Skip to main navigation Skip to search Skip to main content

Cardiac trabeculae segmentation: An application of computational topology

  • Chao Chen
  • , Dimitris Metaxas
  • , Yusu Wang
  • , Pengxiang Wu
  • Rutgers - The State University of New Jersey, New Brunswick
  • Ohio State University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this video, we present a research project on cardiac trabeculae segmentation. Trabeculae are fine muscle columns within human ventricles whose both ends are attached to the wall. Extracting these structures are very challenging even with state-of-the-art image segmentation techniques. We observed that these structures form natural topological handles. Based on such observation, we developed a topological approach, which employs advanced computational topology methods and achieve high quality segmentation results.

Original languageEnglish
Title of host publication33rd International Symposium on Computational Geometry, SoCG 2017
EditorsMatthew J. Katz, Boris Aronov
PublisherSchloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing
Pages651-654
Number of pages4
ISBN (Electronic)9783959770385
DOIs
StatePublished - Jun 1 2017
Event33rd International Symposium on Computational Geometry, SoCG 2017 - Brisbane, Australia
Duration: Jul 4 2017Jul 7 2017

Publication series

NameLeibniz International Proceedings in Informatics, LIPIcs
Volume77
ISSN (Print)1868-8969

Conference

Conference33rd International Symposium on Computational Geometry, SoCG 2017
Country/TerritoryAustralia
CityBrisbane
Period07/4/1707/7/17

Keywords

  • Homology localization
  • Image segmentation
  • Persistent homology
  • Trabeculae

Fingerprint

Dive into the research topics of 'Cardiac trabeculae segmentation: An application of computational topology'. Together they form a unique fingerprint.

Cite this