Fast Deformable Image Registration With Non-Smooth Dual Optimization

Martin Rajchl, John S.H Baxter, Wu Qiu, Ali R. Khan, Aaron Fenster, Terry M. Peters, Daniel Rueckert, Jing Yuan; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2016, pp. 25-32

Abstract


Optimization techniques have been widely used in deformable registration, allowing for the incorporation of similarity metrics with regularization mechanisms. These regularization mechanisms are designed to mitigate the effects of trivial solutions to ill-posed registration problems and to otherwise ensure the resulting deformation fields are well-behaved. This paper introduces a novel deformable registration (DR) algorithm, RANCOR, which uses iterative convexification to address deformable registration problems under non-smooth total-variation regularization. Initial comparative results against four state-of-the-art registration algorithms and under smooth regularization, respectively, are presented using the Internet Brain Segmentation Repository (IBSR) database.

Related Material


[pdf]
[bibtex]
@InProceedings{Rajchl_2016_CVPR_Workshops,
author = {Rajchl, Martin and Baxter, John S.H and Qiu, Wu and Khan, Ali R. and Fenster, Aaron and Peters, Terry M. and Rueckert, Daniel and Yuan, Jing},
title = {Fast Deformable Image Registration With Non-Smooth Dual Optimization},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2016}
}