A Variational Bayesian Method for Similarity Learning in Non-Rigid Image Registration

Daniel Grzech, Mohammad Farid Azampour, Ben Glocker, Julia Schnabel, Nassir Navab, Bernhard Kainz, Loïc Le Folgoc; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 119-128

Abstract

We propose a novel variational Bayesian formulation for diffeomorphic non-rigid registration of medical images, which learns in an unsupervised way a data-specific similarity metric. The proposed framework is general and may be used together with many existing image registration models. We evaluate it on brain MRI scans from the UK Biobank and show that use of the learnt similarity metric, which is parametrised as a neural network, leads to more accurate results than use of traditional functions, e.g. SSD and LCC, to which we initialise the model, without a negative impact on image registration speed or transformation smoothness. In addition, the method estimates the uncertainty associated with the transformation. The code and the trained models are available in a public repository: https://github.com/dgrzech/learnsim.

Related Material

[pdf]
[bibtex]
@InProceedings{Grzech_2022_CVPR, author = {Grzech, Daniel and Azampour, Mohammad Farid and Glocker, Ben and Schnabel, Julia and Navab, Nassir and Kainz, Bernhard and Le Folgoc, Lo{\"\i}c}, title = {A Variational Bayesian Method for Similarity Learning in Non-Rigid Image Registration}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {119-128} }