mlVIRNET: Multilevel Variational Image Registration Network

A. Hering, B. van Ginneken and S. Heldmann

Medical Image Computing and Computer-Assisted Intervention 2019;11769:257-265.

DOI arXiv Cited by ~54

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.