Accurate liver extraction using a local-thickness-based graph-cut approach

Yasuhiro Kobayashi, Masanori Hariyama, Mitsugi Shimoda, Keiichi Kubota

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This article presents an accurate and automatic approach to extract a liver from CT images for oncologic surgery planning. Our algorithm exploits graph cut segmentation, which perform global optimization. The quality of graph cut segmentation strongly depends on the edge image that gives prior knowledge about locations of foreground and background regions. In order to get a good edge image, a liver candidate region is extracted based on three types of liver structure models: intensity model, shape model, and blood vessel model. Moreover, the "local-thickness" image of the liver candidate region is used as the edge image. The experimental results show that the use of local-thickness edge image can avoid the over-extraction of anatomical structures surrounding the liver.

Original languageEnglish
Title of host publicationProceedings of the 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015
EditorsHamid R. Arabnia, Leonidas Deligiannidis, Fernando G. Tinetti, George Jandieri, Gerald Schaefer, Ashu M. G. Solo
PublisherCSREA Press
Pages315-318
Number of pages4
ISBN (Electronic)1601324049, 9781601324047
Publication statusPublished - 2015 Jan 1
Event2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015, at WORLDCOMP 2015 - Las Vegas, United States
Duration: 2015 Jul 272015 Jul 30

Publication series

NameProceedings of the 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015

Conference

Conference2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015, at WORLDCOMP 2015
CountryUnited States
CityLas Vegas
Period15/7/2715/7/30

Keywords

  • 3D simulation analysis
  • Anatomic hepatectomy
  • Local thickness
  • Medical imaging

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Graphics and Computer-Aided Design

Fingerprint Dive into the research topics of 'Accurate liver extraction using a local-thickness-based graph-cut approach'. Together they form a unique fingerprint.

Cite this