Unimodal Cyclic Regularization for Training Multimodal Image Registration Networks
This work addresses a domain-specific problem in medical imaging by providing an incremental improvement for multimodal image registration, benefiting researchers and practitioners in healthcare and computer vision.
The paper tackled the problem of improving regularization in unsupervised multimodal image registration by proposing a unimodal cyclic regularization training pipeline that learns task-specific priors from simpler unimodal registration, resulting in better performance over conventional methods, particularly for severely deformed local regions in abdominal CT-MR registration.
The loss function of an unsupervised multimodal image registration framework has two terms, i.e., a metric for similarity measure and regularization. In the deep learning era, researchers proposed many approaches to automatically learn the similarity metric, which has been shown effective in improving registration performance. However, for the regularization term, most existing multimodal registration approaches still use a hand-crafted formula to impose artificial properties on the estimated deformation field. In this work, we propose a unimodal cyclic regularization training pipeline, which learns task-specific prior knowledge from simpler unimodal registration, to constrain the deformation field of multimodal registration. In the experiment of abdominal CT-MR registration, the proposed method yields better results over conventional regularization methods, especially for severely deformed local regions.