DiffOp-net: A Differential Operator-based Fully Convolutional Network for Unsupervised Deformable Image Registration

arXiv:2404.04244v1 Announce Type: new
Abstract: Existing unsupervised deformable image registration methods usually rely on metrics applied to the gradients of predicted displacement or velocity fields as a regularization term to ensure transformation smoothness, which potentially limits registration accuracy. In this study, we propose a novel approach to enhance unsupervised deformable image registration by introducing a new differential operator into the registration framework. This operator, acting on the velocity field and mapping it to a dual space, ensures the smoothness of …

abstract accuracy arxiv cs.cv differential fields image metrics network novel registration regularization study transformation type unsupervised