Large Deformation Diffeomorphic Image Registration with Laplacian Pyramid Networks

Tony C. W. Mok, Albert C. S. Chung
6/29/2020
eess.IVcs.CV

Official code: cwmok/LapIRN (145 stars, MIT, last commit 2023-07-20).

Abstract

Deep learning-based methods have recently demonstrated promising results in deformable image registration for a wide range of medical image analysis tasks. However, existing deep learning-based methods are usually limited to small deformation settings, and desirable properties of the transformation including bijective mapping and topology preservation are often being ignored by these approaches. In this paper, we propose a deep Laplacian Pyramid Image Registration Network, which can solve the image registration optimization problem in a coarse-to-fine fashion within the space of diffeomorphic maps. Extensive quantitative and qualitative evaluations on two MR brain scan datasets show that our method outperforms the existing methods by a significant margin while maintaining desirable diffeomorphic properties and promising registration speed.

View on arXivView PDF

Code Implementations(1)

cwmok/LapIRNOfficial100%
MIT

Large Deformation Diffeomorphic Image Registration with Laplacian Pyramid Networks

14525PythonNov 4, 20203 years agoMIT

Similar Papers

A Symmetric Dynamic Learning Framework for Diffeomorphic Medical Image Registration

89% match2024

Learning Homeomorphic Image Registration via Conformal-Invariant Hyperelastic Regularisation

89% match2023

An Unsupervised Learning Model for Deformable Medical Image Registration

89% match1 repo532018

NimbleReg: A light-weight deep-learning framework for diffeomorphic image registration

88% match2025

Conditional Deformable Image Registration with Convolutional Neural Network

88% match2 repos1452021

Fast Diffeomorphic Image Registration using Patch based Fully Convolutional Networks

88% match2024

Cite this paper

@article{mok2020large,
  title  = {Large Deformation Diffeomorphic Image Registration with Laplacian Pyramid Networks},
  author = {Tony C. W. Mok and Albert C. S. Chung},
  year   = {2020},
  eprint = {2006.16148},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2006.16148}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2006.16148.svg)](https://codeofpaper.com/paper/2006.16148)

Discussion