FiRework: Field Refinement Framework for Efficient Enhancement of Deformable Registration

TL;DR

FiRework is a novel unsupervised deformable registration framework that improves accuracy and efficiency by redesigning continuous deformation, requiring fewer recursion levels and supporting continuous inference, validated on brain MRI datasets.

Contribution

The paper introduces FiRework, a field refinement framework that enhances deformable registration accuracy and efficiency with a simplified recursive approach and continuous inference capability.

Findings

Outperforms existing registration networks on brain MRI datasets

Requires only one recursion during training, reducing computational load

Demonstrates superior registration accuracy and efficiency

Abstract

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.