Accurate and rapid diagnosis of coronavirus disease 2019 (COVID-19) from chest CT scans is of great importance and urgency during the worldwide outbreak. However, radiologists have to distinguish COVID-19 pneumonia from other pneumonia in a large number of CT scans, which is tedious and inefficient. Thus, it is urgently and clinically needed to develop an efficient and accurate diagnostic tool to help radiologists to fulfill the difficult task. In this study, we proposed a deep supervised autoencoder (DSAE) framework to automatically identify COVID-19 using multi-view features extracted from CT images. To fully explore features characterizing CT images from different frequency domains, DSAE was proposed to learn the latent representation by multi-task learning. The proposal was designed to both encode valuable information from different frequency features and construct a compact class structure for separability. To achieve this, we designed a multi-task loss function, which consists of a supervised loss and a reconstruction loss. Our proposed method was evaluated on a newly collected dataset of 787 subjects including COVID-19 pneumonia patients, other pneumonia patients, and normal subjects without abnormal CT findings. Extensive experimental results demonstrated that our proposed method achieved encouraging diagnostic performance and may have potential clinical application for the diagnosis of COVID-19.

中文翻译：

---

使用具有 CT 图像多视图特征的深度监督自动编码器自动诊断 COVID-19


在全球疫情爆发期间，通过胸部 CT 扫描准确快速诊断 2019 冠状病毒病（COVID-19）具有重要意义和紧迫性。然而，放射科医生必须在大量的CT扫描中将COVID-19肺炎与其他肺炎区分开来，这既繁琐又低效。因此，临床上迫切需要开发一种高效、准确的诊断工具来帮助放射科医生完成这一艰巨的任务。在本研究中，我们提出了一种深度监督自动编码器 (DSAE) 框架，利用从 CT 图像中提取的多视图特征自动识别 COVID-19。为了充分探索不同频域 CT 图像的特征，提出了 DSAE 通过多任务学习来学习潜在表示。该提案旨在对来自不同频率特征的有价值的信息进行编码，并构建紧凑的类结构以实现可分离性。为了实现这一目标，我们设计了一个多任务损失函数，它由监督损失和重建损失组成。我们提出的方法在新收集的 787 名受试者数据集上进行了评估，其中包括 COVID-19 肺炎患者、其他肺炎患者和没有异常 CT 发现的正常受试者。大量的实验结果表明，我们提出的方法取得了令人鼓舞的诊断性能，并可能在诊断 COVID-19 方面具有潜在的临床应用。