Reducing over- and undersegmentations of the liver in computed tomographies using anatomical knowledge

Cristina Oyarzun Laura, S. Oelmann, K. Drechsler, S. Wesarg

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

1 Scopus citations

Abstract

In the last decades several liver segmentation methods have been proposed. The proposed methods go from region growing to the more complex statistical shape models. Despite the robustness of those algorithms, liver segmentation is still a challenging task especially in areas in which its neighboring organs have similar intensities, e.g., heart and ribcage. In addition to this, pathological organs that contain tumors near their surface present additional difficulties. This paper presents a solution to increase the accuracy of those algorithms in the aforementioned areas. The effect of the improvement using the generated heart and ribcage walls (7% and 1% respectively) is evaluated on 9 clinical computer tomographies (CT). The improvement (12%) when tumors are near the surface, on the contrary, is tested on 7 clinical CT images.

Original languageEnglish
Title of host publicationXIV Mediterranean Conference on Medical and Biological Engineering and Computing, MEDICON 2016
EditorsEfthyvoulos Kyriacou, Stelios Christofides, Constantinos S. Pattichis
PublisherSpringer Verlag
Pages382-387
Number of pages6
ISBN (Print)9783319327013
DOIs
StatePublished - 2016
Externally publishedYes
Event14th Mediterranean Conference on Medical and Biological Engineering and Computing, MEDICON 2016 - Paphos, Cyprus
Duration: 31 Mar 20162 Apr 2016

Publication series

NameIFMBE Proceedings
Volume57
ISSN (Print)1680-0737

Conference

Conference14th Mediterranean Conference on Medical and Biological Engineering and Computing, MEDICON 2016
Country/TerritoryCyprus
CityPaphos
Period31/03/162/04/16

Keywords

  • Liver
  • Oversegmentation
  • Segmentation

Fingerprint

Dive into the research topics of 'Reducing over- and undersegmentations of the liver in computed tomographies using anatomical knowledge'. Together they form a unique fingerprint.

Cite this