PuSH - Publikationsserver des Helmholtz Zentrums München

Sekuboyina, A.* ; Husseini, M.E.* ; Bayat, A.* ; Löffler, M.* ; Liebl, H.* ; Li, H.* ; Tetteh, G.* ; Kukacka, J. ; Payer, C.* ; Štern, D.* ; Urschler, M.* ; Chen, M.* ; Cheng, D.S.* ; Lessmann, N.* ; Hu, Y.* ; Wang, T.* ; Yang, D.* ; Xu, D.* ; Ambellan, F.* ; Amiranashvili, T.* ; Ehlke, M.* ; Lamecker, H.* ; Lehnert, S.* ; Lirio, M.* ; Olaguer, N.P.d.* ; 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, B.H.* ; Yeah, T.* ; Zhang, A.* ; Xu, S.* ; Hou, F.* ; He, Z.* ; Zeng, C.* ; Xiangshang, Z.* ; Liming, X.* ; Netherton, T.J.* ; Mumme, R.P.* ; Court, L.E.* ; Huang, Z.* ; He, C.* ; Wang, L.W.* ; Ling, S.H.* ; Huỳnh, L.D.* ; Boutry, N.* ; Jakubicek, R.* ; Chmelik, J.* ; Mulay, S.* ; Sivaprakasam, M.* ; Paetzold, J.C.* ; Shit, S.* ; Ezhov, I.* ; Wiestler, B.* ; Glocker, B.* ; Valentinitsch, A.* ; Rempfler, M.* ; Menze, B.H.* ; Kirschke, J.S.*

VERSE: A Vertebrae labelling and segmentation benchmark for multi-detector CT images.

Med. Image Anal. 73:102166 (2021)
DOI
Open Access Green: Postprint online verfügbar 09/2023
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.
Altmetric
Weitere Metriken?
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Wissenschaftlicher Artikel
Schlagwörter Labelling ; Segmentation ; Spine ; Vertebrae; Spine Segmentation; Fractures; Models; Bodies
ISSN (print) / ISBN 1361-8415
e-ISSN 1361-8415
Quellenangaben Band: 73, Heft: , Seiten: , Artikelnummer: 102166 Supplement: ,
Verlag Elsevier
Verlagsort Radarweg 29, 1043 Nx Amsterdam, Netherlands
Begutachtungsstatus Peer reviewed
Förderungen German Ministry of Research and Education (BMBF)
NVIDIA Corporation
European Research Council (ERC) under the European Union