Volume 22, Issue 2 (JIAEEE Vol.22 No.2 2025)
Journal of Iranian Association of Electrical and Electronics Engineers 2025, 22(2): 0-0 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Mavaddati S, Azhari Lamraski H S. Brain Tumor Detection and Classification Based on MRI Images Using Deep Learning and Transfer Learning Models. Journal of Iranian Association of Electrical and Electronics Engineers 2025; 22 (2)
URL: http://jiaeee.com/article-1-1782-en.html
URL: http://jiaeee.com/article-1-1782-en.html
University of Mazandaran
Abstract: (198 Views)
Brain tumors are among the most common and fatal types of cancer. Accurate and timely diagnosis of these tumors is essential for disease management and successful patient prognosis. Additionally, the precise identification of the tumor type is crucial in determining the treatment path. By recognizing the type of tumor, doctors can select the most appropriate treatment method, which may include surgery, radiation therapy, chemotherapy, or a combination of these methods. Furthermore, the tumor type helps predict disease progression and the quality of life post-treatment. In recent years, deep learning has been a powerful tool for various image-processing tasks, including brain tumor detection. In this paper, various deep learning models such as CNN, RNN, VGG16, InceptionV3, and ResNet101 are evaluated for classifying brain tumor types from the Figshare dataset based on MRI images of glioma, meningioma, pituitary tumors, and no tumor. Finally, a suitable deep model based on ResNet101 combined with transfer learning is proposed. Based on various metrics and statistical tests, the findings indicate that deep learning models can be effectively used for brain tumor detection. Among these, the ResNet101 model achieved an accuracy of 98.37% in classifying the four tumor classes. This study demonstrates that deep learning holds significant potential for improving brain tumor detection accuracy.
Keywords: Brain tumor detection, Deep learning, Transfer learning, Figshare dataset, Image processing, ResNet101, Deep neural network.
Send email to the article author
| Rights and permissions | |
 |
This Journal is an open access Journal Licensed under the Creative Commons Attribution-NonCommercial 4.0 International License. (CC BY NC 4.0) |
