Bone Segmentation in CT-Angiography Data Using a Probabilistic Atlas

Information

• Publication Type: Conference Paper
• Workgroup(s)/Project(s): not specified
• Date: November 2003
• Publisher: VMV
• Booktitle: Vision, Modeling and Visualization
• Pages: 505 – 512
• Keywords: Knowledge Based Segmentation, CT Angiography, Probabilistic Atlas, Thin-Plate Spline, Distance Fields, Histogram Classficication

Abstract

Automatic segmentation of bony structures in CT angiography datasets is an essential pre-processing step necessary for most visualization and analysis tasks. Since traditional density and gradient operators fail in non-trivial cases (or at last require extensive operator work), we propose a new method for segmentation of CTA data based on a probabilistic atlas. Sorting densities and masks of previously manually segmented tissues to the atlas can constitute a statistical information base for latter accurate segmentation. In order to eliminate dimensional and anatomic variability of the atlas input datasets, these have to be spatially normalized (registered) first by applying a non-rigid transformation. After this transformation, densities and tissue masks are statistically processed (e.g. averaged) within the atlas. Records in the atlas can be later evaluated for estimating the probability of bone tissue in a voxel of an unsegmented dataset.

Additional Files and Images

Weblinks

No further information available.

BibTeX

@inproceedings{Straka-2003-Bon,
  title =      "Bone Segmentation in CT-Angiography Data Using a
               Probabilistic Atlas",
  author =     "Mat\'{u}s Straka and Alexandra La Cruz and Leonid Dimitrov
               and Milo\v{s} \v{S}r\'{a}mek and Dominik Fleischmann and
               Eduard Gr\"{o}ller",
  year =       "2003",
  abstract =   "Automatic segmentation of bony structures in CT angiography
               datasets is an essential pre-processing step necessary for
               most visualization and analysis tasks. Since traditional
               density and gradient operators fail in non-trivial cases (or
               at last require extensive operator work), we propose a new
               method for segmentation of CTA data based on a probabilistic
               atlas. Sorting densities and masks of previously manually
               segmented tissues to the atlas can constitute a statistical
               information base for latter accurate segmentation. In order
               to eliminate dimensional and anatomic variability of the
               atlas input datasets, these have to be spatially normalized
               (registered) first by applying a non-rigid transformation.
               After this transformation, densities and tissue masks are
               statistically processed (e.g. averaged) within the atlas.
               Records in the atlas can be later evaluated for estimating
               the probability of bone tissue in a voxel of an unsegmented
               dataset.",
  month =      nov,
  publisher =  "VMV",
  booktitle =  "Vision, Modeling and Visualization",
  pages =      "505--512",
  keywords =   "Knowledge Based Segmentation, CT Angiography, Probabilistic
               Atlas, Thin-Plate Spline, Distance Fields, Histogram
               Classficication",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2003/Straka-2003-Bon/",
}