Interactive relaxation labeling for 3D cardiac image analysis

William E. Higgins, Michael W. Hansen, Werner L. Sharp

Research output: Contribution to journalConference articlepeer-review

7 Scopus citations

Abstract

Image segmentation remains one of the major challenges in 3D medical image analysis. The typical 3D imagesegmentation approach requires a skilled human operator to interactively extract the desired regions. Such techniques demand exorbitant operator interaction time, are error prone, and do not entail true 3D processing. Recently, researchers have realized that a combination of operator interaction and automatic processing can greatly circumvent the difficulties inherent in strictly interactive methods. Unfortunately, past efforts employing this strategy are usually not applicable to general problems. We describe a generally applicable 3D image-segmentation technique that combines operator interaction and automatic processing, with a particular focus on 3D cardiac image analysis. For a given 3D image, the method works as follows. First, the operator interactively defines region cues that either give region "tissue samples" or that impose spatial constraints on where regions can and cannot lie. Next, a threestep relaxation-labeling algorithm is applied. For the first step, each image voxel gets an initial probability vector assigned to it. This vector, computed using the previously defined region cues, contains the initial probabilities that a voxel belongs to various regions of interest. Next, a true 3D relaxation-labeling process is performed to update the probability vectors. Relaxation labeling concludes by assigning region labels to image voxels. Results for 3D cardiac image segmentation demonstrate the method's efficacy. A major advantage of the method is that the operator, who understands what he sees but has less understanding of the "numbers" defining the image, can apply the technique without having to set parameters.

Original languageEnglish (US)
Pages (from-to)51-62
Number of pages12
JournalProceedings of SPIE - The International Society for Optical Engineering
Volume1905
DOIs
StatePublished - Jul 29 1993
EventBiomedical Image Processing and Biomedical Visualization 1993 - San Jose, United States
Duration: Jan 31 1993Feb 5 1993

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Interactive relaxation labeling for 3D cardiac image analysis'. Together they form a unique fingerprint.

Cite this