mlVIRNET: Multilevel Variational Image Registration Network

Abstract

We present a novel multilevel approach for deep learning based image registration. Recently published deep learning based registration methods have shown promising results for a wide range of tasks. However, these algorithms are still limited to relatively small deformations. Our method addresses this shortcoming by introducing a multilevel framework, which computes deformation fields on different scales, similar to conventional methods. Thereby, a coarse-level alignment is obtained first, which is subsequently improved on finer levels. We demonstrate our method on the complex task of inhale-to-exhale lung registration. We show that the use of a deep learning multilevel approach leads to significantly better registration results.

arXiv commentaccepted for publication at MICCAI 2019

References in corpus (4)

• A Deep Learning Framework for Unsupervised Affine and Deformable Image Registration
• An Unsupervised Learning Model for Deformable Medical Image Registration
• Label-driven weakly-supervised learning for multimodal deformable image registration
• Estimation of Large Motion in Lung CT by Integrating Regularized Keypoint Correspondences into Dense Deformable Registration

Cited by in corpus (3)

• Medical image registration using unsupervised deep neural network: A scoping literature review
• Learning Deformable Image Registration from Optimization: Perspective, Modules, Bilevel Training and Beyond
• Non-iterative Coarse-to-fine Registration based on Single-pass Deep Cumulative Learning