VerSe: A Vertebrae labelling and segmentation benchmark for multi-detector CT images
Language English Country Netherlands Media print-electronic
Document type Journal Article, Research Support, Non-U.S. Gov't
Grant support
L30 CA274754
NCI NIH HHS - United States
PubMed
34340104
DOI
10.1016/j.media.2021.102166
PII: S1361-8415(21)00212-7
Knihovny.cz E-resources
- Keywords
- Labelling, Segmentation, Spine, Vertebrae,
- MeSH
- Algorithms MeSH
- Benchmarking * MeSH
- Humans MeSH
- Spine diagnostic imaging MeSH
- Tomography, X-Ray Computed * MeSH
- Image Processing, Computer-Assisted MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
- Research Support, Non-U.S. Gov't MeSH
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.
Chinese Academy of Sciences China
College of Computer Science and Technology Zhejiang University China
Computer Vision Group iFLYTEK Research South China China
Damo Academy Alibaba Group China
Department of Biomedical Engineering Brno University of Technology Czech Republic
Department of Computing Imperial College London UK
Department of Computing The Hong Kong Polytechnic University China
Department of Electronic and Information Engineering The Hong Kong Polytechnic University China
Department of Informatics Technical University of Munich Germany
Department of Mathematics University of Innsbruck Austria
Department of Neuroradiology Klinikum Rechts der Isar Germany
East China Normal University China
EPITA Research and Development Laboratory France
Friedrich Miescher Institute for Biomedical Engineering Switzerland
Gottfried Schatz Research Center Biophysics Medical University of Graz Austria
Indian Institute of Technology Madras India; Healthcare Technology Innovation Centre India
Institute of Biological and Medical Imaging Helmholtz Zentrum München Germany
Institute of Computer Graphics and Vision Graz University of Technology Austria
Institute of Computing Technology Chinese Academy of Sciences China
School of Biomedical Engineering Health Science Center Shenzhen University China
School of Computer Science The University of Auckland New Zealand
Shenzhen Research Institute of Big Data China
Technical University of Munich Germany
The School of Biomedical Engineering University of Technology Sydney Australia
References provided by Crossref.org
