Vertebrae Segmentation in 3D CT Images based on a Variational Framework

Kerstin Hammernik, Thomas Ebner, Darko Stern, Martin Urschler, Thomas Pock

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Automatic segmentation of 3D vertebrae is a challenging task in medical imaging. In this paper, we introduce a total variation (TV) based framework that incorporates an a priori model, i.e., a vertebral mean shape, image intensity and edge information. The algorithm was evaluated using leave-one-out cross validation on a data set containing ten computed tomography scans and ground truth segmentations provided for the CSI MICCAI 2014 spine and vertebrae segmentation challenge. We achieve promising results in terms of the Dice Similarity Coefficient (DSC) of 0.93±0.04 averaged over the whole data set.
Original languageEnglish
Title of host publicationRecent Advances in Computational Methods and Clinical Applications for Spine Imaging and Clinical Applications for Spine Imaging
Subtitle of host publicationPart VI
EditorsJianhua Yao, Ben Glocker, Tobias Klinder, Shuo Li
Place of PublicationSwitzerland
PublisherSpringer International Publishing AG
Pages227-233
ISBN (Electronic)978-3-319-14148-0
ISBN (Print)978-3-319-14147-3
DOIs
Publication statusPublished - 2015

Publication series

NameLecture Notes in Computational Vision and Biomechanics
PublisherSpringer International Publishing
Volume20

Fields of Expertise

  • Information, Communication & Computing
  • Human- & Biotechnology

Treatment code (Nähere Zuordnung)

  • Basic - Fundamental (Grundlagenforschung)

Cooperations

  • BioTechMed-Graz

Fingerprint Dive into the research topics of 'Vertebrae Segmentation in 3D CT Images based on a Variational Framework'. Together they form a unique fingerprint.

Cite this