Robust deformable image registration using synthetic data and transfer learning

Deep learning models have recently achieved accuracy comparable to traditional iterative methods for deformable image registration. However, their performance often degrades when test data deviate from the training distribution, for example due to changes in imaging protocols or subject demographics. While data augmentation can improve robustness, it may not account for all types of domain shifts, particularly those that are unpredictable. To address this limitation, recent approaches have explored training on synthetic images with diverse structures and intensities to promote generalization across modalities and anatomical regions. Nevertheless, the robustness of such models to other types of domain shifts, and their adaptability to specific registration tasks, remains unclear.
In this study, we investigate whether transfer learning can enhance registration model robustness under unforeseen domain shifts. We first train a generic, weakly supervised model on synthetic data, then fine-tune it on target domains. Specifically, we examine: (1) how design factors in synthetic data influence cross-domain performance (e.g., brain MRI vs. lung CT); (2) the efficiency of fine-tuning compared to training from scratch; and (3) the robustness of fine-tuned models on previously unseen datasets. Our results show that the fine-tuned model achieved the most consistent registration performance across datasets. It also required fewer training epochs and less target domain data than from-scratch training. Furthermore, while the use of random geometric shapes and dynamic contrast in the synthetic data was critical for cross-domain performance, we found that different target domains may benefit from different synthetic data. These findings support transfer learning as a promising strategy to improve robustness to diverse domain shifts in deformable image registration.