[论文解读] COVIDomaly: A Deep Convolutional Autoencoder Approach for Detecting Early Cases of COVID-19.

Faraz Khoshbakhtian, Ahmed Ashraf+1 more|arXiv (Cornell University)|Oct 6, 2020

COVID-19 diagnosis using AI被引用 6

一句话总结

COVIDomaly 提出了一种使用深度卷积自编码器的一类异常检测框架，旨在在缺乏标记感染数据的情况下，从胸部X光片中识别早期COVID-19病例。该模型仅使用健康或非COVID-19肺炎X光片进行训练，实现了0.7652的合并ROC-AUC，表明在数据有限的情况下具有早期疫情检测的潜力。

ABSTRACT

As of September 2020, the COVID-19 pandemic continues to devastate the health and well-being of the global population. With more than 33 million confirmed cases and over a million deaths, global health organizations are still a long way from fully containing the pandemic. This pandemic has raised serious questions about the emergency preparedness of health agencies, not only in terms of treatment of an unseen disease, but also in identifying its early symptoms. In the particular case of COVID-19, several studies have indicated that chest radiography images of the infected patients show characteristic abnormalities. However, at the onset of a given pandemic, such as COVID-19, there may not be sufficient data for the affected cases to train models for their robust detection. Hence, supervised classification is ill-posed for this problem because the time spent in collecting large amounts of infected peoples' data could lead to the loss of human lives and delays in preventive interventions. Therefore, we formulate this problem within a one-class classification framework, in which the data for healthy patients is abundantly available, whereas no training data is present for the class of interest (COVID-19 in our case). To solve this problem, we present COVIDomaly, a convolutional autoencoder framework to detect unseen COVID-19 cases from the chest radiographs. We tested two settings on a publicly available dataset (COVIDx) by training the model on chest X-rays from (i) only healthy adults, and (ii) healthy and other non-COVID-19 pneumonia, and detected COVID-19 as an anomaly. After performing 3-fold cross validation, we obtain a pooled ROC-AUC of 0.7652 and 0.6902 in the two settings respectively. These results are very encouraging and pave the way towards research for ensuring emergency preparedness in future pandemics, especially the ones that could be detected from chest X-rays.

研究动机与目标

• 为解决在大流行初期缺乏标记感染数据时检测早期COVID-19病例的挑战。
• 开发一种一类分类框架，将COVID-19视为异常，仅使用健康或非COVID-19肺炎X光片进行训练。
• 通过医学影像实现对新型传染性疾病的早期检测，提升应急准备能力。

提出的方法

• 仅使用健康个体的胸部X光片对深度卷积自编码器进行训练，以学习正常的解剖结构模式。
• 模型对输入X光片进行重建，并将重建误差作为异常评分，误差越高表示可能存在COVID-19。
• 评估了两种训练设置：一种仅使用健康成年人的X光片，另一种同时包含健康和非COVID-19肺炎X光片。
• 通过设定重建误差的阈值来检测异常，高误差表示可能存在COVID-19感染。
• 在公开的COVIDx数据集上进行3折交叉验证以评估性能。
• 该框架基于正常X光片丰富而感染病例稀少且在大流行早期难以获取的假设。

实验结果

研究问题

• RQ1 仅使用正常或非COVID-19肺炎X光片进行训练的一类异常检测模型，能否有效识别早期COVID-19病例？
• RQ2 在训练集中包含非COVID-19肺炎X光片，是否会影响模型将COVID-19识别为异常的能力？
• RQ3 卷积自编码器框架在公开数据集上检测未见COVID-19病例的性能如何？
• RQ4 该方法能否作为未来大流行中在标记数据有限情况下的可行应急检测系统？

主要发现

• 当仅使用健康成年人X光片进行训练时，模型在未见COVID-19病例上的合并ROC-AUC达到0.7652，表明其检测性能出色。
• 当同时使用健康和非COVID-19肺炎X光片进行训练时，模型的合并ROC-AUC为0.6902，显示出中等但依然有希望的检测能力。
• 结果表明，即使目标类别训练数据极少，卷积自编码器框架也能有效检测胸部X光片中的异常。
• 该框架对数据稀缺具有鲁棒性，适用于在感染病例数据不可用的早期大流行阶段进行检测。
• 本研究证实，使用自编码器的一类分类方法在紧急情况下通过医学影像检测新发疾病是切实可行的。
• 研究结果支持将此类模型作为未来大流行应急准备策略的一部分。