"Adaptive Stochastic Gradient Descent Optimisation for Image Registration"

Stefan Klein, Josien P.W. Pluim, Marius Staring and Max A. Viergever


We present a stochastic gradient descent optimisation method for image registration with adaptive step size prediction. The method is based on the theoretical work by Plakhov and Cruz (2004). Our main methodological contribution is the derivation of an image-driven mechanism to select proper values for the most important free parameters of the method. The selection mechanism employs general characteristics of the cost functions that commonly occur in intensity-based image registration. Also, the theoretical convergence conditions of the optimisation method are taken into account. The proposed adaptive stochastic gradient descent (ASGD) method is compared to a standard, non-adaptive Robbins-Monro (RM) algorithm. Both ASGD and RM employ a stochastic subsampling technique to accelerate the optimisation process. Registration experiments were performed on 3D CT and MR data of the head, lungs, and prostate, using various similarity measures and transformation models. The results indicate that ASGD is robust to these variations in the registration framework and is less sensitive to the settings of the user-defined parameters than RM. The main disadvantage of RM is the need for a predetermined step size function. The ASGD method provides a solution for that issue.



PDF (20 pages, 611 kB) click to start download
From publisher link

Copyright © 2009 by the authors. Published version © 2009 by Springer. Personal use of this material is permitted. However, permission to reprint or republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works, must be obtained from the copyright holder.


Source code

The source code of the methods described in this paper can be found in the image registration toolkit elastix, available at http://elastix.isi.uu.nl.

The optimizer can be selected through: (Optimizer "AdaptiveStochasticGradientDescent").

BibTeX entry

author = "{Stefan Klein and Josien P.W. Pluim and Marius Staring and Max A. Viergever}",
title = "{Adaptive Stochastic Gradient Descent Optimisation for Image Registration}",
journal = "{International Journal of Computer Vision}",
volume = "{81}",
number = "{3}",
pages = "{227 - 239}",
month = "{March}",
year = "{2009}",

last modified: 13-11-2012 |webmaster |Copyright 2004-2019 © by Marius Staring