Intensity-based shape propagation for volumetric image segmentation

E. T. Tan, R. Srinivasan, R. A. Robb

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

The shape propagation scheme robustly combines shape and edge information in two steps to perform volumetric image segmentation. The inward-propagating step performs shape interpolation from user-defined sparse segmentations. The edge estimation step improves the accuracy of interpolated boundaries using a Bayesian approach that handles the presence of edges or its lack of. The scheme was found to be robust in segmenting T-1 weighted MRI of the Corpus Callosum. The algorithm also runs in linear time. The efficiency and robustness of this scheme demonstrates significant potential for use in assisting tedious manual volumetric segmentation that may be performed in clinical applications.

Original languageEnglish (US)
Title of host publication2006 3rd IEEE International Symposium on Biomedical Imaging
Subtitle of host publicationFrom Nano to Macro - Proceedings
Pages738-741
Number of pages4
StatePublished - 2006
Event2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Arlington, VA, United States
Duration: Apr 6 2006Apr 9 2006

Publication series

Name2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings
Volume2006

Other

Other2006 3rd IEEE International Symposium on Biomedical Imaging: From Nano to Macro
Country/TerritoryUnited States
CityArlington, VA
Period4/6/064/9/06

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'Intensity-based shape propagation for volumetric image segmentation'. Together they form a unique fingerprint.

Cite this