Evaluation and comparison of 3D intervertebral disc localization and segmentation methods for 3D T2 MR data: A grand challenge

Guoyan Zheng, Chengwen Chu, Daniel L. Belavý, Bulat Ibragimov, Robert Korez, Tomaž Vrtovec, Hugo Hutt, Richard Everson, Judith Meakin, Isabel Lŏpez Andrade, Ben Glocker, Hao Chen, Qi Dou, Pheng Ann Heng, Chunliang Wang, Daniel Forsberg, Aleš Neubert, Jürgen Fripp, Martin Urschler, Darko Stern & 6 others Maria Wimmer, Alexey A. Novikov, Hui Cheng, Gabriele Armbrecht, Dieter Felsenberg, Shuo Li

Research output: Contribution to journalArticleResearchpeer-review

Abstract

The evaluation of changes in Intervertebral Discs (IVDs) with 3D Magnetic Resonance (MR) Imaging (MRI) can be of interest for many clinical applications. This paper presents the evaluation of both IVD localization and IVD segmentation methods submitted to the Automatic 3D MRI IVD Localization and Segmentation challenge, held at the 2015 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI2015) with an on-site competition. With the construction of a manually annotated reference data set composed of 25 3D T2-weighted MR images acquired from two different studies and the establishment of a standard validation framework, quantitative evaluation was performed to compare the results of methods submitted to the challenge. Experimental results show that overall the best localization method achieves a mean localization distance of 0.8 mm and the best segmentation method achieves a mean Dice of 91.8%, a mean average absolute distance of 1.1 mm and a mean Hausdorff distance of 4.3 mm, respectively. The strengths and drawbacks of each method are discussed, which provides insights into the performance of different IVD localization and segmentation methods.

Original languageEnglish
Pages (from-to)327-344
Number of pages18
JournalMedical image analysis
Volume35
DOIs
Publication statusPublished - 1 Jan 2017

Fingerprint

Intervertebral Disc
Magnetic resonance
Magnetic Resonance Spectroscopy
Imaging techniques
Magnetic Resonance Imaging

Keywords

  • Challenge
  • Evaluation
  • Intervertebral disc
  • Localization
  • MRI
  • Segmentation

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Health Informatics
  • Computer Graphics and Computer-Aided Design

Fields of Expertise

  • Information, Communication & Computing

Cooperations

  • BioTechMed-Graz

Cite this

Evaluation and comparison of 3D intervertebral disc localization and segmentation methods for 3D T2 MR data: A grand challenge. / Zheng, Guoyan; Chu, Chengwen; Belavý, Daniel L.; Ibragimov, Bulat; Korez, Robert; Vrtovec, Tomaž; Hutt, Hugo; Everson, Richard; Meakin, Judith; Andrade, Isabel Lŏpez; Glocker, Ben; Chen, Hao; Dou, Qi; Heng, Pheng Ann; Wang, Chunliang; Forsberg, Daniel; Neubert, Aleš; Fripp, Jürgen; Urschler, Martin; Stern, Darko; Wimmer, Maria; Novikov, Alexey A.; Cheng, Hui; Armbrecht, Gabriele; Felsenberg, Dieter; Li, Shuo.

In: Medical image analysis, Vol. 35, 01.01.2017, p. 327-344.

Research output: Contribution to journalArticleResearchpeer-review

Zheng, G, Chu, C, Belavý, DL, Ibragimov, B, Korez, R, Vrtovec, T, Hutt, H, Everson, R, Meakin, J, Andrade, IL, Glocker, B, Chen, H, Dou, Q, Heng, PA, Wang, C, Forsberg, D, Neubert, A, Fripp, J, Urschler, M, Stern, D, Wimmer, M, Novikov, AA, Cheng, H, Armbrecht, G, Felsenberg, D & Li, S 2017, 'Evaluation and comparison of 3D intervertebral disc localization and segmentation methods for 3D T2 MR data: A grand challenge' Medical image analysis, vol. 35, pp. 327-344. https://doi.org/10.1016/j.media.2016.08.005
Zheng, Guoyan ; Chu, Chengwen ; Belavý, Daniel L. ; Ibragimov, Bulat ; Korez, Robert ; Vrtovec, Tomaž ; Hutt, Hugo ; Everson, Richard ; Meakin, Judith ; Andrade, Isabel Lŏpez ; Glocker, Ben ; Chen, Hao ; Dou, Qi ; Heng, Pheng Ann ; Wang, Chunliang ; Forsberg, Daniel ; Neubert, Aleš ; Fripp, Jürgen ; Urschler, Martin ; Stern, Darko ; Wimmer, Maria ; Novikov, Alexey A. ; Cheng, Hui ; Armbrecht, Gabriele ; Felsenberg, Dieter ; Li, Shuo. / Evaluation and comparison of 3D intervertebral disc localization and segmentation methods for 3D T2 MR data: A grand challenge. In: Medical image analysis. 2017 ; Vol. 35. pp. 327-344.
@article{010877d5cba6458383bd330aa3441c17,
title = "Evaluation and comparison of 3D intervertebral disc localization and segmentation methods for 3D T2 MR data: A grand challenge",
abstract = "The evaluation of changes in Intervertebral Discs (IVDs) with 3D Magnetic Resonance (MR) Imaging (MRI) can be of interest for many clinical applications. This paper presents the evaluation of both IVD localization and IVD segmentation methods submitted to the Automatic 3D MRI IVD Localization and Segmentation challenge, held at the 2015 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI2015) with an on-site competition. With the construction of a manually annotated reference data set composed of 25 3D T2-weighted MR images acquired from two different studies and the establishment of a standard validation framework, quantitative evaluation was performed to compare the results of methods submitted to the challenge. Experimental results show that overall the best localization method achieves a mean localization distance of 0.8 mm and the best segmentation method achieves a mean Dice of 91.8{\%}, a mean average absolute distance of 1.1 mm and a mean Hausdorff distance of 4.3 mm, respectively. The strengths and drawbacks of each method are discussed, which provides insights into the performance of different IVD localization and segmentation methods.",
keywords = "Challenge, Evaluation, Intervertebral disc, Localization, MRI, Segmentation",
author = "Guoyan Zheng and Chengwen Chu and Belav{\'y}, {Daniel L.} and Bulat Ibragimov and Robert Korez and Tomaž Vrtovec and Hugo Hutt and Richard Everson and Judith Meakin and Andrade, {Isabel Lŏpez} and Ben Glocker and Hao Chen and Qi Dou and Heng, {Pheng Ann} and Chunliang Wang and Daniel Forsberg and Aleš Neubert and J{\"u}rgen Fripp and Martin Urschler and Darko Stern and Maria Wimmer and Novikov, {Alexey A.} and Hui Cheng and Gabriele Armbrecht and Dieter Felsenberg and Shuo Li",
year = "2017",
month = "1",
day = "1",
doi = "10.1016/j.media.2016.08.005",
language = "English",
volume = "35",
pages = "327--344",
journal = "Medical image analysis",
issn = "1361-8415",
publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Evaluation and comparison of 3D intervertebral disc localization and segmentation methods for 3D T2 MR data: A grand challenge

AU - Zheng, Guoyan

AU - Chu, Chengwen

AU - Belavý, Daniel L.

AU - Ibragimov, Bulat

AU - Korez, Robert

AU - Vrtovec, Tomaž

AU - Hutt, Hugo

AU - Everson, Richard

AU - Meakin, Judith

AU - Andrade, Isabel Lŏpez

AU - Glocker, Ben

AU - Chen, Hao

AU - Dou, Qi

AU - Heng, Pheng Ann

AU - Wang, Chunliang

AU - Forsberg, Daniel

AU - Neubert, Aleš

AU - Fripp, Jürgen

AU - Urschler, Martin

AU - Stern, Darko

AU - Wimmer, Maria

AU - Novikov, Alexey A.

AU - Cheng, Hui

AU - Armbrecht, Gabriele

AU - Felsenberg, Dieter

AU - Li, Shuo

PY - 2017/1/1

Y1 - 2017/1/1

N2 - The evaluation of changes in Intervertebral Discs (IVDs) with 3D Magnetic Resonance (MR) Imaging (MRI) can be of interest for many clinical applications. This paper presents the evaluation of both IVD localization and IVD segmentation methods submitted to the Automatic 3D MRI IVD Localization and Segmentation challenge, held at the 2015 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI2015) with an on-site competition. With the construction of a manually annotated reference data set composed of 25 3D T2-weighted MR images acquired from two different studies and the establishment of a standard validation framework, quantitative evaluation was performed to compare the results of methods submitted to the challenge. Experimental results show that overall the best localization method achieves a mean localization distance of 0.8 mm and the best segmentation method achieves a mean Dice of 91.8%, a mean average absolute distance of 1.1 mm and a mean Hausdorff distance of 4.3 mm, respectively. The strengths and drawbacks of each method are discussed, which provides insights into the performance of different IVD localization and segmentation methods.

AB - The evaluation of changes in Intervertebral Discs (IVDs) with 3D Magnetic Resonance (MR) Imaging (MRI) can be of interest for many clinical applications. This paper presents the evaluation of both IVD localization and IVD segmentation methods submitted to the Automatic 3D MRI IVD Localization and Segmentation challenge, held at the 2015 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI2015) with an on-site competition. With the construction of a manually annotated reference data set composed of 25 3D T2-weighted MR images acquired from two different studies and the establishment of a standard validation framework, quantitative evaluation was performed to compare the results of methods submitted to the challenge. Experimental results show that overall the best localization method achieves a mean localization distance of 0.8 mm and the best segmentation method achieves a mean Dice of 91.8%, a mean average absolute distance of 1.1 mm and a mean Hausdorff distance of 4.3 mm, respectively. The strengths and drawbacks of each method are discussed, which provides insights into the performance of different IVD localization and segmentation methods.

KW - Challenge

KW - Evaluation

KW - Intervertebral disc

KW - Localization

KW - MRI

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=84983405445&partnerID=8YFLogxK

U2 - 10.1016/j.media.2016.08.005

DO - 10.1016/j.media.2016.08.005

M3 - Article

VL - 35

SP - 327

EP - 344

JO - Medical image analysis

JF - Medical image analysis

SN - 1361-8415

ER -