GPU accelerated registration of a statistical shape model of the lumbar spine to 3D ultrasound images

Download
  1. Get@NRC: GPU accelerated registration of a statistical shape model of the lumbar spine to 3D ultrasound images (Opens in a new window)
DOIResolve DOI: http://doi.org/10.1117/12.878377
AuthorSearch for: ; Search for: ; Search for: ; Search for: ; Search for: ; Search for: ; Search for: ; Search for: ; Search for: ; Search for:
TypeArticle
Proceedings titleProgress in Biomedical Optics and Imaging - Proceedings of SPIE
ConferenceMedical Imaging 2011: Visualization, Image-Guided Procedures, and Modeling, 13 February 2011 through 15 February 2011, Lake Buena Vista, FL
ISSN1605-7422
ISBN9780819485069
Volume7964
Article number79642W
SubjectGraphics Processing Unit; Registration; Spine; Statistical shape model; Ultrasound; Computer graphics equipment; Covariance matrix; Evolutionary algorithms; Medical imaging; Program processors; Ultrasonic applications; Ultrasonics; Visualization; Three dimensional
AbstractWe present a parallel implementation of a statistical shape model registration to 3D ultrasound images of the lumbar vertebrae (L2-L4). Covariance Matrix Adaptation Evolution Strategy optimization technique, along with Linear Correlation of Linear Combination similarity metric have been used, to improve the robustness and capture range of the registration approach. Instantiation and ultrasound simulation have been implemented on a graphics processing unit for a faster registration. Phantom studies show a mean target registration error of 3.2 mm, while 80% of all the cases yield target registration error of below 3.5 mm. © 2011 SPIE.
Publication date
LanguageEnglish
AffiliationNational Research Council Canada (NRC-CNRC)
Peer reviewedYes
NPARC number21271679
Export citationExport as RIS
Report a correctionReport a correction
Record identifiera74c2990-6953-4157-bdc0-6981154762e3
Record created2014-03-24
Record modified2016-05-09
Bookmark and share
  • Share this page with Facebook (Opens in a new window)
  • Share this page with Twitter (Opens in a new window)
  • Share this page with Google+ (Opens in a new window)
  • Share this page with Delicious (Opens in a new window)