Document Detail


Gauss-Newton inspired preconditioned optimization in large deformation diffeomorphic metric mapping.
MedLine Citation:
PMID:  25254606     Owner:  NLM     Status:  In-Data-Review    
Abstract/OtherAbstract:
In this work, we propose a novel preconditioned optimization method in the paradigm of Large Deformation Diffeomorphic Metric Mapping (LDDMM). The preconditioned update scheme is formulated for the non-stationary and the stationary parameterizations of diffeomorphisms, yielding three different LDDMM methods. The preconditioning matrices are inspired in the Hessian approximation used in Gauss-Newton method. The derivatives are computed using Frechet differentials. Thus, optimization is performed in a Sobolev space, in contrast to optimization in L(2) commonly used in non-rigid registration literature. The proposed LDDMM methods have been evaluated and compared with their respective implementations of gradient descent optimization. Evaluation has been performed using real and simulated images from the Non-rigid Image Registration Evaluation Project (NIREP). The experiments conducted in this work reported that our preconditioned LDDMM methods achieved a performance similar or superior to well-established-in-literature gradient descent non-stationary LDDMM in the great majority of cases. Moreover, preconditioned optimization showed a substantial reduction in the execution time with an affordable increase of the memory usage per iteration. Additional experiments reported that optimization using Frechet differentials should be preferable to optimization using L(2) differentials.
Authors:
Monica Hernandez
Related Documents :
25317426 - Canonical correlation analysis on riemannian manifolds and its applications.
16372116 - Virtual endoscopy of the urinary tract.
20022736 - New look inside the spindle: microtubule-dependent microtubule generation within the sp...
25313236 - Impact of imaging measurements on response assessment in glioblastoma clinical trials.
16160296 - Myocardium tissue analysis based on textures in ultrasound images.
24099806 - Automatic 3d ultrasound calibration for image guided therapy using intramodality image ...
Publication Detail:
Type:  Journal Article     Date:  2014-09-25
Journal Detail:
Title:  Physics in medicine and biology     Volume:  59     ISSN:  1361-6560     ISO Abbreviation:  Phys Med Biol     Publication Date:  2014 Oct 
Date Detail:
Created Date:  2014-09-26     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  0401220     Medline TA:  Phys Med Biol     Country:  England    
Other Details:
Languages:  eng     Pagination:  6085-115     Citation Subset:  IM    
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Network Analysis in the Investigation of Chronic Respiratory Diseases: from Basics to Application.
Next Document:  Laterality and deep brain stimulation of the subthalamic nucleus: applying a dichotic listening task...