Liver segmentation from 3D abdominal CT images

Pham The Bao, Tran Hong Tai, Viet Hang Duong, Jia Ching Wang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

Segmentation of the whole liver region from computed tomography (CT) image is the first step in the computer-aided diagnosis for liver disease. In this paper, we propose a new method for segmenting liver region from 3D CT images of abdomen using enhanced Otsu method. Our algorithm uses Otsu method with some improvements to construct intensity model and shape model for liver. First, the 3D CT image of abdomen is cropped, preserving only the part that contains liver. Second, the liver region in each slice of preserved part is segmented using intensity model. Finally, the segmented liver regions from all slices are post-processed to increase performance and merged into a single liver region.

Original languageEnglish
Title of host publication2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages342-343
Number of pages2
ISBN (Electronic)9781479987443
DOIs
StatePublished - 20 Aug 2015
Event2nd IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015 - Taipei, Taiwan
Duration: 6 Jun 20158 Jun 2015

Publication series

Name2015 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015

Conference

Conference2nd IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2015
Country/TerritoryTaiwan
CityTaipei
Period6/06/158/06/15

Keywords

  • 3D abdominal CT image
  • liver segmentation
  • Medical image processing
  • Otsu method

Fingerprint

Dive into the research topics of 'Liver segmentation from 3D abdominal CT images'. Together they form a unique fingerprint.

Cite this