A new fully automatic and robust algorithm for fast segmentation of liver tissue and tumors from CT scans
- 1.4k Downloads
Accurate knowledge of the liver structure, including liver surface and lesion localization, is usually required in treatments such as liver tumor ablations and/or radiotherapy. This paper presents a new method and corresponding algorithm for fast segmentation of the liver and its internal lesions from CT scans. No interaction between the user and analysis system is required for initialization since the algorithm is fully automatic. A statistical model-based approach was created to distinguish hepatic tissue from other abdominal organs. It was combined to an active contour technique using gradient vector flow in order to obtain a smoother and more natural liver surface segmentation. Thereafter, automatic classification was performed to isolate hepatic lesions from liver parenchyma. Twenty-one datasets, presenting different anatomical and pathological situations, have been processed and analyzed. Special focus has been driven to the resulting processing time together with quality assessment. Our method allowed robust and efficient liver and lesion segmentations very close to the ground truth, in a relatively short processing time (average of 11.4 s for a 512 × 512-pixel slice). A volume overlap of 94.2% and an accuracy of 3.7 mm were achieved for liver surface segmentation. Sensitivity and specificity for tumor lesion detection were 82.6% and 87.5%, respectively.
KeywordsComputer-assisted image interpretation Statistical data analysis Automatic segmentation GVF active contours Liver
The authors would like to thank Prof. Caramella and his staff from the Department of Diagnostic and Interventional Radiology, University of Pisa, and also Petter Risholm from the Interventional Center, Rikshospitalet University Hospital, for the datasets and the help provided.
This work was a part of a European project that received research funding from the Research Training Network Marie Curie Action of the Sixth Framework Program of the European Community. As specifically requested by the European Community, the authors state that “this paper reflects only the author’s views and the European Community is not liable for any use that may be made of the information contained therein.”
- 1.World Health Organization (2002) The World Health Report 2002. Available online at: http://www.who.int/whr/2002/en. Accessed May 9, 2007
- 13.Lamecker H, Lange T, Seebaß M (2004) Segmentation of the liver using a 3D statistical shape model. ZIB Technical Report 04-09Google Scholar
- 16.Fernandez G, Bischof H, Beichel R (2003) Nonlinear Filters on 3D CT imaging - bilateral filter and mean shift Filter. Proceedings of the 8th Computer Vision Winter Workshop (CVWW’03) 1:21–26Google Scholar
- 18.Bartlett JE, Kotrlik JW, Higgins CC (2001) Organizational research: determining appropriate sample size in survey research. Info Technol Learn Perf J 19:43–50Google Scholar
- 20.Dillencourt MB, Samet H, Tamminen M (1992) A general approach to connected-component labeling for arbitrary image representations. J Assoc Comput Machinery 39:253–280Google Scholar
- 21.Soille P (1999) Morphological image analysis: principles and applications. Springer, Berlin Heidelberg, New YorkGoogle Scholar
- 25.Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data via the EM algorithm. J Roy Statist Soc B 39:1–38Google Scholar
- 27.Ibanez L, Schroeder W, Ng L, Cates J (2005) The ITK software guide second edition. Insight Software Consortium. http://www.itk.org/ItkSoftwareGuide.pdf
- 28.ITK-SNAP. University of North Carolina at Chapel Hill, Gerig G, Yushkevich PA. http://www.itksnap.org/
- 31.Zhang J, Ma KK, Meng HE, Chong V (2004) Tumor segmentation from magnetic resonance imaging by learning via one-class support vector machine. Proc 7th Int Workshop on Advanced Image Technology (IWAIT’04) 1:207–211Google Scholar