Skip to main navigation Skip to search Skip to main content

Fully automatic segmentation of the dentate nucleus using diffusion weighted images

  • Chuyang Ye*
  • , John A. Bogovic
  • , Pierre Louis Bazin
  • , Jerry L. Prince
  • , Sarah H. Ying
  • *Corresponding author for this work
  • Johns Hopkins University
  • Max Planck Institute for Human Cognitive and Brain Sciences

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

Abstract

We propose a fully automatic method to segment the dentate nucleus using diffusion weighted images (DWI). Initialization of the dentate nucleus is produced by combining the information from tractography results on the diffusion tensor images (reconstructed from DWI) and b0 images. A geometric de-formable model (GDM) with generalized gradient vector flow (GGVF) is then applied on the b0 image to generate the segmentation by evolving the level set function. Experiments have been carried out on real data and quantitative comparison shows that our segmentation results agree well with expert manual delineations and produce accurate results.

Original languageEnglish
Title of host publication2012 9th IEEE International Symposium on Biomedical Imaging
Subtitle of host publicationFrom Nano to Macro, ISBI 2012 - Proceedings
PublisherIEEE Computer Society
Pages1128-1131
Number of pages4
ISBN (Print)9781457718588
DOIs
Publication statusPublished - 2012
Externally publishedYes
Event9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012 - Barcelona, Spain
Duration: 2 May 2012 → 5 May 2012

Publication series

NameProceedings - International Symposium on Biomedical Imaging
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452

Conference

Conference9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012
Country/TerritorySpain
CityBarcelona
Period2/05/12 → 5/05/12

Keywords

  • dentate nucleus
  • diffusion weighted images
  • generalized gradient vector flow
  • geometric deformable model
  • segmentation

Fingerprint

Dive into the research topics of 'Fully automatic segmentation of the dentate nucleus using diffusion weighted images'. Together they form a unique fingerprint.

Cite this