# Non-rigid image registration using spatially region-weighted correlation ratio and GPU-acceleration

Source: [Non-rigid image registration using spatially region-weighted correlation ratio and GPU-acceleration](<https://www.sota2.com/research/paper/68fa7d861e209131cea93771>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T06:23:26.944Z

Authors: Lun Gong, Cheng Zhang, Luwen Duan, Xueying Du, Hanqiu Liu, Xinjian Chen, Jian Zheng

Published: 2018-04-13T09:13:41.000Z

## Abstract

Objective: Non-rigid image registration with high accuracy and efficiency is still a challenging task for medical image analysis. In this work, we present the spatially region-weighted correlation ratio (SRWCR) as a novel similarity measure to improve the registration performance. Methods: SRWCR is rigorously deduced from a three-dimension joint probability density function combining the intensity channels with an extra spatial information channel. SRWCR estimates the optimal functional dependence between the intensities for each spatial bin, in which the spatial distribution modeled by a cubic B-spline function is used to differentiate the contribution of voxels. We also analytically derive the gradient of SRWCR with respect to the transformation parameters and optimize it using a quasi-Newton approach. Furthermore, we propose a GPU-based parallel mechanism to accelerate the computation of SRWCR and its derivatives. Results: The experiments on synthetic images, public 4-D thoracic computed tomography (CT) dataset, retinal optical coherence tomography (OCT) data, and clinical CT and positron emission tomography (PET) images confirm that SRWCR significantly outperforms some state-of-the-art techniques such as spatially encoded mutual information and Robust PaTch-based cOrrelation Ration. Conclusion: This study demonstrates the advantages of SRWCR in tackling the practical difficulties due to distinct intensity changes, serious speckle noise, or different imaging modalities. Significance: The proposed registration framework might be more reliable to correct the non-rigid deformations and more potential for clinical applications.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Medical Image Registration on CERMEP-IDB-MRXFDG Head MRI-CT (test)](<https://www.sota2.com/research/sota/medical-image-registration-on-cermep-idb-mrxfdg-head-mri-ct-test.md>): Medical Image Registration; CERMEP-IDB-MRXFDG Head MRI-CT (test); MAE: 76.89.

- [Medical Image Registration on Learn2Reg Abdomen MRI-CT 2021 (test)](<https://www.sota2.com/research/sota/medical-image-registration-on-learn2reg-abdomen-mri-ct-2021-test.md>): Medical Image Registration; Learn2Reg Abdomen MRI-CT 2021 (test); Dice Score: 89.

- [Medical Image Registration on IXI Head MRI T2-PD (test)](<https://www.sota2.com/research/sota/medical-image-registration-on-ixi-head-mri-t2-pd-test.md>): Medical Image Registration; IXI Head MRI T2-PD (test); TRE: 0.3.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1804.05061>)

[PDF](<https://arxiv.org/pdf/1804.05061.pdf>)
