Robust Atlas-Based Segmentation of Highly Variable Anatomy: Left Atrium Segmentation

Michal Depa, Mert R. Sabuncu, Godtfred Holmvang, Reza Nezafat, Ehud J. Schmidt, Polina Golland

Abstract

Automatic segmentation of the heart’s left atrium offers great benefits for planning and outcome evaluation of atrial ablation procedures. However, the high anatomical variability of the left atrium presents significant challenges for atlas-guided segmentation. In this paper, we demonstrate an automatic method for left atrium segmentation using weighted voting label fusion and a variant of the demons registration algorithm adapted to handle images with different intensity distributions. We achieve accurate automatic segmentation that is robust to the high anatomical variations in the shape of the left atrium in a clinical dataset of MRA images.
BibTeX
@inproceedings{depa2010robust,
  author = {Michal Depa and Mert R. Sabuncu and Godtfred Holmvang and Reza Nezafat and Ehud J. Schmidt and Polina Golland},
  title = {{Robust Atlas-Based Segmentation of Highly Variable Anatomy: Left Atrium Segmentation}},
  booktitle = {STACOM/CESC},
  year = {2010},
  doi = {10.1007/978-3-642-15835-3\_9},
}

Loading related content...

Figure