Adaptive Stochastic Gradient Descent Optimisation for Image Registration

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 mec...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of computer vision Jg. 81; H. 3; S. 227 - 239
Hauptverfasser: Klein, Stefan, Pluim, Josien P. W., Staring, Marius, Viergever, Max A.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Boston Springer US 01.03.2009
Springer
Springer Nature B.V
Schlagworte:
Applied sciences
Artificial Intelligence
Computer Imaging
Computer Science
Computer science; control theory; systems
Exact sciences and technology
Image Processing and Computer Vision
Pattern Recognition
Pattern Recognition and Graphics
Pattern recognition. Digital image processing. Computational geometry
Programming theory
Registration
Studies
Theoretical computing
Vision
Image registration
Parameter selection
Stochastic gradient descent
Adaptive step sizes
Optimisation
Human
Head
Adaptive algorithm
Probabilistic approach
Similarity
Image processing
Lung
Model driven architecture
Respiratory system
Adaptive method
Characteristic function
Gradient descent
Stochastic gradient descent, Adaptive step sizes, Parameter selection
Descent method
Metric
Gradient method
Prostate
Step function
ISSN:0920-5691, 1573-1405
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
Bibliographie:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-2
content type line 23
ISSN:0920-5691
1573-1405
DOI:10.1007/s11263-008-0168-y