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

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

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in Buch/BerichtForschung

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.
Originalspracheenglisch
TitelRecent Advances in Computational Methods and Clinical Applications for Spine Imaging and Clinical Applications for Spine Imaging
UntertitelPart VI
Redakteure/-innenJianhua Yao, Ben Glocker, Tobias Klinder, Shuo Li
ErscheinungsortSwitzerland
Herausgeber (Verlag)Springer International Publishing AG
Seiten227-233
ISBN (elektronisch)978-3-319-14148-0
ISBN (Print)978-3-319-14147-3
DOIs
PublikationsstatusVeröffentlicht - 2015

Publikationsreihe

NameLecture Notes in Computational Vision and Biomechanics
Herausgeber (Verlag)Springer International Publishing
Band20

Fingerprint

Medical imaging
Tomography

Fields of Expertise

  • Information, Communication & Computing
  • Human- & Biotechnology

Treatment code (Nähere Zuordnung)

  • Basic - Fundamental (Grundlagenforschung)

Kooperationen

  • BioTechMed-Graz

Dies zitieren

Hammernik, K., Ebner, T., Stern, D., Urschler, M., & Pock, T. (2015). Vertebrae Segmentation in 3D CT Images based on a Variational Framework. in J. Yao, B. Glocker, T. Klinder, & S. Li (Hrsg.), Recent Advances in Computational Methods and Clinical Applications for Spine Imaging and Clinical Applications for Spine Imaging: Part VI (S. 227-233). (Lecture Notes in Computational Vision and Biomechanics; Band 20). Switzerland: Springer International Publishing AG . https://doi.org/10.1007/978-3-319-14148-0_20

Vertebrae Segmentation in 3D CT Images based on a Variational Framework. / Hammernik, Kerstin; Ebner, Thomas; Stern, Darko; Urschler, Martin; Pock, Thomas.

Recent Advances in Computational Methods and Clinical Applications for Spine Imaging and Clinical Applications for Spine Imaging: Part VI. Hrsg. / Jianhua Yao; Ben Glocker; Tobias Klinder; Shuo Li. Switzerland : Springer International Publishing AG , 2015. S. 227-233 (Lecture Notes in Computational Vision and Biomechanics; Band 20).

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in Buch/BerichtForschung

Hammernik, K, Ebner, T, Stern, D, Urschler, M & Pock, T 2015, Vertebrae Segmentation in 3D CT Images based on a Variational Framework. in J Yao, B Glocker, T Klinder & S Li (Hrsg.), Recent Advances in Computational Methods and Clinical Applications for Spine Imaging and Clinical Applications for Spine Imaging: Part VI. Lecture Notes in Computational Vision and Biomechanics, Bd. 20, Springer International Publishing AG , Switzerland, S. 227-233. https://doi.org/10.1007/978-3-319-14148-0_20
Hammernik K, Ebner T, Stern D, Urschler M, Pock T. Vertebrae Segmentation in 3D CT Images based on a Variational Framework. in Yao J, Glocker B, Klinder T, Li S, Hrsg., Recent Advances in Computational Methods and Clinical Applications for Spine Imaging and Clinical Applications for Spine Imaging: Part VI. Switzerland: Springer International Publishing AG . 2015. S. 227-233. (Lecture Notes in Computational Vision and Biomechanics). https://doi.org/10.1007/978-3-319-14148-0_20
Hammernik, Kerstin ; Ebner, Thomas ; Stern, Darko ; Urschler, Martin ; Pock, Thomas. / Vertebrae Segmentation in 3D CT Images based on a Variational Framework. Recent Advances in Computational Methods and Clinical Applications for Spine Imaging and Clinical Applications for Spine Imaging: Part VI. Hrsg. / Jianhua Yao ; Ben Glocker ; Tobias Klinder ; Shuo Li. Switzerland : Springer International Publishing AG , 2015. S. 227-233 (Lecture Notes in Computational Vision and Biomechanics).
@inbook{6d3a84eba0ac47a4a52c070ca02a83e9,
title = "Vertebrae Segmentation in 3D CT Images based on a Variational Framework",
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.",
author = "Kerstin Hammernik and Thomas Ebner and Darko Stern and Martin Urschler and Thomas Pock",
year = "2015",
doi = "10.1007/978-3-319-14148-0_20",
language = "English",
isbn = "978-3-319-14147-3",
series = "Lecture Notes in Computational Vision and Biomechanics",
publisher = "Springer International Publishing AG",
pages = "227--233",
editor = "Jianhua Yao and Ben Glocker and Tobias Klinder and Shuo Li",
booktitle = "Recent Advances in Computational Methods and Clinical Applications for Spine Imaging and Clinical Applications for Spine Imaging",
address = "Switzerland",

}

TY - CHAP

T1 - Vertebrae Segmentation in 3D CT Images based on a Variational Framework

AU - Hammernik, Kerstin

AU - Ebner, Thomas

AU - Stern, Darko

AU - Urschler, Martin

AU - Pock, Thomas

PY - 2015

Y1 - 2015

N2 - 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.

AB - 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.

U2 - 10.1007/978-3-319-14148-0_20

DO - 10.1007/978-3-319-14148-0_20

M3 - Chapter

SN - 978-3-319-14147-3

T3 - Lecture Notes in Computational Vision and Biomechanics

SP - 227

EP - 233

BT - Recent Advances in Computational Methods and Clinical Applications for Spine Imaging and Clinical Applications for Spine Imaging

A2 - Yao, Jianhua

A2 - Glocker, Ben

A2 - Klinder, Tobias

A2 - Li, Shuo

PB - Springer International Publishing AG

CY - Switzerland

ER -