NITRC News Group Forum: an-open-source-multivariate-framework-for-n-tissue-segmentation-with-evaluation-on-public-data

NITRC News Group Forum: an-open-source-multivariate-framework-for-n-tissue-segmentation-with-evaluation-on-public-data http://www.nitrc.org/forum/forum.php?forum_id=2960 <div class="Abstract" lang="en"><a name="Abs1"></a>Abstract  <div class="normal">We introduce Atropos, an ITK-based multivariate n-class open source segmentation algorithm distributed with ANTs (<a href="http://www.picsl.upenn.edu/ANTs">http://www.picsl.upenn.edu/ANTs</a>). The Bayesian formulation of the segmentation problem is solved using the Expectation Maximization (EM) algorithm with the modeling of the class intensities based on either parametric or non-parametric finite mixtures. Atropos is capable of incorporating spatial prior probability maps (sparse), prior label maps and/or Markov Random Field (MRF) modeling. Atropos has also been efficiently implemented to handle large quantities of possible labelings (in the experimental section, we use up to 69 classes) with a minimal memory footprint. This work describes the technical and implementation aspects of Atropos and evaluates its performance on two different ground-truth datasets. First, we use the BrainWeb dataset from Montreal Neurological Institute to evaluate three-tissue segmentation performance via (1) K-means segmentation without use of template data; (2) MRF segmentation with initialization by prior probability maps derived from a group template; (3) Prior-based segmentation with use of spatial prior probability maps derived from a group template. We also evaluate Atropos performance by using spatial priors to drive a 69-class EM segmentation problem derived from the Hammers atlas from University College London. These evaluation studies, combined with illustrative examples that exercise Atropos options, demonstrate both performance and wide applicability of this new platform-independent open source segmentation tool. </div> </div><ul> <li>Content Type Journal Article</li><li>Category Original Article</li><li>Pages 381-400</li><li>DOI 10.1007/s12021-011-9109-y</li><li>Authors<ul> <li>Brian B. Avants, Penn Image Computing and Science Laboratory, University of Pennsylvania, 3600 Market Street, Suite 370, Philadelphia, PA 19104, USA</li><li>Nicholas J. Tustison, Department of Radiology and Medical Imaging, University of Virginia, Charlottesville, VA, USA</li><li>Jue Wu, Penn Image Computing and Science Laboratory, University of Pennsylvania, 3600 Market Street, Suite 370, Philadelphia, PA 19104, USA</li><li>Philip A. Cook, Penn Image Computing and Science Laboratory, University of Pennsylvania, 3600 Market Street, Suite 370, Philadelphia, PA 19104, USA</li><li>James C. Gee, Penn Image Computing and Science Laboratory, University of Pennsylvania, 3600 Market Street, Suite 370, Philadelphia, PA 19104, USA</li> </ul></li> </ul><ul class="parents"> <ul class="details"> <li>Journal <a href="http://www.springerlink.com/content/120559/">Neuroinformatics</a></li><li>Online ISSN 1559-0089</li><li>Print ISSN 1539-2791</li> </ul><ul class="details"> <li>Journal Volume Volume 9</li> </ul><ul class="details"> <li>Journal Issue <a href="http://www.springerlink.com/content/v50w168v4hq8/">Volume 9, Number 4</a></li> </ul> </ul> en-us Copyright 2000-2026 NITRC OSI Mon, 20 Apr 2026 7:33:42 GMT http://blogs.law.harvard.edu/tech/rss NITRC RSS generator