Adaptive stochastic gradient descent optimisation for image registration

S. Klein, J.P.W. Pluim, M. Staring, M.A. Viergever

Research output: Contribution to journalArticleAcademicpeer-review

309 Citations (Scopus)
358 Downloads (Pure)


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 (J. Math. Sci. 120(1):964-973, 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.
Original languageEnglish
Pages (from-to)227-239
Number of pages13
JournalInternational Journal of Computer Vision
Issue number3
Publication statusPublished - 2009


Dive into the research topics of 'Adaptive stochastic gradient descent optimisation for image registration'. Together they form a unique fingerprint.

Cite this