Automatic liver contour segmentation using GVF snake Conference Paper


Authors: Liu, F.; Zhao, B.; Kijewski, P.; Ginsberg, M.; Wang, L.; Schwartz, L.
Title: Automatic liver contour segmentation using GVF snake
Conference Title: Progress in Biomedical Optics and Imaging - Medical Imaging 2004: Imaging Processing
Abstract: Liver segmentation is critical for the development of algorithms to detect and define focal lesions. It is also helpful in presurgical planning for hepatic resection and to gauge the results of therapies. The purpose of this study is to develop a computerized method for extraction of liver contours on contrast-enhanced hepatic CT. The method is based on a snake algorithm with a Gradient Vector Flow (GVF) field as its external force. An edge map and an initial contour are used as the starting point. A Canny edge algorithm is applied to obtain the initial edge map. To suppress edges inside liver parenchyma, a liver template determined by analyzing the histogram of the liver image is used. Based on the modified edge map, the GVF field is computed in an iterative manner. Due to the finite number of iteration steps, an area uncovered by the GVF field in the liver can be extracted and serves as the initial contour for the snake algorithm. Preliminary results have shown the potential of separating the liver from its adjacent structures (e.g., kidney and stomach) of similar densities.
Keywords: algorithms; radiology; computerized tomography; medical imaging; problem solving; biological organs; standards; computed tomography (ct); image segmentation; statistical methods; canny edge detector; gvf; liver contour; snake; brownian movement; canny edge detectors; gradient vector flow (gvf)
Journal Title Proceedings of SPIE
Volume: 5370
Conference Dates: 2004 Feb 14
Conference Location: San Diego, CA
ISBN: 0277-786X
Publisher: SPIE  
Date Published: 2004-05-12
Start Page: 1466
End Page: 1473
Language: English
DOI: 10.1117/12.535276
PROVIDER: scopus
DOI/URL:
Notes: Proc SPIE Int Soc Opt Eng -- Conference code: 63695 -- Cited By (since 1996):5 -- Export Date: 16 June 2014 -- CODEN: PSISD -- 16 February 2004 through 19 February 2004 -- Source: Scopus
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
  1. Michelle S Ginsberg
    235 Ginsberg
  2. Lawrence H Schwartz
    306 Schwartz
  3. Binsheng Zhao
    55 Zhao
  4. Fan Ying Liu
    22 Liu
  5. Liang Wang
    35 Wang