Correlation Ratio for Unsupervised Learning of Multi-modal Deformable Registration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Xiaojian, Liu, Yihao, Wei, Shuwen, Carass, Aaron, Du, Yong, Chen, Junyu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910912831553536
author Chen, Xiaojian
Liu, Yihao
Wei, Shuwen
Carass, Aaron
Du, Yong
Chen, Junyu
author_facet Chen, Xiaojian
Liu, Yihao
Wei, Shuwen
Carass, Aaron
Du, Yong
Chen, Junyu
contents In recent years, unsupervised learning for deformable image registration has been a major research focus. This approach involves training a registration network using pairs of moving and fixed images, along with a loss function that combines an image similarity measure and deformation regularization. For multi-modal image registration tasks, the correlation ratio has been a widely-used image similarity measure historically, yet it has been underexplored in current deep learning methods. Here, we propose a differentiable correlation ratio to use as a loss function for learning-based multi-modal deformable image registration. This approach extends the traditionally non-differentiable implementation of the correlation ratio by using the Parzen windowing approximation, enabling backpropagation with deep neural networks. We validated the proposed correlation ratio on a multi-modal neuroimaging dataset. In addition, we established a Bayesian training framework to study how the trade-off between the deformation regularizer and similarity measures, including mutual information and our proposed correlation ratio, affects the registration performance.
format Preprint
id arxiv_https___arxiv_org_abs_2504_12265
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Correlation Ratio for Unsupervised Learning of Multi-modal Deformable Registration
Chen, Xiaojian
Liu, Yihao
Wei, Shuwen
Carass, Aaron
Du, Yong
Chen, Junyu
Image and Video Processing
In recent years, unsupervised learning for deformable image registration has been a major research focus. This approach involves training a registration network using pairs of moving and fixed images, along with a loss function that combines an image similarity measure and deformation regularization. For multi-modal image registration tasks, the correlation ratio has been a widely-used image similarity measure historically, yet it has been underexplored in current deep learning methods. Here, we propose a differentiable correlation ratio to use as a loss function for learning-based multi-modal deformable image registration. This approach extends the traditionally non-differentiable implementation of the correlation ratio by using the Parzen windowing approximation, enabling backpropagation with deep neural networks. We validated the proposed correlation ratio on a multi-modal neuroimaging dataset. In addition, we established a Bayesian training framework to study how the trade-off between the deformation regularizer and similarity measures, including mutual information and our proposed correlation ratio, affects the registration performance.
title Correlation Ratio for Unsupervised Learning of Multi-modal Deformable Registration
topic Image and Video Processing
url https://arxiv.org/abs/2504.12265