Nonrigid image registration using multi-scale 3D convolutional neural networks

Conference paper (2017)

Authors

Hessam Sokooti Leiden University Medical Center
Bob D. De Vos University Medical Center Utrecht
Floris Berendsen Leiden University Medical Center
B.P.F. Lelieveldt Pattern Recognition and Bioinformatics - EEMCS
Ivana Išgum University Medical Center Utrecht
M. Staring Pattern Recognition and Bioinformatics - EEMCS , Leiden University Medical Center
Research Group
Pattern Recognition and Bioinformatics (EEMCS) (TU Delft)
Image registration Multi-scale analysis Convolutional neural networks Chest CT
More Info
expand_more

Published Date

2017

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Department

Intelligent Systems

Research Group

Pattern Recognition and Bioinformatics

Abstract

In this paper we propose a method to solve nonrigid image registration through a learning approach, instead of via iterative optimization of a predefined dissimilarity metric. We design a Convolutional Neural Network (CNN) architecture that, in contrast to all other work, directly estimates the displacement vector field (DVF) from a pair of input images. The proposed RegNet is trained using a large set of artificially generated DVFs, does not explicitly define a dissimilarity metric, and integrates image content at multiple scales to equip the network with contextual information. At testing time nonrigid registration is performed in a single shot, in contrast to current iterative methods. We tested RegNet on 3D chest CT follow-up data. The results show that the accuracy of RegNet is on par with a conventional B-spline registration, for anatomy within the capture range. Training RegNet with artificially generated DVFs is therefore a promising approach for obtaining good results on real clinical data, thereby greatly simplifying the training problem. Deformable image registration can therefore be successfully casted as a learning problem.