VerSe：面向多排CT图像的多椎骨标注与分割基准
计算机视觉与模式识别
2022-04-06 v6 图像与视频处理
摘要
椎骨标注与分割是自动化脊柱处理流程中的两项基础任务。对脊柱图像进行可靠且准确的处理，有望惠及用于诊断、手术规划以及基于人群的脊柱与骨骼健康分析的临床决策支持系统。然而，设计自动化脊柱处理算法具有挑战性，主要原因在于解剖结构与采集协议存在显著差异，以及公开可用数据的严重匮乏。为应对这些局限，大型椎骨分割挑战赛（VerSe）于2019年和2020年与国际医学图像计算与计算机辅助干预会议（MICCAI）联合举办，征集面向椎骨标注与分割的算法。我们准备了包含两个数据集、共来自355名患者的374幅多排CT扫描的图像，并由人机混合算法在体素级别对4505块椎骨逐一进行了标注（https://osf.io/nqjyw/，https://osf.io/t98fz/）。共有25种算法在这些数据集上进行了基准测试。在本工作中，我们呈现了该评估的结果，并进一步在椎骨级、扫描级以及不同视野下考察了性能差异。我们还通过在一个挑战赛迭代中表现最优的算法在另一迭代的数据上进行评估，来检验这些方法对数据中隐式域偏移的泛化能力。VerSe的主要结论在于：算法在标注和分割脊柱扫描时的性能，取决于其在罕见解剖变异情况下正确识别椎骨的能力。有关VerSe的内容与代码可访问：https://github.com/anjany/verse。
引用
@article{arxiv.2001.09193,
title = {VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images},
author = {Anjany Sekuboyina and Malek E. Husseini and Amirhossein Bayat and Maximilian Löffler and Hans Liebl and Hongwei Li and Giles Tetteh and Jan Kukačka and Christian Payer and Darko Štern 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 Tamaz Amiranashvili and Moritz Ehlke and Hans Lamecker and Sebastian Lehnert and Marilia Lirio and Nicolás Pérez de Olaguer and Heiko Ramm and Manish Sahu and Alexander Tack and Stefan Zachow and Tao Jiang and Xinjun Ma and Christoph Angerman and Xin Wang and Kevin Brown and Alexandre Kirszenberg and Élodie Puybareau and Di Chen and Yiwei Bai and Brandon H. Rapazzo and Timyoas Yeah and Amber Zhang and Shangliang Xu and Feng Hou and Zhiqiang He and Chan Zeng and Zheng Xiangshang and Xu Liming and Tucker J. Netherton and Raymond P. Mumme and Laurence E. Court and Zixun Huang and Chenhang He and Li-Wen Wang and Sai Ho Ling and Lê Duy Huynh and Nicolas Boutry and Roman Jakubicek and Jiri Chmelik and Supriti Mulay and Mohanasankar Sivaprakasam and Johannes C. Paetzold and Suprosanna Shit and Ivan Ezhov and Benedikt Wiestler and Ben Glocker and Alexander Valentinitsch and Markus Rempfler and Björn H. Menze and Jan S. Kirschke},
journal= {arXiv preprint arXiv:2001.09193},
year = {2022}
}
备注
Challenge report for the VerSe 2019 and 2020. Published in Medical Image Analysis (DOI: https://doi.org/10.1016/j.media.2021.102166)