[论文解读] CovidCTNet: An Open-Source Deep Learning Approach to Identify Covid-19 Using CT Image

Tahereh Javaheri, Morteza Homayounfar+20 more|arXiv (Cornell University)|May 6, 2020

COVID-19 diagnosis using AI参考文献 34被引用 42

一句话总结

CovidCTNet 是一个开源的深度学习框架，通过 CT 图像识别 Covid-19，准确率约为 90%，在这一任务中表现优于放射科医生。

ABSTRACT

Coronavirus disease 2019 (Covid-19) is highly contagious with limited treatment options. Early and accurate diagnosis of Covid-19 is crucial in reducing the spread of the disease and its accompanied mortality. Currently, detection by reverse transcriptase polymerase chain reaction (RT-PCR) is the gold standard of outpatient and inpatient detection of Covid-19. RT-PCR is a rapid method, however, its accuracy in detection is only ~70-75%. Another approved strategy is computed tomography (CT) imaging. CT imaging has a much higher sensitivity of ~80-98%, but similar accuracy of 70%. To enhance the accuracy of CT imaging detection, we developed an open-source set of algorithms called CovidCTNet that successfully differentiates Covid-19 from community-acquired pneumonia (CAP) and other lung diseases. CovidCTNet increases the accuracy of CT imaging detection to 90% compared to radiologists (70%). The model is designed to work with heterogeneous and small sample sizes independent of the CT imaging hardware. In order to facilitate the detection of Covid-19 globally and assist radiologists and physicians in the screening process, we are releasing all algorithms and parametric details in an open-source format. Open-source sharing of our CovidCTNet enables developers to rapidly improve and optimize services, while preserving user privacy and data ownership.

研究动机与目标

• 鉴于 RT-PCR 的局限性和 CT 成像优势，推动快速、准确的新冠肺炎筛查。
• 提供一个开源、硬件无关的一套算法，用于区分 Covid-19、CAP 和其他肺部疾病。
• 在保护用户隐私和数据所有权的同时，实现快速、全球可访问的改进与部署。

提出的方法

• 开发一个开源的 CovidCTNet 流水线，能够使用 CT 图像将 Covid-19 与 CAP 及其他肺部疾病区分开来。
• 设计为能够处理异质的、小样本量和不同 CT 成像硬件。
• 以开源格式发布所有算法和参数细节，促进社区驱动的改进。
• 通过利用深度学习，专注于提高基于 CT 的检测准确性，超过放射科医生。

实验结果

研究问题

• RQ1 CT 成像结合 CovidCTNet 框架是否能够可靠地区分 Covid-19、CAP 及其他肺部疾病？
• RQ2 在异质、小样本的 CT 数据集上，CovidCTNet 能达到怎样的准确性，相较于放射科医生？
• RQ3 所提出的开源方法是否对 CT 硬件和成像条件的变化具有鲁棒性？
• RQ4 开源分享对隐私、数据所有权以及全球部署 Covid-19 检测工具有何影响？

主要发现

• CovidCTNet 将基于 CT 的检测准确性提高到约 90%。
• 模型的性能超过放射科医生，在此情境下放射科医生的准确率约为 70%。
• 所有算法和参数细节以开源格式发布，以实现全球快速改进。
• 该方法设计为硬件无关，且可扩展到异质的小数据集。
• 开源共享旨在保护用户隐私和数据所有权，同时实现广泛部署。