1. VERSE: A Vertebrae labelling and segmentation benchmark for multi-detector CT images
- Author
-
Mohanasankar Sivaprakasam, Timyoas Yeah, Tao Jiang, Xin Wang, Dalong Cheng, Manish Sahu, Maodong Chen, Sebastian Lehnert, Alexander Valentinitsch, Dong Yang, Nicolas Boutry, Shangliang Xu, Johannes C. Paetzold, Alexander Tack, Yujin Hu, Kevin W. Brown, Marilia Lirio, Malek El Husseini, Xu Liming, Darko Štern, Nikolas Lessmann, Suprosanna Shit, Tianfu Wang, Alexandre Kirszenberg, Martin Urschler, Daguang Xu, Feng Hou, Laurence E. Court, Raymond P. Mumme, Maximilian T. Löffler, Sai Ho Ling, Stefan Zachow, Zheng Xiangshang, Markus Rempfler, Yiwei Bai, Elodie Puybareau, Li-Wen Wang, Nicolás Pérez de Olaguer, Moritz Ehlke, Tamaz Amiranashvili, Di Chen, Christoph Angerman, Chan Zeng, Zixun Huang, Jiri Chmelik, Giles Tetteh, Hongwei Li, Jan S. Kirschke, Heiko Ramm, Amirhossein Bayat, Björn H. Menze, Ivan Ezhov, Jan Kukačka, Anjany Sekuboyina, Chenhang He, Ben Glocker, Tucker Netherton, Hans Liebl, Zhiqiang He, Roman Jakubicek, Christian Payer, Felix Ambellan, Supriti Mulay, Lê Duy Huỳnh, Brandon H. Rapazzo, Xinjun Ma, Amber Zhang, Hans Lamecker, and Benedikt Wiestler
- Subjects
FOS: Computer and information sciences ,Computer science ,Computer Vision and Pattern Recognition (cs.CV) ,Population ,Computer Science - Computer Vision and Pattern Recognition ,Labelling ,Segmentation ,Spine ,Vertebrae ,Health Informatics ,computer.software_genre ,09 Engineering, 11 Medical and Health Sciences ,Voxel ,medicine ,FOS: Electrical engineering, electronic engineering, information engineering ,Image Processing, Computer-Assisted ,Humans ,Radiology, Nuclear Medicine and imaging ,education ,education.field_of_study ,Radiological and Ultrasound Technology ,business.industry ,Image and Video Processing (eess.IV) ,Medical image computing ,Pattern recognition ,Electrical Engineering and Systems Science - Image and Video Processing ,Computer Graphics and Computer-Aided Design ,Hybrid algorithm ,Pipeline (software) ,Vertebra ,Nuclear Medicine & Medical Imaging ,Benchmarking ,medicine.anatomical_structure ,Benchmark (computing) ,Computer Vision and Pattern Recognition ,Artificial intelligence ,business ,Tomography, X-Ray Computed ,computer ,Algorithms ,Rare cancers Radboud Institute for Health Sciences [Radboudumc 9] - 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 on 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 towards 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 the results of this evaluation and further investigate the performance-variation at vertebra-level, scan-level, and at 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 content and code concerning VerSe can be accessed at: https://github.com/anjany/verse., Comment: Challenge report for the VerSe 2019 and 2020. Published in Medical Image Analysis (DOI: https://doi.org/10.1016/j.media.2021.102166)
- Published
- 2021