DocumentCode :
1477198
Title :
Liver Vessels Segmentation Using a Hybrid Geometrical Moments/Graph Cuts Method
Author :
Esneault, Simon ; Lafon, Cyril ; Dillenseger, Jean-Louis
Author_Institution :
Inst. Nat. de la Sante et de la Rech. Medicale (INSERM), Rennes, France
Volume :
57
Issue :
2
fYear :
2010
Firstpage :
276
Lastpage :
283
Abstract :
This paper describes a fast and fully automatic method for liver vessel segmentation on computerized tomography scan preoperative images. The basis of this method is the introduction of a 3-D geometrical moment-based detector of cylindrical shapes within the minimum-cut/maximum-flow energy minimization framework. This method represents an original way to introduce a data term as a constraint into the widely used Boykov´s graph cuts algorithm, and hence, to automate the segmentation. The method is evaluated and compared with others on a synthetic dataset. Finally, the relevancy of our method regarding the planning of a necessarily accurate percutaneous high-intensity focused ultrasound surgical operation is demonstrated with some examples.
Keywords :
blood vessels; computerised tomography; image segmentation; liver; medical image processing; physiological models; 3-D geometrical moment-based detector; Boykov graph cut algorithm; automatic method; computerized tomography scan preoperative images; graph cut method; high-intensity focused ultrasound surgical operation; hybrid geometrical moments; liver vessel segmentation; minimum-cut-maximum-flow energy minimization framework; synthetic dataset; Applicators; Biomedical imaging; Blood vessels; Computed tomography; Image segmentation; Liver; Medical treatment; Neoplasms; Oncological surgery; Radio frequency; Ultrasonic imaging; Geometrical moments; graph cuts; hepatocellular carcinoma (HCC); liver segmentation; vessels extraction; Algorithms; Carcinoma, Hepatocellular; Computer Simulation; Hepatic Veins; Humans; Image Processing, Computer-Assisted; Liver; Liver Neoplasms; Phantoms, Imaging; Radiography, Abdominal; Tomography, X-Ray Computed;
fLanguage :
English
Journal_Title :
Biomedical Engineering, IEEE Transactions on
Publisher :
ieee
ISSN :
0018-9294
Type :
jour
DOI :
10.1109/TBME.2009.2032161
Filename :
5268216
Link To Document :
بازگشت