LEVERAGING RESNET50 AND XCEPTION FOR ACCURATE BRAIN TUMOR CLASSIFICATION IN MRI SCANS
DOI: 
SHARE THIS ARTICLE
DOWNLOAD ARTICLE
REVIEW REPORT
CITE THIS ARTICLE
For improved treatment and increased chances of survival, brain tumors should be detected early and accurately. Comparing the two most popular convolutional neural networks for automated brain tumor identification from MRI brain scan images: ResNet50 and Xception. A variety of tumor forms under various scanning circumstances were included in the publicly accessible MRI data. Both models were adjusted to the requirements of the medical imaging environment using transfer learning techniques. Accuracy, precision, recall, F1-score, and AUC-ROC score were used to assess the test findings.The studies’ findings indicate that both models performed exceptionally well in classification, with ResNet50 exhibiting stronger convergence and stability against overfitting and Xception registering somewhat higher generalization over complicated tumor presentations. By analyzing each model’s advantages and disadvantages, the study shed light on how deep learning
Keywords
Article Information
Article Metrics
HOW TO CITE
Copy
Bhattacharyya, A., Uddin, M. I., Mondal, A. & Pyne, R. (2026). Leveraging ResNet50 and Xception for Accurate Brain Tumor Classification in MRI Scans. International Journal of Science, Strategic Management and Technology, 02(05). https://doi.org/10.55041/ijsmt.v2i4.637
Bhattacharyya, Aritra, et al.. "Leveraging ResNet50 and Xception for Accurate Brain Tumor Classification in MRI Scans." International Journal of Science, Strategic Management and Technology, vol. 02, no. 05, 2026, pp. . doi:https://doi.org/10.55041/ijsmt.v2i4.637.
Bhattacharyya, Aritra,Md Uddin,Ayan Mondal, and Ria Pyne. "Leveraging ResNet50 and Xception for Accurate Brain Tumor Classification in MRI Scans." International Journal of Science, Strategic Management and Technology 02, no. 05 (2026). https://doi.org/https://doi.org/10.55041/ijsmt.v2i4.637.
References
2.Hemanth and M. Anitha, “Deep Learning-Based Brain Tumor Detec-tion and Classification Using ResNet50 and Xception Models,” Comput. Biol. Med., vol. 131, p. 104248, Jan. 2021.
3.Afshar, A. Mohammadi, M. Plataniotis, and K. N. Plataniotis, “Brain Tumor Type Classification via Capsule Networks,” Proc. IEEE ICASSP,1368–1372, 2019.
4.Tandel et al., “A Review on a Deep Learning Perspective in Brain Tumor Classification and Segmentation,” Comput. Biol. Med., vol. 131,104248, Jan. 2021.
5.Amin et al., “Brain Tumor Classification Based on Deep Fea-tures Extracted by ResNet50 and Xception,” IEEE Access, vol. 9, pp. 90112–90120, 2021.
6.Aslam, T. Khan, and S. Khan, “Comparative Analysis of CNN Architectures for Brain Tumor Detection in MRI,” IEEE Int. Conf. Bioinformatics and Biomedicine, pp. 1180–1184, 2020.
7.Jain, S. S. Tiwari, and M. M. Rathore, “Hybrid Deep Learning Model for Brain Tumor Detection Using MRI Images,” Multimedia Tools Appl., vol. 80, pp. 8091–8107, 2021.
8.Rehman et al., “Classification of Brain Tumor MRIs Using Deep Learning Based CNNs,” Proc. IEEE Int. Conf. Eng. Tech. (ICET), pp. 1–6, 2020.
Ethics and Compliance
Indexed In
Similar Articles
Previous Article
