Version 1
: Received: 21 October 2024 / Approved: 23 October 2024 / Online: 23 October 2024 (16:01:03 CEST)
How to cite:
Sarshar, N. T.; Sadeghi, S.; Kamsari, M.; Avazpour, M.; Ghoushchi, S. J.; Ranjbarzadeh, R. Advancing Brain MRI Images Classification: Integrating VGG16 and ResNet50 with a Multi-verse Optimization Method. Preprints2024, 2024101858. https://doi.org/10.20944/preprints202410.1858.v1
Sarshar, N. T.; Sadeghi, S.; Kamsari, M.; Avazpour, M.; Ghoushchi, S. J.; Ranjbarzadeh, R. Advancing Brain MRI Images Classification: Integrating VGG16 and ResNet50 with a Multi-verse Optimization Method. Preprints 2024, 2024101858. https://doi.org/10.20944/preprints202410.1858.v1
Sarshar, N. T.; Sadeghi, S.; Kamsari, M.; Avazpour, M.; Ghoushchi, S. J.; Ranjbarzadeh, R. Advancing Brain MRI Images Classification: Integrating VGG16 and ResNet50 with a Multi-verse Optimization Method. Preprints2024, 2024101858. https://doi.org/10.20944/preprints202410.1858.v1
APA Style
Sarshar, N. T., Sadeghi, S., Kamsari, M., Avazpour, M., Ghoushchi, S. J., & Ranjbarzadeh, R. (2024). Advancing Brain MRI Images Classification: Integrating VGG16 and ResNet50 with a Multi-verse Optimization Method. Preprints. https://doi.org/10.20944/preprints202410.1858.v1
Chicago/Turabian Style
Sarshar, N. T., Saeid Jafarzadeh Ghoushchi and Ramin Ranjbarzadeh. 2024 "Advancing Brain MRI Images Classification: Integrating VGG16 and ResNet50 with a Multi-verse Optimization Method" Preprints. https://doi.org/10.20944/preprints202410.1858.v1
Abstract
This research presents a novel methodology for classifying MRI images into two categories: tumor and non-tumor. The study utilizes a combination of two advanced Convolutional Neural Network (CNN) architectures, VGG16 and ResNet50, to address the challenges in analyzing the complexity and variability of brain MRI scans. The approach begins with a comprehensive preprocessing phase, where the MRI images are enhanced through techniques such as resizing, grayscale conversion, Gaussian blurring, and brain area isolation. Central to the approach is the application of the Multi-verse Optimizer (MVO), a metaheuristic algorithm inspired by theories of the multi-verse in physics. The MVO is utilized to optimize the parameters for data augmentation and to fine-tune the combination of trainable layers within the VGG16 and ResNet50 models. The results of this study indicate a high level of effectiveness of the combined CNN models, significantly enhanced by the MVO, in classifying MRI images. These models show marked improvements in accuracy, precision, and recall, underscoring their potential utility in enhancing brain tumor diagnosis. The paper concludes with an analysis of these findings, emphasizing the importance of this approach in medical imaging and suggesting potential avenues for future research in the area of automated MRI classification.
Keywords
Brain Tumor Classification; MRI Image Analysis; Optimization; Deep Learning; Data Augmentation; Multi-verse Optimizer.
Subject
Computer Science and Mathematics, Computer Vision and Graphics
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.