Issue |
ITM Web Conf.
Volume 70, 2025
2024 2nd International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2024)
|
|
---|---|---|
Article Number | 03014 | |
Number of page(s) | 10 | |
Section | Image Processing and Computer Vision | |
DOI | https://doi.org/10.1051/itmconf/20257003014 | |
Published online | 23 January 2025 |
Enhancing Brain Tumor Detection: A Comparative Study of CNN Architectures Using MRI Data
School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, Hubei, 430074, China
Corresponding author: U202215216@hust.edu.cn
Deep learning models have become essential for automated medical image analysis in brain tumor detection. Existing Convolutional Neural Network (CNN) models like Visual Geometry Group 19 (VGG19), Residual Network 18 (ResNet18), and Residual Network 34 (ResNet34), despite their success in image classification and recognition, face challenges such as unclear boundary detection, limited generalization, and lower computational efficiency in detecting brain tumors. To address these issues, this study introduces VGG19-Brain’s MRI for Tumor (BMT), an enhanced version of the classic VGG19 model. VGG19-BMT incorporates targeted optimizations, including adjustments to convolutional layers and improved feature extraction modules. A systematic comparative analysis of VGG19-BMT and traditional CNN models was conducted using the Kaggle dataset “Brain MRI Images for Brain Tumor Detection.” The results demonstrate that VGG19-BMT outperforms conventional models’ boundary recognition accuracy, generalization, and computational efficiency, providing a more effective solution for automated brain tumor detection. This advancement not only enhances diagnostic capabilities but also sets the stage for future model improvements and clinical applications in medical imaging.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.