Enhanced Gan-Based Data Augmentation for Multimodal Medical Images Registration

Zarif, Sameh; Amin, Khalid M.; George, Maryam; Hadhoud, Mohy; Wagdy, Marian

doi:10.21608/ijci.2025.337581.1186

	Enhanced Gan-Based Data Augmentation for Multimodal Medical Images Registration
IJCI. International Journal of Computers and Information
Article 5, Volume 12, Issue 2, July 2025, Page 47-59 PDF (1.38 MB)
Document Type: Original Article
DOI: 10.21608/ijci.2025.337581.1186
View on SCiNiTO
Authors
Sameh Zarif ¹; Khalid M. Amin ²; Maryam George³; Mohy Hadhoud⁴; Marian Wagdy⁵
¹Faculty of computers and information, Menofia university
²Information technology dept., Faculty of computers and information, Menofia university
³Information Technology Department Menofia University
⁴Department of information technology, Faculty of computers and Information, Menofia University
⁵Department of Information Technology, Faculty of Computers and Information
Abstract
Data augmentation is a crucial technique for enhancing the generalization of deep learning registration models, especially in the medical imaging domain, where high-quality and diverse multimodal data are often scarce. Prior multimodal registration approaches faced multiple limitations, such as intricate implementation processes and overfitting, which reduce the generalizability of the models and impact registration accuracy. These limitations underscore the need for improved methodologies to enhance the effectiveness of medical image analysis by advancing the progressive GAN framework that synthesizes high-quality multimodal medical images. In this study, we propose an approach based on Generative Adversarial Networks (GANs) to improve the quality and diversity of multimodal medical images. Our methodology includes preprocessing steps, real-time modifications during GAN training, and post-processing techniques to enhance the generated images. The results demonstrate that the proposed method outperforms traditional registration techniques, achieving a mean Dice Similarity Coefficient of 0.78, indicating a significant improvement in registration accuracy. These findings support the potential application of our approach in clinical settings, enhancing the effectiveness of medical image analysis.
Keywords
Gan Augmentation; Image Registration; Multimodal Images; Unsupervised Learning; Medical Image Analysis


Statistics Article View: 124 PDF Download: 60