Liver extraction from ct images based on liver structure models

Masanori Hariyama, Riichi Tanizawa, Mitsugi Shimoda, Keiichi Kubota

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

1 Citation (Scopus)

Abstract

The extraction of a liver from CT images is es- sential for oncologic surgery planning. This article presents an accurate and automatic approach to extract a liver from CT images. Our algorithm exploits three types of liver structure models: Intensity model, shape model, and blood vessel model. First, the region including the liver is roughly extracted based on intensity histogram analysis. Second, the extracted regions are segmented using a shape feature called • local thickness • based on the observation that the liver is thicker than other organs. Finally, the segmented regions including blood vessels in the liver are merged into a single liver region. Experimental results show that the average error of the volume extraction is 61.25 cc, and this result is much superior to the conventional one.

Original languageEnglish
Title of host publicationProceedings of the 2014 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2014
EditorsHamid R. Arabnia, Leonidas Deligiannidis, Joan Lu, Fernando G. Tinetti, Jane You, George Jandieri, Gerald Schaefer, Ashu M. G. Solo
PublisherCSREA Press
Pages170-173
Number of pages4
ISBN (Electronic)1601322801, 9781601322807
Publication statusPublished - 2014 Jan 1
Event2014 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2014, at WORLDCOMP 2014 - Las Vegas, United States
Duration: 2014 Jul 212014 Jul 24

Publication series

NameProceedings of the 2014 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2014

Conference

Conference2014 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2014, at WORLDCOMP 2014
CountryUnited States
CityLas Vegas
Period14/7/2114/7/24

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 'Liver extraction from ct images based on liver structure models'. Together they form a unique fingerprint.

Cite this