Due to the shortage of COVID-19 viral testing kits, radiology imaging is used to complement the screening process. Deep learning based methods are promising in automatically detecting COVID-19 disease in chest x-ray images. Most of these works first train a Convolutional Neural Network (CNN) on an existing large-scale chest x-ray image dataset and then fine-tune the model on the newly collected COVID-19 chest x-ray dataset, often at a much smaller scale. However, simple fine-tuning may lead to poor performance for the CNN model due to two issues, first the large domain shift present in chest x-ray datasets and second the relatively small scale of the COVID-19 chest x-ray dataset. In an attempt to address these two important issues, we formulate the problem of COVID-19 chest x-ray image classification in a semi-supervised open set domain adaptation setting and propose a novel domain adaptation method, S emi-supervised O pen set D omain A dversarial network (SODA). SODA is designed to align the data distributions across different domains in the general domain space and also in the common subspace of source and target data. In our experiments, SODA achieves a leading classification performance compared with recent state-of-the-art models in separating COVID-19 with common pneumonia. We also present initial results showing that SODA can produce better pathology localizations in the chest x-rays.

中文翻译：

---

SODA：通过半监督开放集域适应检测胸部 X 射线中的 COVID-19


由于 COVID-19 病毒检测试剂盒短缺，放射成像被用来补充筛查过程。基于深度学习的方法在胸部 X 射线图像中自动检测 COVID-19 疾病方面很有前景。这些工作中的大多数首先在现有的大规模胸部 X 射线图像数据集上训练卷积神经网络 (CNN)，然后在新收集的 COVID-19 胸部 X 射线数据集上微调模型，通常以小得多的数据集进行微调。规模。然而，由于两个问题，简单的微调可能会导致 CNN 模型的性能不佳，首先是胸部 X 射线数据集中存在较大的域偏移，其次是 COVID-19 胸部 X 射线数据集的规模相对较小。为了解决这两个问题，我们在半监督开放集域适应设置中制定了 COVID-19 胸部 X 射线图像分类问题，并提出了一种新颖的域适应方法，S emi-supervised O pen set D omain 对抗网络（SODA）。 SODA 旨在对齐通用域空间以及源数据和目标数据的公共子空间中不同域之间的数据分布。在我们的实验中，与最近最先进的模型相比，SODA 在区分 COVID-19 和普通肺炎方面实现了领先的分类性能。我们还提出了初步结果，表明 SODA 可以在胸部 X 光检查中产生更好的病理定位。