FiRework: Field Refinement Framework for Efficient Enhancement of Deformable Registration
This work addresses efficiency and accuracy issues in deformable registration for clinical practice, though it appears incremental as it enhances existing networks.
The paper tackles the challenge of deformable image registration by proposing FiRework, a field refinement framework that reduces accumulated errors and interpolation inaccuracies in deep learning-based methods, achieving superior performance on brain MRI datasets with only one level of recursion during training.
Deformable image registration remains a fundamental task in clinical practice, yet solving registration problems involving complex deformations remains challenging. Current deep learning-based registration methods employ continuous deformation to model large deformations, which often suffer from accumulated registration errors and interpolation inaccuracies. Moreover, achieving satisfactory results with these frameworks typically requires a large number of cascade stages, demanding substantial computational resources. Therefore, we propose a novel approach, the field refinement framework (FiRework), tailored for unsupervised deformable registration, aiming to address these challenges. In FiRework, we redesign the continuous deformation framework to mitigate the aforementioned errors. Notably, our FiRework requires only one level of recursion during training and supports continuous inference, offering improved efficacy compared to continuous deformation frameworks. We conducted experiments on two brain MRI datasets, enhancing two existing deformable registration networks with FiRework. The experimental results demonstrate the superior performance of our proposed framework in deformable registration. The code is publicly available at https://github.com/ZAX130/FiRework.