VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images

Sekuboyina, A; Husseini, ME; Bayat, A; Löffler, M; Liebl, H; Li, H; Tetteh, G; Kukačka, J; Payer, C; Štern, D; Urschler, M; Chen, M; Cheng, D; Lessmann, N; Hu, Y; Wang, T; Yang, D; Xu, D; Ambellan, F; Amiranashvili, T; Ehlke, M; Lamecker, H; Lehnert, S; Lirio, M; de Olaguer, NP; Ramm, H; Sahu, M; Tack, A; Zachow, S; Jiang, T; Ma, X; Angerman, C; Wang, X; Brown, K; Kirszenberg, A; Puybareau, É; Chen, D; Bai, Y; Rapazzo, BH; Yeah, T; Zhang, A; Xu, S; Hou, F; He, Z; Zeng, C; Xiangshang, Z; Liming, X; Netherton, TJ; Mumme, RP; Court, LE; Huang, Z; He, C; Wang, L-W; Ling, SH; Huỳnh, LD; Boutry, N; Jakubicek, R; Chmelik, J; Mulay, S; Sivaprakasam, M; Paetzold, JC; Shit, S; Ezhov, I; Wiestler, B; Glocker, B; Valentinitsch, A; Rempfler, M; Menze, BH; Kirschke, JS

VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images

Sekuboyina, A Husseini, ME Bayat, A Löffler, M Liebl, H Li, H Tetteh, G Kukačka, J Payer, C Štern, D Urschler, M Chen, M Cheng, D Lessmann, N Hu, Y Wang, T Yang, D Xu, D Ambellan, F Amiranashvili, T Ehlke, M Lamecker, H Lehnert, S Lirio, M de Olaguer, NP Ramm, H Sahu, M Tack, A Zachow, S Jiang, T Ma, X Angerman, C Wang, X Brown, K Kirszenberg, A Puybareau, É Chen, D Bai, Y Rapazzo, BH Yeah, T Zhang, A Xu, S Hou, F He, Z Zeng, C Xiangshang, Z Liming, X Netherton, TJ Mumme, RP Court, LE Huang, Z He, C Wang, L-W Ling, SH Huỳnh, LD Boutry, N Jakubicek, R Chmelik, J Mulay, S Sivaprakasam, M Paetzold, JC Shit, S Ezhov, I Wiestler, B Glocker, B Valentinitsch, A Rempfler, M Menze, BH Kirschke, JS

Permalink

Publisher:: ELSEVIER
Publication Type:: Journal Article
Citation:: Medical Image Analysis, 2021, 73, pp. 102166
Issue Date:: 2021-07-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Accepted versionAdobe PDF (26.9 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Sekuboyina, A
dc.contributor.author	Husseini, ME
dc.contributor.author	Bayat, A
dc.contributor.author	Löffler, M
dc.contributor.author	Liebl, H
dc.contributor.author	Li, H
dc.contributor.author	Tetteh, G
dc.contributor.author	Kukačka, J
dc.contributor.author	Payer, C
dc.contributor.author	Štern, D
dc.contributor.author	Urschler, M
dc.contributor.author	Chen, M
dc.contributor.author	Cheng, D
dc.contributor.author	Lessmann, N
dc.contributor.author	Hu, Y
dc.contributor.author	Wang, T
dc.contributor.author	Yang, D
dc.contributor.author	Xu, D
dc.contributor.author	Ambellan, F
dc.contributor.author	Amiranashvili, T
dc.contributor.author	Ehlke, M
dc.contributor.author	Lamecker, H
dc.contributor.author	Lehnert, S
dc.contributor.author	Lirio, M
dc.contributor.author	de Olaguer, NP
dc.contributor.author	Ramm, H
dc.contributor.author	Sahu, M
dc.contributor.author	Tack, A
dc.contributor.author	Zachow, S
dc.contributor.author	Jiang, T
dc.contributor.author	Ma, X
dc.contributor.author	Angerman, C
dc.contributor.author	Wang, X
dc.contributor.author	Brown, K
dc.contributor.author	Kirszenberg, A
dc.contributor.author	Puybareau, É
dc.contributor.author	Chen, D
dc.contributor.author	Bai, Y
dc.contributor.author	Rapazzo, BH
dc.contributor.author	Yeah, T
dc.contributor.author	Zhang, A
dc.contributor.author	Xu, S
dc.contributor.author	Hou, F
dc.contributor.author	He, Z
dc.contributor.author	Zeng, C
dc.contributor.author	Xiangshang, Z
dc.contributor.author	Liming, X
dc.contributor.author	Netherton, TJ
dc.contributor.author	Mumme, RP
dc.contributor.author	Court, LE
dc.contributor.author	Huang, Z
dc.contributor.author	He, C
dc.contributor.author	Wang, L-W
dc.contributor.author	Ling, SH
dc.contributor.author	Huỳnh, LD
dc.contributor.author	Boutry, N
dc.contributor.author	Jakubicek, R
dc.contributor.author	Chmelik, J
dc.contributor.author	Mulay, S
dc.contributor.author	Sivaprakasam, M
dc.contributor.author	Paetzold, JC
dc.contributor.author	Shit, S
dc.contributor.author	Ezhov, I
dc.contributor.author	Wiestler, B
dc.contributor.author	Glocker, B
dc.contributor.author	Valentinitsch, A
dc.contributor.author	Rempfler, M
dc.contributor.author	Menze, BH
dc.contributor.author	Kirschke, JS
dc.date.accessioned	2022-01-31T01:53:47Z
dc.date.available	2021-07-06
dc.date.available	2022-01-31T01:53:47Z
dc.date.issued	2021-07-01
dc.identifier.citation	Medical Image Analysis, 2021, 73, pp. 102166
dc.identifier.issn	1361-8415
dc.identifier.issn	1361-8423
dc.identifier.uri	http://hdl.handle.net/10453/153907
dc.description.abstract	Vertebral labelling and segmentation are two fundamental tasks in an automated spine processing pipeline. Reliable and accurate processing of spine images is expected to benefit clinical decision support systems for diagnosis, surgery planning, and population-based analysis of spine and bone health. However, designing automated algorithms for spine processing is challenging predominantly due to considerable variations in anatomy and acquisition protocols and due to a severe shortage of publicly available data. Addressing these limitations, the Large Scale Vertebrae Segmentation Challenge (VerSe) was organised in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2019 and 2020, with a call for algorithms tackling the labelling and segmentation of vertebrae. Two datasets containing a total of 374 multi-detector CT scans from 355 patients were prepared and 4505 vertebrae have individually been annotated at voxel level by a human-machine hybrid algorithm (https://osf.io/nqjyw/, https://osf.io/t98fz/). A total of 25 algorithms were benchmarked on these datasets. In this work, we present the results of this evaluation and further investigate the performance variation at the vertebra level, scan level, and different fields of view. We also evaluate the generalisability of the approaches to an implicit domain shift in data by evaluating the top-performing algorithms of one challenge iteration on data from the other iteration. The principal takeaway from VerSe: the performance of an algorithm in labelling and segmenting a spine scan hinges on its ability to correctly identify vertebrae in cases of rare anatomical variations. The VerSe content and code can be accessed at: https://github.com/anjany/verse.
dc.format	Print-Electronic
dc.language	eng
dc.publisher	ELSEVIER
dc.relation.ispartof	Medical Image Analysis
dc.relation.isbasedon	10.1016/j.media.2021.102166
dc.rights	This is a pre-copyedited, author-produced version of an article accepted for publication in [The Review of Corporate Finance Studies, 2021] is available online at: https://academic.oup.com/rcfs/advance-article-abstract/doi/10.1093/rcfs/cfab022/6414629?redirectedFrom=fulltext
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	09 Engineering, 11 Medical and Health Sciences
dc.subject.classification	Nuclear Medicine & Medical Imaging
dc.subject.mesh	Algorithms
dc.subject.mesh	Benchmarking
dc.subject.mesh	Humans
dc.subject.mesh	Image Processing, Computer-Assisted
dc.subject.mesh	Spine
dc.subject.mesh	Tomography, X-Ray Computed
dc.subject.mesh	Spine
dc.subject.mesh	Humans
dc.subject.mesh	Tomography, X-Ray Computed
dc.subject.mesh	Algorithms
dc.subject.mesh	Image Processing, Computer-Assisted
dc.subject.mesh	Benchmarking
dc.title	VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images
dc.type	Journal Article
utslib.citation.volume	73
utslib.location.activity	Netherlands
utslib.for	09 Engineering
utslib.for	11 Medical and Health Sciences
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - CHT - Health Technologies
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
pubs.organisational-group	/University of Technology Sydney/Centre for Health Technologies (CHT)
utslib.copyright.status	open_access	*
dc.date.updated	2022-01-31T01:53:45Z
pubs.publication-status	Published
pubs.volume	73

Abstract:

Vertebral labelling and segmentation are two fundamental tasks in an automated spine processing pipeline. Reliable and accurate processing of spine images is expected to benefit clinical decision support systems for diagnosis, surgery planning, and population-based analysis of spine and bone health. However, designing automated algorithms for spine processing is challenging predominantly due to considerable variations in anatomy and acquisition protocols and due to a severe shortage of publicly available data. Addressing these limitations, the Large Scale Vertebrae Segmentation Challenge (VerSe) was organised in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2019 and 2020, with a call for algorithms tackling the labelling and segmentation of vertebrae. Two datasets containing a total of 374 multi-detector CT scans from 355 patients were prepared and 4505 vertebrae have individually been annotated at voxel level by a human-machine hybrid algorithm (https://osf.io/nqjyw/, https://osf.io/t98fz/). A total of 25 algorithms were benchmarked on these datasets. In this work, we present the results of this evaluation and further investigate the performance variation at the vertebra level, scan level, and different fields of view. We also evaluate the generalisability of the approaches to an implicit domain shift in data by evaluating the top-performing algorithms of one challenge iteration on data from the other iteration. The principal takeaway from VerSe: the performance of an algorithm in labelling and segmenting a spine scan hinges on its ability to correctly identify vertebrae in cases of rare anatomical variations. The VerSe content and code can be accessed at: https://github.com/anjany/verse.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/153907