Department of Mathematics, Nanjing University of Science and Technology, Nanjing, 210094, P. R. China.
Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, 100190, P. R. China.
Med Phys. 2021 Mar;48(3):1197-1210. doi: 10.1002/mp.14676. Epub 2021 Feb 6.
Accurate segmentation of lung and infection in COVID-19 computed tomography (CT) scans plays an important role in the quantitative management of patients. Most of the existing studies are based on large and private annotated datasets that are impractical to obtain from a single institution, especially when radiologists are busy fighting the coronavirus disease. Furthermore, it is hard to compare current COVID-19 CT segmentation methods as they are developed on different datasets, trained in different settings, and evaluated with different metrics.
To promote the development of data-efficient deep learning methods, in this paper, we built three benchmarks for lung and infection segmentation based on 70 annotated COVID-19 cases, which contain current active research areas, for example, few-shot learning, domain generalization, and knowledge transfer. For a fair comparison among different segmentation methods, we also provide standard training, validation and testing splits, evaluation metrics and, the corresponding code.
Based on the state-of-the-art network, we provide more than 40 pretrained baseline models, which not only serve as out-of-the-box segmentation tools but also save computational time for researchers who are interested in COVID-19 lung and infection segmentation. We achieve average dice similarity coefficient (DSC) scores of 97.3%, 97.7%, and 67.3% and average normalized surface dice (NSD) scores of 90.6%, 91.4%, and 70.0% for left lung, right lung, and infection, respectively.
To the best of our knowledge, this work presents the first data-efficient learning benchmark for medical image segmentation, and the largest number of pretrained models up to now. All these resources are publicly available, and our work lays the foundation for promoting the development of deep learning methods for efficient COVID-19 CT segmentation with limited data.
在 COVID-19 计算机断层扫描（CT）扫描中准确分割肺部和感染区域对于患者的定量管理至关重要。现有的大多数研究都是基于大型的、私人标注的数据集，从单个机构获取这些数据集是不切实际的，尤其是当放射科医生忙于抗击冠状病毒病时。此外，由于现有的 COVID-19 CT 分割方法是在不同的数据集上开发的，在不同的环境中进行训练，并使用不同的指标进行评估，因此很难进行比较。
为了促进数据高效的深度学习方法的发展，本文基于 70 个标注的 COVID-19 病例构建了三个肺部和感染分割基准，其中包含了当前的活跃研究领域，例如少样本学习、领域泛化和知识转移。为了在不同的分割方法之间进行公平的比较，我们还提供了标准的训练、验证和测试分割、评估指标和相应的代码。
基于最先进的网络，我们提供了超过 40 个预训练的基线模型，这些模型不仅可以作为即插即用的分割工具，还可以为对 COVID-19 肺部和感染分割感兴趣的研究人员节省计算时间。我们分别实现了左肺、右肺和感染的平均骰子相似系数（DSC）得分 97.3%、97.7%和 67.3%，以及平均归一化表面 DSC（NSD）得分 90.6%、91.4%和 70.0%。
据我们所知，这是第一篇针对医学图像分割的高效学习基准的工作，也是迄今为止提供的预训练模型数量最多的工作。所有这些资源都是公开可用的，我们的工作为促进使用有限数据的高效 COVID-19 CT 分割的深度学习方法的发展奠定了基础。
