Skip to main navigation Skip to search Skip to main content

Simultaneous boundary and partial volume estimation in medical images

  • Dzung L. Pham*
  • , Pierre Louis Bazin
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

12 Scopus citations

Abstract

Partial volume effects are present in nearly all medical imaging data. These artifacts blur the boundaries between different regions, making accurate delineation of anatomical structures difficult. In this paper, we propose a method for unsupervised estimation of partial volume fractions in single-channel image data. Unlike previous methods, the proposed algorithm simultaneously estimates partial volume fractions, the means of the different tissue classes, as well as the the locations of tissue boundaries within the image. The latter allows the partial volume fractions to be constrained to represent pure or nearly pure tissue except along tissue boundaries. We demonstrate the application of the algorithm on simulated and real magnetic resonance images.

Original languageEnglish
Title of host publicationMedical Image Computing and Computer-Assisted Intervention, MICCAI 2004 - 7th International Conference, Proceedings
PublisherSpringer Verlag
Pages119-126
Number of pages8
EditionPART 1
ISBN (Electronic)9783540229766
DOIs
StatePublished - 2004
Event7th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2004 - Saint-Malo, France
Duration: 26 Sep 2004 → 29 Sep 2004

Publication series

NameLecture Notes in Computer Science
NumberPART 1
Volume3216
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference7th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2004
Country/TerritoryFrance
CitySaint-Malo
Period26/09/04 → 29/09/04

Fingerprint

Dive into the research topics of 'Simultaneous boundary and partial volume estimation in medical images'. Together they form a unique fingerprint.

Cite this