A Multi-center Milestone Study of Clinical Vertebral CT Segmentation

Jianhua Yao, Joseph E. Burns, Daniel Forsberg, Alexander Seitel, Abtin Rasoulian, Purang Abolmaesumi, Kerstin Hammernik, Martin Urschler, Bulat Ibragimov, Robert Korez, Tomaž Vrtovec, Isaac Castro-Mateos, Jose M. Pozo, Alejandro F. Frangi, Ronald M. Summers, Shuo Li

Research output: Contribution to journalArticle

Abstract

A multiple center milestone study of clinical vertebra segmentation is presented in this paper. Vertebra segmentation is a fundamental step for spinal image analysis and intervention. The first half of the study was conducted in the spine segmentation challenge in 2014 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) Workshop on Computational Spine Imaging (CSI 2014). The objective was to evaluate the performance of several state-of-the-art vertebra segmentation algorithms on computed tomography (CT) scans using ten training and five testing dataset, all healthy cases; the second half of the study was conducted after the challenge, where additional 5 abnormal cases are used for testing to evaluate the performance under abnormal cases. Dice coefficients and absolute surface distances were used as evaluation metrics. Segmentation of each vertebra as a single geometric unit, as well as separate segmentation of vertebra substructures, was evaluated. Five teams participated in the comparative study. The top performers in the study achieved Dice coefficient of 0.93 in the upper thoracic, 0.95 in the lower thoracic and 0.96 in the lumbar spine for healthy cases, and 0.88 in the upper thoracic, 0.89 in the lower thoracic and 0.92 in the lumbar spine for osteoporotic and fractured cases. The strengths and weaknesses of each method as well as future suggestion for improvement are discussed. This is the first multi-center comparative study for vertebra segmentation methods, which will provide an up-to-date performance milestone for the fast growing spinal image analysis and intervention.
LanguageEnglish
Pages16-28
JournalComputerized medical imaging and graphics
Volume49
DOIs
StatusPublished - Apr 2016

Fingerprint

Image analysis
Tomography
Spine
Testing
Imaging techniques
Thorax
Clinical Studies
Education

Fields of Expertise

  • Information, Communication & Computing
  • Human- & Biotechnology

Cooperations

  • BioTechMed-Graz

Cite this

Yao, J., Burns, J. E., Forsberg, D., Seitel, A., Rasoulian, A., Abolmaesumi, P., ... Li, S. (2016). A Multi-center Milestone Study of Clinical Vertebral CT Segmentation. Computerized medical imaging and graphics, 49, 16-28. DOI: http://dx.doi.org/10.1016/j.compmedimag.2015.12.006

A Multi-center Milestone Study of Clinical Vertebral CT Segmentation. / Yao, Jianhua; Burns, Joseph E.; Forsberg, Daniel; Seitel, Alexander; Rasoulian, Abtin; Abolmaesumi, Purang; Hammernik, Kerstin; Urschler, Martin; Ibragimov, Bulat; Korez, Robert; Vrtovec, Tomaž; Castro-Mateos, Isaac; Pozo, Jose M.; Frangi, Alejandro F.; Summers, Ronald M.; Li, Shuo.

In: Computerized medical imaging and graphics, Vol. 49, 04.2016, p. 16-28.

Research output: Contribution to journalArticle

Yao, J, Burns, JE, Forsberg, D, Seitel, A, Rasoulian, A, Abolmaesumi, P, Hammernik, K, Urschler, M, Ibragimov, B, Korez, R, Vrtovec, T, Castro-Mateos, I, Pozo, JM, Frangi, AF, Summers, RM & Li, S 2016, 'A Multi-center Milestone Study of Clinical Vertebral CT Segmentation' Computerized medical imaging and graphics, vol 49, pp. 16-28. DOI: http://dx.doi.org/10.1016/j.compmedimag.2015.12.006
Yao J, Burns JE, Forsberg D, Seitel A, Rasoulian A, Abolmaesumi P et al. A Multi-center Milestone Study of Clinical Vertebral CT Segmentation. Computerized medical imaging and graphics. 2016 Apr;49:16-28. Available from, DOI: http://dx.doi.org/10.1016/j.compmedimag.2015.12.006
Yao, Jianhua ; Burns, Joseph E. ; Forsberg, Daniel ; Seitel, Alexander ; Rasoulian, Abtin ; Abolmaesumi, Purang ; Hammernik, Kerstin ; Urschler, Martin ; Ibragimov, Bulat ; Korez, Robert ; Vrtovec, Tomaž ; Castro-Mateos, Isaac ; Pozo, Jose M. ; Frangi, Alejandro F. ; Summers, Ronald M. ; Li, Shuo. / A Multi-center Milestone Study of Clinical Vertebral CT Segmentation. In: Computerized medical imaging and graphics. 2016 ; Vol. 49. pp. 16-28
@article{ebd9ec41f9f242f8b70f228dfec712a6,
title = "A Multi-center Milestone Study of Clinical Vertebral CT Segmentation",
abstract = "A multiple center milestone study of clinical vertebra segmentation is presented in this paper. Vertebra segmentation is a fundamental step for spinal image analysis and intervention. The first half of the study was conducted in the spine segmentation challenge in 2014 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) Workshop on Computational Spine Imaging (CSI 2014). The objective was to evaluate the performance of several state-of-the-art vertebra segmentation algorithms on computed tomography (CT) scans using ten training and five testing dataset, all healthy cases; the second half of the study was conducted after the challenge, where additional 5 abnormal cases are used for testing to evaluate the performance under abnormal cases. Dice coefficients and absolute surface distances were used as evaluation metrics. Segmentation of each vertebra as a single geometric unit, as well as separate segmentation of vertebra substructures, was evaluated. Five teams participated in the comparative study. The top performers in the study achieved Dice coefficient of 0.93 in the upper thoracic, 0.95 in the lower thoracic and 0.96 in the lumbar spine for healthy cases, and 0.88 in the upper thoracic, 0.89 in the lower thoracic and 0.92 in the lumbar spine for osteoporotic and fractured cases. The strengths and weaknesses of each method as well as future suggestion for improvement are discussed. This is the first multi-center comparative study for vertebra segmentation methods, which will provide an up-to-date performance milestone for the fast growing spinal image analysis and intervention.",
author = "Jianhua Yao and Burns, {Joseph E.} and Daniel Forsberg and Alexander Seitel and Abtin Rasoulian and Purang Abolmaesumi and Kerstin Hammernik and Martin Urschler and Bulat Ibragimov and Robert Korez and Tomaž Vrtovec and Isaac Castro-Mateos and Pozo, {Jose M.} and Frangi, {Alejandro F.} and Summers, {Ronald M.} and Shuo Li",
year = "2016",
month = "4",
doi = "http://dx.doi.org/10.1016/j.compmedimag.2015.12.006",
language = "English",
volume = "49",
pages = "16--28",
journal = "Computerized medical imaging and graphics",
issn = "0895-6111",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - A Multi-center Milestone Study of Clinical Vertebral CT Segmentation

AU - Yao,Jianhua

AU - Burns,Joseph E.

AU - Forsberg,Daniel

AU - Seitel,Alexander

AU - Rasoulian,Abtin

AU - Abolmaesumi,Purang

AU - Hammernik,Kerstin

AU - Urschler,Martin

AU - Ibragimov,Bulat

AU - Korez,Robert

AU - Vrtovec,Tomaž

AU - Castro-Mateos,Isaac

AU - Pozo,Jose M.

AU - Frangi,Alejandro F.

AU - Summers,Ronald M.

AU - Li,Shuo

PY - 2016/4

Y1 - 2016/4

N2 - A multiple center milestone study of clinical vertebra segmentation is presented in this paper. Vertebra segmentation is a fundamental step for spinal image analysis and intervention. The first half of the study was conducted in the spine segmentation challenge in 2014 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) Workshop on Computational Spine Imaging (CSI 2014). The objective was to evaluate the performance of several state-of-the-art vertebra segmentation algorithms on computed tomography (CT) scans using ten training and five testing dataset, all healthy cases; the second half of the study was conducted after the challenge, where additional 5 abnormal cases are used for testing to evaluate the performance under abnormal cases. Dice coefficients and absolute surface distances were used as evaluation metrics. Segmentation of each vertebra as a single geometric unit, as well as separate segmentation of vertebra substructures, was evaluated. Five teams participated in the comparative study. The top performers in the study achieved Dice coefficient of 0.93 in the upper thoracic, 0.95 in the lower thoracic and 0.96 in the lumbar spine for healthy cases, and 0.88 in the upper thoracic, 0.89 in the lower thoracic and 0.92 in the lumbar spine for osteoporotic and fractured cases. The strengths and weaknesses of each method as well as future suggestion for improvement are discussed. This is the first multi-center comparative study for vertebra segmentation methods, which will provide an up-to-date performance milestone for the fast growing spinal image analysis and intervention.

AB - A multiple center milestone study of clinical vertebra segmentation is presented in this paper. Vertebra segmentation is a fundamental step for spinal image analysis and intervention. The first half of the study was conducted in the spine segmentation challenge in 2014 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) Workshop on Computational Spine Imaging (CSI 2014). The objective was to evaluate the performance of several state-of-the-art vertebra segmentation algorithms on computed tomography (CT) scans using ten training and five testing dataset, all healthy cases; the second half of the study was conducted after the challenge, where additional 5 abnormal cases are used for testing to evaluate the performance under abnormal cases. Dice coefficients and absolute surface distances were used as evaluation metrics. Segmentation of each vertebra as a single geometric unit, as well as separate segmentation of vertebra substructures, was evaluated. Five teams participated in the comparative study. The top performers in the study achieved Dice coefficient of 0.93 in the upper thoracic, 0.95 in the lower thoracic and 0.96 in the lumbar spine for healthy cases, and 0.88 in the upper thoracic, 0.89 in the lower thoracic and 0.92 in the lumbar spine for osteoporotic and fractured cases. The strengths and weaknesses of each method as well as future suggestion for improvement are discussed. This is the first multi-center comparative study for vertebra segmentation methods, which will provide an up-to-date performance milestone for the fast growing spinal image analysis and intervention.

U2 - http://dx.doi.org/10.1016/j.compmedimag.2015.12.006

DO - http://dx.doi.org/10.1016/j.compmedimag.2015.12.006

M3 - Article

VL - 49

SP - 16

EP - 28

JO - Computerized medical imaging and graphics

T2 - Computerized medical imaging and graphics

JF - Computerized medical imaging and graphics

SN - 0895-6111

ER -