An iterative model-constrained graph-cut algorithm for abdominal aortic aneurysm thrombus segmentation

Moti Freiman*, Steven J. Esses, Leo Joskowicz, Jacob Sosna

*Corresponding author for this work

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

29 Scopus citations

Abstract

We present an iterative model-constrained graph-cut algorithm for the segmentation of Abdominal Aortic Aneurysm (AAA) thrombus. Given an initial segmentation of the aortic lumen, our method automatically segments the thrombus by iteratively coupling intensity-based graph min-cut segmentation and geometric parametric model fitting. The geometric model effectively constrains the graph min-cut segmentation from "leaking" to nearby veins and organs. Experimental results on 8 AAA CTA datasets yield robust segmentations of the AAA thrombus in 2 mins computer time with a mean absolute volume difference of 8.0% and mean volumetric overlap error of 12.9%, which is comparable to the interobserver error.

Original languageAmerican English
Title of host publication2010 7th IEEE International Symposium on Biomedical Imaging
Subtitle of host publicationFrom Nano to Macro, ISBI 2010 - Proceedings
Pages672-675
Number of pages4
DOIs
StatePublished - 2010
Event7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Rotterdam, Netherlands
Duration: 14 Apr 201017 Apr 2010

Publication series

Name2010 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Proceedings

Conference

Conference7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010
Country/TerritoryNetherlands
CityRotterdam
Period14/04/1017/04/10

Keywords

  • AbdominalAortic aneurysm thrombus
  • Model constrained graph min-cut
  • Segmentation

Fingerprint

Dive into the research topics of 'An iterative model-constrained graph-cut algorithm for abdominal aortic aneurysm thrombus segmentation'. Together they form a unique fingerprint.

Cite this