The pandemic of coronavirus disease 2019 (COVID-19) has lead to a global public health crisis spreading hundreds of countries. With the continuous growth of new infections, developing automated tools for COVID-19 identification with CT image is highly desired to assist the clinical diagnosis and reduce the tedious workload of image interpretation. To enlarge the datasets for developing machine learning methods, it is essentially helpful to aggregate the cases from different medical systems for learning robust and generalizable models. This paper proposes a novel joint learning framework to perform accurate COVID-19 identification by effectively learning with heterogeneous datasets with distribution discrepancy. We build a powerful backbone by redesigning the recently proposed COVID-Net in aspects of network architecture and learning strategy to improve the prediction accuracy and learning efficiency. On top of our improved backbone, we further explicitly tackle the cross-site domain shift by conducting separate feature normalization in latent space. Moreover, we propose to use a contrastive training objective to enhance the domain invariance of semantic embeddings for boosting the classification performance on each dataset. We develop and evaluate our method with two public large-scale COVID-19 diagnosis datasets made up of CT images. Extensive experiments show that our approach consistently improves the performanceson both datasets, outperforming the original COVID-Net trained on each dataset by 12.16% and 14.23% in AUC respectively, also exceeding existing state-of-the-art multi-site learning methods.

中文翻译：

---

使用重新设计的 COVID-19 CT 分类网络进行对比跨站点学习。

2019 年冠状病毒病 (COVID-19) 的大流行已导致全球公共卫生危机蔓延到数百个国家。随着新感染病例的不断增长，迫切需要开发利用CT图像识别COVID-19的自动化工具，以辅助临床诊断并减少繁琐的图像判读工作量。为了扩大用于开发机器学习方法的数据集，聚合来自不同医疗系统的病例以学习稳健且可推广的模型本质上是有帮助的。本文提出了一种新颖的联合学习框架，通过有效地学习具有分布差异的异构数据集来执行准确的 COVID-19 识别。我们通过在网络架构和学习策略方面重新设计最近提出的COVID-Net来构建强大的骨干网，以提高预测精度和学习效率。除了改进的主干网之外，我们还通过在潜在空间中进行单独的特征归一化来进一步明确地解决跨站点域转移问题。此外，我们建议使用对比训练目标来增强语义嵌入的域不变性，从而提高每个数据集的分类性能。我们使用两个由 CT 图像组成的公共大规模 COVID-19 诊断数据集来开发和评估我们的方法。大量实验表明，我们的方法持续提高了两个数据集的性能，AUC 分别比在每个数据集上训练的原始 COVID-Net 提高了 12.16% 和 14.23%，也超过了现有最先进的多站点学习方法。