 0.9860, 0.9858 and 0.9985, respectively. From these results, the importance of attention mechanisms in deep-learning models for medical imaging is highlighted, which suggests that SE and CBAM modules can be available as more dependable and effective instruments for brain-tumor classification in clinical settings. Future studies should investigate transformer-based and hybrid attention techniques to enhance automated brain tumor categorization.

References

[1] P. Sapra, R. Singh and S. Khurana, "Brain Tumor MRI Detection Using Neural Network," Int. J. of Innovative Science and Modern Engineering (IJISME), vol. 1, no. 3, 2013.

[2] S. Zhang and G. Xu, "A Novel Approach for Brain Tumor MRI Detection Using MRI Images," Journal of Biomedical Science and Engineering, vol. 9, no. 10, pp. 44–52, 2016.

[3] M. Alfonse and A. B. M. Salem, "An Automatic Classification of Brain Tumor MRIs through MRI Using Support Vector Machine," Egyptian Computer Science Journal, vol. 40, no. 3, pp. 11-21, 2016.

[4] J. Amin, M. Sharif, M. Yasmin and S. L. Fernandes, "A Distinctive Approach in Brain Tumor MRI Detection and Classification Using MRI," Pattern Recognition Letters, vol. 139, pp. 118-127, 2017.

[5] H. Dong et al., "Automatic Brain Tumor MRI Detection and Segmentation Using U-Net Based Fully Convolutional Networks," Proc. Med. Image Understand. Anal., pp. 506–517, Cham: Springer, 2017.

[6] S. K. V. Rao and B. Lingappa, "Image Analysis for MRI-based Brain Tumor Detection Using Hybrid Segmentation and Deep Learning Classification Technique," Int. Journal of Intelligent Engineering and Systems, vol. 12, no. 5, pp. 170–179, DOI: 10.22266/IJIES2019.1031.06, 2019.

[7] M. Sajjad et al., "Multi-grade Brain Tumor MRI Classification Using Deep CNN with Extensive Data Augmentation," J. of Computational Science, vol. 30, pp. 174–182, 2019.

[8] N. Abiwinanda et al., "Brain Tumor MRI Classification Using Convolutional Neural Network," World Congr. Med. Phys. Biomed. Eng., pp. 183–189, Singapore: Springer, 2018.

[9] A. Samreen et al., "Brain Tumor MRI Detection by Using Convolution Neural Network," Int. J. Online Biomed. Eng., vol. 16, no. 13, DOI: 10.3991/ijoe.v16i13.18545, 2020.

[10] H. Alsaif et al., "A Novel Data Augmentation-based Brain Tumor MRI Detection Using Convolutional Neural Network," Applied Sciences, vol. 12, no. 8, DOI: 10.3390/app12083773, 2022.

[11] M. S. I. Khan et al., "Accurate Brain Tumor MRI Detection Using Deep Convolutional Neural Network," Computational and Structural Biotech. J., vol. 20, DOI: 10.1016/j.csbj.2022.08.039, 2022.

[12] A. B. Abdusalomov, M. Mukhiddinov and T. K. Whangbo, "Brain Tumor MRI Detection Based on Deep Learning Approaches and MRI," Cancers, vol. 15, no. 16, DOI: 10.3390/cancers15164172, 2023.

[13] S. Albawi et al., "Understanding of a Convolutional Neural Network," Proc. of the 2017 IEEE Int. Conf. on Engineering and Technology (ICET), pp. 1–6, Antalya, Turkey, Aug. 2017.

[14] I. H. Sarker, "Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions," SN Computer Sci., vol. 2, no. 6, DOI: 10.1007/s42979-021-00815-1, 2021.

[15] R. Yamashita et al., "Convolutional Neural Networks: An Overview and Application in Radiology," Insights Imaging, vol. 9, no. 4, DOI: 10.1007/s13244-018-0639-9, 2018.

[16] Z. Li et al., "A Survey of Convolutional Neural Networks: Analysis, Applications and Prospects," IEEE Trans. Neural Netw. Learn. Syst., vol. 33, no. 12, DOI: 10.1109/TNNLS.2021.3084827, 2022.

[17] L. Alzubaidi et al., "Review of Deep Learning: Concepts, CNN Architectures, Challenges, Applications, Future Directions," J. Big Data, vol. 8, no. 1, DOI: 10.1186/s40537-021-00444-8, 2021.

[18] S. Anantharajan et al., "MRI Brain Tumor MRI Detection Using Deep Learning and Machine Learning Approaches," Measurement: Sensors, vol. 31, DOI: 10.1016/j.measen.2024.101026, 2024.

[19] M. Toğaçar, B. Ergen and Z. Cömert, "Tumor Type Detection in Brain MR Images Using a Deep Model Developed with Hyper-column Technique, Attention Modules and Residual Blocks," Medical & Biological Engineering & Computing, vol. 59, no. 1, DOI: 10.1007/s11517-020-02290-x, 2021.

[20] M. B. Sahaai et al., "ResNet-50 Based Deep Neural Network Using Transfer Learning for Brain Tumor MRI Classification," AIP Conf. Proc., vol. 2463, DOI: 10.1063/5.0082328, 2022.

[21] O. O. Oladimeji et al., "Brain Tumor MRI Classification Using ResNet50-convolutional Block Attention Module," Applied Computing and Informatics, DOI: 10.1108/ACI-09-2023-0022, 2023.

[22] V. R. Raja et al., "Enhanced Brain Tumor MRI Analysis Integrating ResNet50 with CBAM," J. of Electrical Systems, vol. 20, no. 6s, DOI: 10.52783/jes.3272, May 2024.

[23] K. A. Huang et al., "Evaluating the Impact of Attention Mechanisms on a Fine-tuned Neural Network for MRI Tumor Classification," Cureus, vol. 17, no. 3, DOI: 10.7759/cureus.80872, Mar. 2025.

[24] R. K. Yadav et al., "A Model for Brain Tumor MRI Detection Using a Modified Convolution Layer ResNet-50," Indian J. of Information Sources and Services, vol. 14, no. 1, DOI: 10.51983/ijiss-2024.14.1.3753, 2024.

[25] M. A. Khan and R. B. Z. Auvee, "Comparative Analysis of Resource-efficient CNN Architectures for Brain Tumor MRI Classification," arXiv preprint, arXiv: 2411.15596, Nov. 2024.

[26] M. Fachrurrozi et al., "Improving the Performance for Automated Brain Tumor MRI Classification on Magnetic Resonance Imaging," IAES Int. J. of Artificial Intell., vol. 13, no. 2, pp. 1679–1686, 2024.

[27] M. Z. Khaliki et al., "Brain Tumor MRI Detection from Images and Comparison with Transfer Learning Methods," Scientific Reports, vol. 14, no. 1, DOI: 10.1038/s41598-024-52823-9, 2024.

[28] S. Asif et al., "Improving Effectiveness of Different Deep Transfer Learning-based Models for Detecting Brain Tumor MRIs from MR Images," IEEE Access, vol. 10, DOI: 10.1109/ACCESS.2022.3153306, 2022.

[29] S. Deepak et al., "Brain Tumor MRI Classification Using Deep CNN Features via Transfer Learning," Computers in Biology and Medicine, vol. 111, DOI: 10.1016/j.compbiomed.2019.103345, 2019.

[30] H. P. A. Tjahyaningtijas et al., "Brain Tumor MRI Classification in MRI Images Using En-CNN," Int. J. of Intelligent Engineering and Systems, vol. 14, no. 4, DOI: 10.22266/ijies2021.0831.38, 2021.

[31] J. Lin, L. Huang, L. Ding and S. Yan, "Deep Brain Tumor MRI Lesion Classification Network: A Hybrid Method Optimizing ResNet50 and EfficientNetB0 for Enhanced Feature Extraction," Fractal and Fractional, vol. 9, no. 9, Art. no. 614, DOI: 10.3390/fractalfract9090614, 2025.

[32] S. Yan, M. Feng and Y. Cai, "An Integrated Deep Learning Model with Enhanced EfficientNetB0 and MobileNetV1 for Diabetic Retinopathy Grading," Biomedical Signal Processing and Control, vol. 113, Art. no. 108915, DOI: 10.1016/j.bspc.2025.108915, 2026.

[33] S. J. Prashantha and H. N. Prakash, "Feature Level Fusion Framework for Brain MR Image Classification Using Supervised Deep Learning and Hand Crafted Features," Jordanian Journal of Computers and Information Technology (JJCIT), vol. 8, no. 4, pp. 314–330, Dec. 2022.

[34] S. Benbakreti et al., "Using ResNet18 in a Deep-learning Framework and Assessing the Effects of Adaptive Learning Rates in the Identification of Malignant Breast Masses in Mammograms," Jordanian Journal of Computers and Information Technology (JJCIT), vol. 10, no. 1, pp. 93–107, Mar. 2024.

[35] K. He, X. Zhang, S. Ren and J. Sun, "Deep Residual Learning for Image Recognition," arXiv preprint, arXiv: 1512.03385, 2015.

[36] J. Hu, L. Shen and G. Sun, "Squeeze-and-excitation Networks," Proc. of IEEE CVPR, DOI: 10.1109/CVPR.2018.00745, 2018.

[37] S. Woo et al., "CBAM: Convolutional Block Attention Module," Proc. ECCV, [Online], Available: https://arxiv.org/abs/1807.06521, 2018.

[38] M. Nickparvar, "Brain Tumor MRI Dataset," Kaggle, DOI: 10.34740/KAGGLE/DSV/2645886, 2021.

[39] A. Fateh et al., "BRISC: Annotated Dataset for Brain Tumor MRI Segmentation and Classification with Swin-HAFNet," arXiv preprint, arXiv: 2506.14318, 2025.

[40] M. Hossin and M. N. Sulaiman, "A Review on Evaluation Metrics for Data Classification Evaluations," Int. J. of Data Mining & Knowledge Management Process, vol. 5, no. 2, pp. 1–11, 2015.

[41] E. F. Gomes and R. S. Barbosa, "Deep Learning Approaches for Brain Tumor MRI Classification in MRI Scans: An Analysis of Model Interpretability," Applied Sciences, vol. 16, no. 2, Art. no. 831, DOI: 10.3390/app16020831, 2026.

[42] Q. Wang, B. Wu, P. Zhu, P. Li, W. Zuo and Q. Hu, "ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks," Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11534–11542, Seattle, USA, DOI: 10.1109/CVPR42600.2020.01155, 2020.

[43] R. R. Selvaraju et al., "Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization," Int. J. of Computer Vision, vol. 128, no. 2, pp. 336–359, Feb. 2020.