Adaptive Stochastic Gradient Descent Optimisation for Image Registration

Authors:
Stefan Klein;Josien P. Pluim;Marius Staring;Max A. Viergever
Affiliations:
Image Sciences Institute, University Medical Center Utrecht, GA Utrecht, The Netherlands 3508;Image Sciences Institute, University Medical Center Utrecht, GA Utrecht, The Netherlands 3508;Image Sciences Institute, University Medical Center Utrecht, GA Utrecht, The Netherlands 3508;Image Sciences Institute, University Medical Center Utrecht, GA Utrecht, The Netherlands 3508
Venue:
International Journal of Computer Vision
Year:
2009

Citing 4
Cited 11

Variational Methods for Multimodal Image Matching

International Journal of Computer Vision
Alignment by maximization of mutual information

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Optimization of mutual information for multiresolution image registration

IEEE Transactions on Image Processing
Evaluation of Optimization Methods for Nonrigid Medical Image Registration Using Mutual Information and B-Splines

IEEE Transactions on Image Processing

A patient-specific coronary density estimate

ISBI'10 Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro
Automated carotid artery distensibility measurements from CTA using nonrigid registration

ISBI'10 Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro
Early diagnosis of dementia based on intersubject whole-brain dissimilarities

ISBI'10 Proceedings of the 2010 IEEE international conference on Biomedical imaging: from nano to Macro
Stochastic approximation for background modelling

Computer Vision and Image Understanding
Automated registration of whole-body follow-up MicroCT data of mice

MICCAI'11 Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention - Volume Part II
Preconditioned stochastic gradient descent optimisation for monomodal image registration

MICCAI'11 Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention - Volume Part II
Hierarchical vs. simultaneous multiresolution strategies for nonrigid image registration

WBIR'12 Proceedings of the 5th international conference on Biomedical Image Registration
Registration of free-hand ultrasound and MRI of carotid arteries through combination of point-based and intensity-based algorithms

WBIR'12 Proceedings of the 5th international conference on Biomedical Image Registration
Multi-atlas based segmentation using probabilistic label fusion with adaptive weighting of image similarity measures

Computer Methods and Programs in Biomedicine
Free-form image registration regularized by a statistical shape model: application to organ segmentation in cervical MR

Computer Vision and Image Understanding
Mutual information based three-dimensional registration of rat brain magnetic resonance imaging time-series

Computers and Electrical Engineering

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.