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

Siavash Khallaghi, Purang Abolmaesumi, Ren Hui Gong, Elvis Chen, Sean Gill, Jonathan Boisvert, David Pichora, Dan Borschneck, Gabor Fichtinger, Parvin Mousavi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We 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.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume7964
DOIs
StatePublished - 2011
Externally publishedYes
EventMedical Imaging 2011: Visualization, Image-Guided Procedures, and Modeling - Lake Buena Vista, FL, United States
Duration: Feb 13 2011Feb 15 2011

Other

OtherMedical Imaging 2011: Visualization, Image-Guided Procedures, and Modeling
CountryUnited States
CityLake Buena Vista, FL
Period2/13/112/15/11

Keywords

  • Graphics processing unit
  • Registration
  • Spine
  • Statistical shape model
  • Ultrasound

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Fingerprint Dive into the research topics of 'GPU accelerated registration of a statistical shape model of the lumbar spine to 3D ultrasound images'. Together they form a unique fingerprint.

Cite this