Deriving Anatomical Context from 4D Ultrasound

Markus Müller, Linn E. S. Helljesen, Raphael Prevost, Ivan Viola, Kim Nylund, Odd Helge Gilja, Nassir Navab, Wolfgang Wein
Deriving Anatomical Context from 4D Ultrasound
In Proceedings of EG VCBM14, pages 173-180. September 2014.
[Paper]

Information

Abstract

Real-time three-dimensional (also known as 4D) ultrasound imaging using matrix array probes has the potential to create large-volume information of entire organs such as the liver without external tracking hardware. This information can in turn be placed into the context of a CT or MRI scan of the same patient. However for such an approach many image processing challenges need to be overcome and sources of error addressed, including reconstruction drift, anatomical deformations, varying appearance of anatomy, and imaging artifacts. In this work,we present a fully automatic system including robust image-based ultrasound tracking, a novel learning-based global initialization of the anatomical context, and joint mono- and multi-modal registration. In an evaluation on 4D US sequences and MRI scans of eight volunteers we achieve automatic reconstruction and registration without any user interaction, assess the registration errors based on physician-defined landmarks, and demonstrate realtime tracking of free-breathing sequences.

Additional Files and Images

Additional images and videos

Additional files

Weblinks

No further information available.

BibTeX

@inproceedings{Viola_Ivan_DAC,
  title =      "Deriving Anatomical Context from 4D Ultrasound",
  author =     "Markus M{"u}ller and Linn E. S. Helljesen and Raphael
               Prevost and Ivan Viola and Kim Nylund and Odd Helge Gilja
               and Nassir Navab and Wolfgang Wein",
  year =       "2014",
  abstract =   "Real-time three-dimensional (also known as 4D) ultrasound
               imaging using matrix array probes has the potential to
               create large-volume information of entire organs such as the
               liver without external tracking hardware. This information
               can in turn be placed into the context of a CT or MRI scan
               of the same patient. However for such an approach many image
               processing challenges need to be overcome and sources of
               error addressed, including reconstruction drift, anatomical
               deformations, varying appearance of anatomy, and imaging
               artifacts. In this work,we present a fully automatic system
               including robust image-based ultrasound tracking, a novel
               learning-based global initialization of the anatomical
               context, and joint mono- and multi-modal registration. In an
               evaluation on 4D US sequences and MRI scans of eight
               volunteers we achieve automatic reconstruction and
               registration without any user interaction, assess the
               registration errors based on physician-defined landmarks,
               and demonstrate realtime tracking of free-breathing
               sequences.",
  month =      sep,
  booktitle =  "Proceedings of EG VCBM14",
  editor =     "Ivan Viola and Katja Buehler and Timo Ropinski",
  event =      "4th Eurographics Workshop on Visual Computing for Biology
               and Medicine",
  isbn =       "978-3-905674-62-0",
  issn =       "2070-5778",
  location =   "Vienna, Austria",
  note =       "The electronic version of the proceedings is available from
               the Eurographics Digital Library at http://diglib.eg.org",
  publisher =  "Eurographics Association",
  pages =      "173--180",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2014/Viola_Ivan_DAC/",
}