VerSe: A Vertebrae Labelling and Segmentation Benchmark

Anjany  Sekuboyina; Amirhossein  Bayat; Malek E Husseini; Maximilian  Löffler; Markus  Rempfler; Jan Kukačka; Giles Tetteh; Alexander  Valentinitsch; Christian Payer; Martin Urschler; Maodong Chen; Dalong  Cheng; Nikolas Lessmann; Yujin Hu; Tianfu Wang; Dong  Yang; Daguang Xu; Felix  Ambellan; Stefan Zachowk; Tao Jiang; Xinjun  Ma; Christoph Angerman; Xin Wang; Qingyue Wei; Kevin  Brown; Matthias Wolf; Alexandre Kirszenberg; Élodie  Puybareauq; Björn H. Menze; Jan S Kirschke

VerSe: A Vertebrae Labelling and Segmentation Benchmark

Anjany Sekuboyina, Amirhossein Bayat, Malek E Husseini, Maximilian Löffler, Markus Rempfler, Jan Kukačka, Giles Tetteh, Alexander Valentinitsch, Christian Payer, Martin Urschler, Maodong Chen, Dalong Cheng, Nikolas Lessmann, Yujin Hu, Tianfu Wang, Dong Yang, Daguang Xu, Felix Ambellan, Stefan Zachowk, Tao JiangXinjun Ma, Christoph Angerman, Xin Wang, Qingyue Wei, Kevin Brown, Matthias Wolf, Alexandre Kirszenberg, Élodie Puybareauq, Björn H. Menze, Jan S Kirschke

Institute of Computer Graphics and Vision (7100)

Research output: Working paper › Preprint

Abstract

In this paper we report the challenge set-up and results of the Large Scale Vertebrae Segmentation Challenge (VerSe) organized in conjunction with the MICCAI 2019. The challenge consisted of two tasks, vertebrae labelling and vertebrae segmentation. For this a total of 160 multidetector CT scan cohort closely resembling clinical setting was prepared and was annotated at a voxel-level by a human-machine hybrid algorithm. In this paper we also present the annotation protocol and the algorithm that aided the medical experts in the annotation process. Eleven fully automated algorithms were benchmarked on this data with the best performing algorithm achieving a vertebrae identification rate of 95% and a Dice coefficient of 90%. VerSe'19 is an open-call challenge at its image data along with the annotations and evaluation tools will continue to be publicly accessible through its online portal.

Original language	English
Publication status	Published - 24 Jan 2020

Publication series

Name	arXiv.org e-Print archive
Publisher	Cornell University Library

Access to Document

https://arxiv.org/abs/2001.09193Licence: CC BY-SA 4.0

Cite this

Sekuboyina, A., Bayat, A., E Husseini, M., Löffler, M., Rempfler, M., Kukačka, J., Tetteh, G., Valentinitsch, A., Payer, C., Urschler, M., Chen, M., Cheng, D., Lessmann, N., Hu, Y., Wang, T., Yang, D., Xu, D., Ambellan, F., Zachowk, S., ... S Kirschke, J. (2020). VerSe: A Vertebrae Labelling and Segmentation Benchmark. (arXiv.org e-Print archive). https://arxiv.org/abs/2001.09193

Sekuboyina, A, Bayat, A, E Husseini, M, Löffler, M, Rempfler, M, Kukačka, J, Tetteh, G, Valentinitsch, A, Payer, C, Urschler, M, Chen, M, Cheng, D, Lessmann, N, Hu, Y, Wang, T, Yang, D, Xu, D, Ambellan, F, Zachowk, S, Jiang, T, Ma, X, Angerman, C, Wang, X, Wei, Q, Brown, K, Wolf, M, Kirszenberg, A, Puybareauq, É, Menze, BH & S Kirschke, J 2020 'VerSe: A Vertebrae Labelling and Segmentation Benchmark' arXiv.org e-Print archive. <https://arxiv.org/abs/2001.09193>

@techreport{dee158f0ed8b4c27b064a1ab0272db92,

title = "VerSe: A Vertebrae Labelling and Segmentation Benchmark",

abstract = "In this paper we report the challenge set-up and results of the Large Scale Vertebrae Segmentation Challenge (VerSe) organized in conjunction with the MICCAI 2019. The challenge consisted of two tasks, vertebrae labelling and vertebrae segmentation. For this a total of 160 multidetector CT scan cohort closely resembling clinical setting was prepared and was annotated at a voxel-level by a human-machine hybrid algorithm. In this paper we also present the annotation protocol and the algorithm that aided the medical experts in the annotation process. Eleven fully automated algorithms were benchmarked on this data with the best performing algorithm achieving a vertebrae identification rate of 95% and a Dice coefficient of 90%. VerSe'19 is an open-call challenge at its image data along with the annotations and evaluation tools will continue to be publicly accessible through its online portal.",

author = "Anjany Sekuboyina and Amirhossein Bayat and {E Husseini}, Malek and Maximilian L{\"o}ffler and Markus Rempfler and Jan Kuka{\v c}ka and Giles Tetteh and Alexander Valentinitsch and Christian Payer and Martin Urschler and Maodong Chen and Dalong Cheng and Nikolas Lessmann and Yujin Hu and Tianfu Wang and Dong Yang and Daguang Xu and Felix Ambellan and Stefan Zachowk and Tao Jiang and Xinjun Ma and Christoph Angerman and Xin Wang and Qingyue Wei and Kevin Brown and Matthias Wolf and Alexandre Kirszenberg and {\'E}lodie Puybareauq and Menze, {Bj{\"o}rn H.} and {S Kirschke}, Jan",

year = "2020",

month = jan,

day = "24",

language = "English",

series = "arXiv.org e-Print archive",

publisher = "Cornell University Library",

type = "WorkingPaper",

institution = "Cornell University Library",

}

TY - UNPB

T1 - VerSe: A Vertebrae Labelling and Segmentation Benchmark

AU - Sekuboyina, Anjany

AU - Bayat, Amirhossein

AU - E Husseini, Malek

AU - Löffler, Maximilian

AU - Rempfler, Markus

AU - Kukačka, Jan

AU - Tetteh, Giles

AU - Valentinitsch, Alexander

AU - Payer, Christian

AU - Urschler, Martin

AU - Chen, Maodong

AU - Cheng, Dalong

AU - Lessmann, Nikolas

AU - Hu, Yujin

AU - Wang, Tianfu

AU - Yang, Dong

AU - Xu, Daguang

AU - Ambellan, Felix

AU - Zachowk, Stefan

AU - Jiang, Tao

AU - Ma, Xinjun

AU - Angerman, Christoph

AU - Wang, Xin

AU - Wei, Qingyue

AU - Brown, Kevin

AU - Wolf, Matthias

AU - Kirszenberg, Alexandre

AU - Puybareauq, Élodie

AU - Menze, Björn H.

AU - S Kirschke, Jan

PY - 2020/1/24

Y1 - 2020/1/24

N2 - In this paper we report the challenge set-up and results of the Large Scale Vertebrae Segmentation Challenge (VerSe) organized in conjunction with the MICCAI 2019. The challenge consisted of two tasks, vertebrae labelling and vertebrae segmentation. For this a total of 160 multidetector CT scan cohort closely resembling clinical setting was prepared and was annotated at a voxel-level by a human-machine hybrid algorithm. In this paper we also present the annotation protocol and the algorithm that aided the medical experts in the annotation process. Eleven fully automated algorithms were benchmarked on this data with the best performing algorithm achieving a vertebrae identification rate of 95% and a Dice coefficient of 90%. VerSe'19 is an open-call challenge at its image data along with the annotations and evaluation tools will continue to be publicly accessible through its online portal.

AB - In this paper we report the challenge set-up and results of the Large Scale Vertebrae Segmentation Challenge (VerSe) organized in conjunction with the MICCAI 2019. The challenge consisted of two tasks, vertebrae labelling and vertebrae segmentation. For this a total of 160 multidetector CT scan cohort closely resembling clinical setting was prepared and was annotated at a voxel-level by a human-machine hybrid algorithm. In this paper we also present the annotation protocol and the algorithm that aided the medical experts in the annotation process. Eleven fully automated algorithms were benchmarked on this data with the best performing algorithm achieving a vertebrae identification rate of 95% and a Dice coefficient of 90%. VerSe'19 is an open-call challenge at its image data along with the annotations and evaluation tools will continue to be publicly accessible through its online portal.

M3 - Preprint

T3 - arXiv.org e-Print archive

BT - VerSe: A Vertebrae Labelling and Segmentation Benchmark

ER -