Fine-Tuning Cycle-GAN for Domain Adaptation of MRI Images

2026-01-18

AI Summary

This work addresses the performance degradation of deep learning models on MRI images due to domain shift arising from differences in acquisition institutions or scanners. To mitigate this issue, the authors propose an enhanced unsupervised domain adaptation method built upon the CycleGAN framework, which jointly optimizes content and discrepancy losses to enable bidirectional translation between source and target domain MRI images without requiring paired data. The approach effectively preserves anatomical structural consistency during domain translation. Experimental results across multiple MRI datasets demonstrate that the proposed method significantly reduces inter-domain distributional divergence, thereby improving model generalization and diagnostic accuracy.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Adversarial Attacks & Robustness
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Magnetic Resonance Imaging (MRI) scans acquired from different scanners or institutions often suffer from domain shifts owing to variations in hardware, protocols, and acquisition parameters. This discrepancy degrades the performance of deep learning models trained on source domain data when applied to target domain images. In this study, we propose a Cycle-GAN-based model for unsupervised medical-image domain adaptation. Leveraging CycleGANs, our model learns bidirectional mappings between the source and target domains without paired training data, preserving the anatomical content of the images. By leveraging Cycle-GAN capabilities with content and disparity loss for adaptation tasks, we ensured image-domain adaptation while maintaining image integrity. Several experiments on MRI datasets demonstrated the efficacy of our model in bidirectional domain adaptation without labelled data. Furthermore, research offers promising avenues for improving the diagnostic accuracy of healthcare. The statistical results confirm that our approach improves model performance and reduces domain-related variability, thus contributing to more precise and consistent medical image analysis.

Problem

• domain shift
• MRI
• domain adaptation
• medical image analysis
• unsupervised learning

Innovation

• Cycle-GAN
• domain adaptation
• unsupervised learning
• MRI
• content preservation