Perceiving Systems, Computer Vision

Left Ventricle Segmentation by Dynamic Shape Constrained Random Walk

2014

Conference Paper

ps


Accurate and robust extraction of the left ventricle (LV) cavity is a key step for quantitative analysis of cardiac functions. In this study, we propose an improved LV cavity segmentation method that incorporates a dynamic shape constraint into the weighting function of the random walks algorithm. The method involves an iterative process that updates an intermediate result to the desired solution. The shape constraint restricts the solution space of the segmentation result, such that the robustness of the algorithm is increased to handle misleading information that emanates from noise, weak boundaries, and clutter. Our experiments on real cardiac magnetic resonance images demonstrate that the proposed method obtains better segmentation performance than standard method.

Author(s): X. Yang and Y. Su and M. Wan and S. Y. Yeo and C. Lim and S. T. Wong and L. Zhong and R. S. Tan
Book Title: Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Year: 2014

Department(s): Perceiving Systems
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

BibTex

@inproceedings{emb1,
  title = {Left Ventricle Segmentation by Dynamic Shape Constrained Random Walk},
  author = {Yang, X. and Su, Y. and Wan, M. and Yeo, S. Y. and Lim, C. and Wong, S. T. and Zhong, L. and Tan, R. S.},
  booktitle = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society},
  year = {2014},
  doi = {}
}