Learning Diffeomorphic and Modality-invariant Registration using B-splines

Huaqi Qiu, Chen Qin, Andreas Schuh, Kerstin Hammernik, Daniel Rueckert
Proceedings of the Fourth Conference on Medical Imaging with Deep Learning, PMLR 143:645-664, 2021.

Abstract

We present a deep learning (DL) registration framework for fast mono-modal and multi-modal image registration using differentiable mutual information and diffeomorphic B-spline free-form deformation (FFD). Deep learning registration has been shown to achieve competitive accuracy and significant speedups from traditional iterative registration methods. In this paper, we propose to use a B-spline FFD parameterisation of Stationary Velocity Field (SVF) to in DL registration in order to achieve smooth diffeomorphic deformation while being computationally-efficient. In contrast to most DL registration methods which use intensity similarity metrics that assume linear intensity relationship, we apply a differentiable variant of a classic similarity metric, mutual information, to achieve robust mono-modal and multi-modal registration. We carefully evaluated our proposed framework on mono- and multi-modal registration using 3D brain MR images and 2D cardiac MR images.

Cite this Paper

BibTeX
@InProceedings{pmlr-v143-qiu21a, title = {Learning Diffeomorphic and Modality-invariant Registration using B-splines}, author = {Qiu, Huaqi and Qin, Chen and Schuh, Andreas and Hammernik, Kerstin and Rueckert, Daniel}, booktitle = {Proceedings of the Fourth Conference on Medical Imaging with Deep Learning}, pages = {645--664}, year = {2021}, editor = {Heinrich, Mattias and Dou, Qi and de Bruijne, Marleen and Lellmann, Jan and Schläfer, Alexander and Ernst, Floris}, volume = {143}, series = {Proceedings of Machine Learning Research}, month = {07--09 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v143/qiu21a/qiu21a.pdf}, url = {https://proceedings.mlr.press/v143/qiu21a.html}, abstract = {We present a deep learning (DL) registration framework for fast mono-modal and multi-modal image registration using differentiable mutual information and diffeomorphic B-spline free-form deformation (FFD). Deep learning registration has been shown to achieve competitive accuracy and significant speedups from traditional iterative registration methods. In this paper, we propose to use a B-spline FFD parameterisation of Stationary Velocity Field (SVF) to in DL registration in order to achieve smooth diffeomorphic deformation while being computationally-efficient. In contrast to most DL registration methods which use intensity similarity metrics that assume linear intensity relationship, we apply a differentiable variant of a classic similarity metric, mutual information, to achieve robust mono-modal and multi-modal registration. We carefully evaluated our proposed framework on mono- and multi-modal registration using 3D brain MR images and 2D cardiac MR images.} }
Endnote
%0 Conference Paper %T Learning Diffeomorphic and Modality-invariant Registration using B-splines %A Huaqi Qiu %A Chen Qin %A Andreas Schuh %A Kerstin Hammernik %A Daniel Rueckert %B Proceedings of the Fourth Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2021 %E Mattias Heinrich %E Qi Dou %E Marleen de Bruijne %E Jan Lellmann %E Alexander Schläfer %E Floris Ernst %F pmlr-v143-qiu21a %I PMLR %P 645--664 %U https://proceedings.mlr.press/v143/qiu21a.html %V 143 %X We present a deep learning (DL) registration framework for fast mono-modal and multi-modal image registration using differentiable mutual information and diffeomorphic B-spline free-form deformation (FFD). Deep learning registration has been shown to achieve competitive accuracy and significant speedups from traditional iterative registration methods. In this paper, we propose to use a B-spline FFD parameterisation of Stationary Velocity Field (SVF) to in DL registration in order to achieve smooth diffeomorphic deformation while being computationally-efficient. In contrast to most DL registration methods which use intensity similarity metrics that assume linear intensity relationship, we apply a differentiable variant of a classic similarity metric, mutual information, to achieve robust mono-modal and multi-modal registration. We carefully evaluated our proposed framework on mono- and multi-modal registration using 3D brain MR images and 2D cardiac MR images.
APA
Qiu, H., Qin, C., Schuh, A., Hammernik, K. & Rueckert, D.. (2021). Learning Diffeomorphic and Modality-invariant Registration using B-splines. Proceedings of the Fourth Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 143:645-664 Available from https://proceedings.mlr.press/v143/qiu21a.html.

Related Material