This post delves in to the use of CT scans in the COVID-19 pandemic, including current guidelines from medical experts (as of August 2020) and examples of recent research papers that use machine learning to make predictions from CT scans of COVID-19 patients.
这篇文章深入探讨了在COVID-19大流行中使用CT扫描的情况，包括医学专家的最新指南(截至2020年8月)以及最近的研究论文示例，这些论文使用机器学习对COVID-19患者的CT扫描做出预测。
Disclaimer: Nothing in this post is medical advice.
免责声明：这篇文章中没有什么是医疗建议。
RT-PCR诊断COVID-19 (Diagnosis of COVID-19 with RT-PCR)
The gold standard for diagnosis of COVID-19 is reverse transcription polymerase chain reaction (RT-PCR), which is a laboratory test that detects genetic material (RNA) from the COVID-19 virus:
诊断COVID-19的金标准是逆转录聚合酶链React(RT-PCR)，这是一项实验室测试，可检测出COVID-19病毒的遗传物质(RNA)：
The RT-PCR test is the “nasal swab test.” The nasal swab is intended to collect virus, if present, so that its RNA can be detected:
RT-PCR测试是“鼻拭子测试”。 鼻拭子旨在收集病毒(如果存在)，以便可以检测其RNA：
The RT-PCR test has high specificity (true negative rate). The specificity is close to 100%, meaning that almost all healthy people are correctly identified as healthy.
RT-PCR检测具有很高的特异性 (真阴性率)。 特异性接近100％，这意味着几乎所有健康人都可以正确识别为健康人。
The RT-PCR test has less sensitivity (aka true positive rate, aka recall), which measures the percentage of sick people correctly identified as sick. Sensitivity = (true positives) / (true positives + false negatives). This means that false negative tests can occur. For extra certainty that a patient is negative, multiple tests may be performed.
RT-PCR检测的敏感性较低(又称真实阳性率，又称为召回率)，该方法可测量正确识别为患病的患病者的百分比。 敏感度=(真阳性)/(真阳性+假阴性)。 这意味着可能会出现假阴性测试。 为了更加确定患者是否阴性，可以执行多次测试。
In spite of the imperfect sensitivity, RT-PCR is still the gold standard — the best test that we currently have for diagnosing COVID-19.
尽管灵敏度不完美，RT-PCR仍然是金标准，这是我们目前用于诊断COVID-19的最佳测试。
胸部CT在COVID-19中的作用 (The Role of Chest CT in COVID-19)
Given that RT-PCR is the gold standard for COVID-19 diagnosis, what is the role of chest CT in COVID-19?
鉴于RT-PCR是诊断COVID-19的金标准，胸部CT在COVID-19中的作用是什么？
The Fleischner Society published a multinational consensus statement in the journal Radiology in April 2020 that states (emphasis added):
弗莱什纳学会(Fleischner Society)于2020年4月在《 放射学 》杂志上发表了一项多国共识声明 ，声明(强调)：
Imaging is not indicated in patients suspected of having coronavirus disease 2019 (COVID-19) and mild clinical features unless they are at risk for disease progression.
除非怀疑有冠状病毒病2019(COVID-19)和轻度临床特征的患者， 否则不建议 影像学检查 。
Imaging is indicated in a patient with COVID-19 and worsening respiratory status.
成像 与COVID-19和恶化呼吸状态的患者表示。
In a resource-constrained environment, imaging indicated for medical triage of patients suspected of having COVID-19 who present with moderate-to-severe clinical features and a high pretest probability of disease.
在 资源受限的环境中 ，影像学表明对患有COVID-19的患者进行医学分类，这些患者表现出中度至重度的临床特征，并且疾病的高患病率很高。
Some research papers have claimed that chest CT scans have high sensitivity or high specificity for COVID-19 diagnosis, and that therefore CT scans could potentially be used for diagnosis. However, a review by Raptis et al., “Chest CT and Coronavirus Disease (COVID-19): A Critical Review of the Literature to Date” identifies numerous methodological problems with these studies. Raptis et al. conclude,
一些研究论文声称，胸部CT扫描对COVID-19诊断具有很高的敏感性或特异性，因此CT扫描可能会被用于诊断。 但是，Raptis等人的一篇综述文章“胸部CT和冠状病毒病(COVID-19)：迄今为止对文献的评论”发现了这些研究的许多方法学问题。 Raptis等。 得出结论，
Even in situations in which RT-PCR test results are negative, delayed, or not available, no data of which we are aware support CT as an adequate replacement test because its true sensitivity is unknown [and] CT findings lack specificity.
即使在RT-PCR测试结果为阴性，延迟或无法获得的情况下，我们也没有任何数据支持CT作为适当的替代测试，因为它的真实敏感性尚不清楚[并且] CT发现缺乏特异性。
In summary, chest CT scans are NOT currently recommended for COVID-19 diagnosis or screening. However, chest CTs may be helpful for evaluating COVID-19 complications, triage in resource-constrained environments, or prediction of worsening vs. improvement:
总之，目前不建议将胸部CT扫描用于COVID-19诊断或筛查。 但是，胸部CT可能有助于评估COVID-19并发症，在资源受限的环境中进行分类或预测恶化与改善之间的关系：
胸部CT出现COVID-19 (COVID-19 Appearance on Chest CT)
What does COVID-19 look like in a chest CT? The primary findings of COVID-19 are the findings of atypical pneumonia or organizing pneumonia. Such findings are non-specific, meaning that they are not unique to COVID-19 and can be seen in lung infections caused by bacteria or by other kinds of viruses.
胸部CT中COVID-19的外观如何？ COVID-19的主要发现是非典型性肺炎或组织性肺炎。 这些发现是非特异性的，这意味着它们不是COVID-19所独有的，并且可以在由细菌或其他种类的病毒引起的肺部感染中看到。
The following figure, based on CT slices from Radiology Assistant, shows some of the findings that can be seen in COVID-19 patients on chest CT. These findings include ground glass opacities, “crazy paving”, traction bronchiectasis, vascular dilation, and architectural distortion:
下图基于Radiology Assistant的 CT切片，显示了一些在胸部CT上的COVID-19患者中可以看到的发现。 这些发现包括毛玻璃不透明，“疯狂铺路”，支气管扩张，血管扩张和建筑变形：
COVID-19胸部CT中的机器学习 (Machine Learning in COVID-19 Chest CTs)
There has been considerable interest in building machine learning models to help with the COVID-19 pandemic. In general, any medical machine learning models should only be deployed after extensive validation, in agreement with medical best practices, and under the guidance of medical professionals.
建立机器学习模型以帮助应对COVID-19大流行已经引起了极大的兴趣。 一般而言，任何医疗机器学习模型都应在经过广泛验证之后，与医疗最佳实践达成一致并在医疗专业人员的指导下进行部署。
It is worth noting that the same model has the potential to be used in appropriate or inappropriate ways. For example, consider a COVID-19 diagnosis model, which is built to take in medical data and output the probability of COVID-19 diagnosis. This model could be used in line with medical guidelines to assist with triage in a resource-constrained environment. It could also be used in violation of medical guidelines to diagnose patients in place of the gold standard RT-PCR test.
值得注意的是，同一模型有可能以适当或不适当的方式使用。 例如，考虑一个COVID-19诊断模型，该模型建立用于接收医学数据并输出COVID-19诊断的可能性。 该模型可以根据医学指南使用，以帮助在资源受限的环境中进行分类。 它也可以代替医学标准用于诊断患者，以代替金标准RT-PCR测试。
All of the papers that I have seen so far about building machine learning models for chest CTs in COVID-19 are focused on development of models. This is distinct from deployment of models which requires a different kind of research focused on determining whether the model benefits clinicians and/or patients in a measurable way.
到目前为止，我所见过的有关在COVID-19中为胸部CT建立机器学习模型的所有论文都集中在模型的开发上。 这与模型的部署不同，模型的部署需要进行另一类研究，重点是确定模型是否以可衡量的方式使临床医生和/或患者受益。
Now I will overview three papers that have built machine learning models on COVID-19 CT data. Each of the papers takes a different approach.
现在，我将概述三篇基于COVID-19 CT数据构建了机器学习模型的论文。 每篇论文都采用不同的方法。
背景 (Background)
All COVID-19 CT scan machine learning models are based on convolutional neural networks. If you are not familiar with convolutional neural networks, please read Convolutional Neural Networks (CNNs) in 5 minutes.
所有COVID-19 CT扫描机器学习模型均基于卷积神经网络。 如果您不熟悉卷积神经网络，请在5分钟内阅读卷积神经网络(CNN) 。
Chest CT scans are volumetric grayscale medical images that depict the heart and lungs. They are used in the diagnosis and management of a wide range of conditions including cancer, fractures, and infections. For more background on chest CT machine learning, please see Chest CT Scan Machine Learning in 5 minutes.
胸部CT扫描是描绘心脏和肺部的体积灰度医学图像。 它们可用于诊断和处理各种疾病，包括癌症，骨折和感染。 有关胸部CT机器学习的更多背景知识，请参阅5分钟内的胸部CT扫描机器学习 。
论文＃1 (Paper #1)
李林等。 “使用人工智能基于肺部CT检测COVID-19和社区获得性肺炎：诊断准确性的评估。” 放射学 296.2(2020)。
In this paper, the authors build and evaluate a model that takes a stack of CT slices as input, and predicts whether the scan shows COVID-19 pneumonia, community acquired pneumonia (“CAP”), or no pneumonia.
在本文中，作者建立并评估了以一堆CT切片作为输入的模型，并预测扫描是否显示COVID-19肺炎，社区获得性肺炎(“ CAP”)或无肺炎。
All COVID-19 cases were confirmed positive using RT-PCR, to ensure that the ground truth was of good quality.
使用RT-PCR确认所有COVID-19病例均为阳性，以确保基本事实的质量。
In this model, the CT scans are first preprocessed using a U-Net, which performs lung segmentation to extract out only the lung regions and exclude the heart and body wall.
在此模型中，首先使用U-Net对CT扫描进行预处理，该网络执行肺分割以仅提取肺区域并排除心脏和体壁。
Here is a diagram of the U-Net architecture:
这是U-Net体系结构的示意图：
After this preprocessing step is complete, features are extracted from each CT slice using a ResNet50 convolutional neural network. The slice features are combined with max pooling and a final fully connected layer produces the predictions.
完成该预处理步骤后，使用ResNet50卷积神经网络从每个CT切片中提取特征。 切片特征与最大池合并在一起，最终的完全连接层产生了预测。
Here is an overall diagram of the “COVID-19 vs. CAP vs. non-pneumonia” model. Note that the U-Net preprocessing step is not explicitly shown:
这是“ COVID-19 vs. CAP vs.非肺炎”模型的整体图。 请注意，未明确显示U-Net预处理步骤：
Results: The authors report good performance, with AUCs of 0.96, 0.95, and 0.98 for COVID-19, community-acquired pneumonia (CAP), and no pneumonia, respectively:
结果：作者报告表现良好，COVID-19，社区获得性肺炎(CAP)和无肺炎的AUC分别为0.96、0.95和0.98：
The authors also made Grad-CAM visualizations as a form of model explanation. Grad-CAM is a technique for creating a heatmap that shows where a model is focusing for a particular class. For more details on Grad-CAM see Grad-CAM: Visual Explanations from Deep Networks.
作者还将Grad-CAM可视化作为模型说明的一种形式。 Grad-CAM是一种用于创建热图的技术，该热图可以显示模型针对特定类的焦点。 有关Grad-CAM的更多详细信息，请参阅Grad-CAM：深度网络的视觉说明 。
The authors provide a good commentary on Grad-CAM in their discussion section:
作者在其讨论部分中对Grad-CAM提供了很好的评论：
a disadvantage of all deep learning methods is the lack of transparency and interpretability (eg, it is impossible to determine what imaging features are being used to determine the output). While we used a heatmap to visualize the important regions in the scans leading to the decision of the algorithm, heatmaps are still not sufficient to visualize what unique features are used by the model to distinguish between COVID-19 and CAP.
所有深度学习方法的一个缺点是缺乏透明度和可解释性(例如，无法确定正在使用哪些成像功能来确定输出)。 尽管我们使用热图来可视化扫描过程中的重要区域，从而决定了算法，但热图仍然不足以可视化模型使用哪些独特功能来区分COVID-19和CAP。
Overall, this was a clean research study, with a ground truth based on the RT-PCR gold standard, a well-explained model architecture, and high performance. The one aspect that would benefit from updating is the motivation, which the authors summarize as, “RT-PCR is considered the reference standard; however it has been reported that chest CT could be used as a reliable and rapid approach for screening of COVID-19.” Currently (as of August 2020), chest CT scans are not recommended for screening. A better motivation, more in line with current clinical recommendations, would be to use their high-performing CT scan model to help with triage in a resource-constrained environment.
总体而言，这是一项干净的研究，具有基于RT-PCR黄金标准的基本事实，充分解释的模型架构和高性能。 从更新中受益的一个方面是动机，作者总结为：“ RT-PCR被认为是参考标准。 但是，据报道胸部CT可以作为一种可靠，快速的筛查COVID-19的方法。” 目前(截至2020年8月)， 不建议进行胸部CT扫描。 更好的动机(更符合当前的临床建议)将是使用它们的高性能CT扫描模型来帮助在资源受限的环境中进行分类。
论文＃2 (Paper #2)
黄璐等。 “ covid-19的串行定量胸部ct评估：深度学习方法。” 放射学：心胸成像 2.2(2020)：e200075。
The previous paper focused on a diagnosis model for COVID-19. Paper #2 by Huang et al. has a different goal: to investigate the relationship between the amount of lung opacification and COVID-19 severity.
先前的论文着重于COVID-19的诊断模型。 Huang等人的论文＃2。 有一个不同的目标：研究肺不透明量与COVID-19严重程度之间的关系。
On a chest CT scan the lungs are black because they are full of air. A “lung opacity” is a white splotch within the lungs, caused by material like water or pus accumulating inside of the lung tissue. Lung opacities are commonly seen in pneumonia, including pneumonia caused by COVID-19.
胸部CT扫描显示肺部黑色，因为它们充满了空气。 “肺部不透明”是指肺内的白色斑点，是由水或脓液等物质在肺组织内部积累引起的。 肺部混浊常见于肺炎，包括由COVID-19引起的肺炎。
In order to quantify the amount of lung opacification, Huang et al. use a commercial machine learning model called “InferRead CT Pneumonia.” Because this commercial model is proprietary the authors do not provide a diagram of the architecture, but they do mention that it is based on a U-Net, the segmentation architecture described in the previous section.
为了量化肺浑浊的数量，Huang等。 使用称为“ InferRead CT肺炎”的商业机器学习模型。 由于此商业模型是专有的，因此作者没有提供该体系结构的图表，但他们确实提到它基于U-Net (上一节中描述的分段体系结构)。
The InferRead CT Pneumonia model traces the outlines of all the lung opacities (more specifically, it identifies all of the pixels that are part of a lung opacity):
InferRead CT肺炎模型可追踪所有肺部混浊的轮廓(更具体地说，它可识别属于肺部混浊的所有像素)：
The percent of lung pixels that are opacified then serves as a quantitative measure of the extent of the lung opacification. A “100% opacified lung” would be all white instead of all black.
然后，不透明的肺像素百分比用作肺不透明程度的定量度量。 “百分百不透明的肺”将是全白而不是全黑。
Huang et al. analyze 126 patients with differing severity of COVID-19 and investigate whether more clinically severe COVID-19 corresponds to quantitatively more lung opacification. COVID-19 diagnosis was confirmed with RT-PCR, and the patient’s clinical severity was measured using the “Diagnosis and Treatment Protocol of Novel Coronavirus” from the National Health Commission of China, which classifies patients into mild, moderate, severe, and critical:
黄等。 分析了COVID-19严重程度不同的126位患者，并调查临床上更严重的COVID-19是否在数量上对应于更多的肺部混浊。 通过RT-PCR确认了COVID-19的诊断，并使用中国国家卫生委员会的“新型冠状病毒诊断和治疗方案”对患者的临床严重程度进行了分类，将患者分为轻度，中度，重度和严重：
Mild type: patients have mild clinical symptoms without CT findings of pneumonia
轻度型 ：患者有轻度临床症状，无肺炎的CT表现
Moderate type: patients have fever and respiratory symptoms with CT findings of pneumonia
中型 ：患者有发烧和呼吸道症状，伴有肺炎的CT表现
Severe type: patients meet any of the following criteria: a) respiratory distress (respiratory rate ≥ 30 bpm) b) SpO2 ≤ 93% at rest c) PaO2/FiO2 ≤ 300 mmHg
严重类型 ：患者符合以下任何标准：a)呼吸窘迫(呼吸频率≥30 bpm)b)静止时SpO2≤93％c)PaO2 / FiO2≤300 mmHg
Critical type: patients meet any of the following criteria: a) respiratory failure with mechanical ventilation b) shock other organ dysfunction and ICU therapy.
严重类型 ：患者符合以下任何标准：a)机械通气导致的呼吸衰竭b)休克其他器官功能障碍和ICU治疗。
Results: As you can see from the table below, the mild type patients had 0% lung opacification (i.e., fully healthy lungs), while the critical type patients had almost 50% lung opacification. A statistical test found that the difference in lung opacification across different clinical severity was significant with p < 0.001.
结果：从下表中可以看出，轻度型患者的肺部混浊为0％(即完全健康的肺)，而重症型患者的肺部混浊几乎为50％。 一项统计测试发现，不同临床严重程度的肺浑浊差异显着，p <0.001。
Huang et al. conclude,
黄等。 得出结论，
There were significant differences in lung opacification percentage, as measured by the deep learning algorithm, among patients with different clinical severity […] This automated tool for quantification of lung involvement may be used to monitor the disease progression and understand the temporal evolution of COVID-19.
根据深度学习算法，在具有不同临床严重程度的患者中，肺浑浊百分比存在显着差异[…]这种用于肺部受累定量的自动化工具可用于监测疾病进展和了解COVID- 19
论文＃3 (Paper #3)
梅雪岩等。 “通过人工智能可以快速诊断COVID-19患者。” 《自然医学》 (2020年)：1-5。
Similar to paper #1, the goal of paper #3 by Mei et al. is to build a COVID-19 diagnosis model. However, while paper #1 uses only CT data as the input, paper #3 uses both CT data and clinical data as input.
与论文1类似，Mei等人在论文3中的目标。 是建立一个COVID-19诊断模型。 然而，虽然论文＃1仅使用CT数据作为输入，但论文＃3同时使用CT数据和临床数据作为输入。
Mei et al. summarize their study as follows:
Mei等。 总结他们的研究如下：
In this study, we used artificial intelligence (AI) algorithms to integrate chest CT findings with clinical symptoms, exposure history and laboratory testing to rapidly diagnose patients who are positive for COVID-19.
在这项研究中，我们使用人工智能(AI)算法将胸部CT表现与临床症状，接触史和实验室检查相结合，以快速诊断出COVID-19阳性的患者。
The paper uses medical data from 905 patients, of which roughly half were positive for COVID-19. The task was binary classification, meaning patients are labeled with a one (COVID-19 positive) or a zero (COVID-19 negative).
该论文使用了905位患者的医学数据，其中大约一半对COVID-19呈阳性。 任务是二进制分类，这意味着将患者标记为一个(COVID-19阳性)或零(COVID-19阴性)。
The authors compare three different models: one model that uses only chest CT data, another model that uses only clinical information, and a third model that combines chest CT data and clinical information.
作者比较了三种不同的模型：一种仅使用胸部CT数据的模型，另一种仅使用临床信息的模型，以及将胸部CT数据和临床信息结合在一起的第三种模型。
These three different models are summarized as different pathways through the figure below:
下图将这三种不同的模型概括为不同的路径：
The model that uses chest CT data involves two steps: first, a slice selection model picks out the top 10 most abnormal slices, and then these slices are fed into a “diagnosis CNN” (ResNet18 architecture) to predict COVID-19 status.
使用胸部CT数据的模型涉及两个步骤：首先，切片选择模型挑选出最常见的10个最不正常的切片，然后将这些切片输入到“诊断CNN”(ResNet18体系结构)中以预测COVID-19的状态。
The model that combines chest CT data and clinical data involves feeding the output of the CT “diagnosis CNN” and the output of the clinical data model into a multilayer perceptron to produce the final prediction of COVID-19 status.
结合胸部CT数据和临床数据的模型涉及将CT“诊断CNN”的输出和临床数据模型的输出馈送到多层感知器中，以产生COVID-19状态的最终预测。
Results: The model combining CT and clinical data (joint model) had a 6% better AUROC than the model on CT data alone ( P = 0.00146), and a 12% better AUROC than the model on clinical information alone ( P < 1 × 10 −4), showing that COVID-19 prediction was most effective when both CT data and other clinical data were used together. The authors also compared their algorithm to a senior thoracic radiologist, and found that “the algorithm performed equally well in sensitivity (P=0.05) in the diagnosis of COVID-19 as compared to a senior thoracic radiologist.”
结果 ：结合CT和临床数据的模型(联合模型)的AUROC比仅基于CT数据的模型好6％( P = 0.00146)，而比仅根据临床信息的模型好12％( P <1× 10 -4)，表明当同时使用CT数据和其他临床数据时，COVID-19预测最有效。 作者还将他们的算法与一名高级胸腔放射科医生进行了比较，发现“与高级胸腔放射科医生相比，该算法在诊断COVID-19方面的敏感性相同(P = 0.05)。”
Mei et al. conclude,
Mei等。 得出结论，
While chest CT is not as accurate as RT-PCR in detecting the virus, it may be a useful tool for triage in the period before definitive results are obtained.
尽管胸部CT在检测病毒方面不如RT-PCR准确，但它可能是在获得明确结果之前的一段时间中进行分类的有用工具。
摘要 (Summary)
- Chest CTs are volumetric grayscale medical images that depict the heart and lungs. 胸部CT是描绘心脏和肺部的体积灰度医学图像。
- 2D and 3D convolutional neural networks (CNNs) are applied to classify, box, or segment CT abnormalities. 2D和3D卷积神经网络(CNN)用于分类，装箱或分割CT异常。
- The gold standard for COVID-19 diagnosis is RT-PCR, not chest CT. 诊断COVID-19的金标准是RT-PCR，而不是胸部CT。
In the context of COVID-19, machine learning on chest CTs has the potential to be helpful for: (a) triage in resource-constrained environments (e.g. diagnosis model), (b) evaluating complications, or © prediction of worsening vs. improvement.
在COVID-19的背景下，胸部CT上的机器学习可能有助于：(a)在资源受限的环境中进行分类( 例如诊断模型)，(b)评估并发症，或©恶化与改善的预测。
- Any machine learning models developed for medical applications should only be deployed in the real world after extensive validation, in agreement with medical best practices, and under the guidance of medical professionals. 为医疗应用开发的任何机器学习模型都应在经过广泛验证之后，并与医疗最佳实践达成一致，并在医疗专业人员的指导下，才能在现实世界中部署。
Originally published at http://glassboxmedicine.com on August 20, 2020.
最初于 2020年8月20日 发布在 http://glassboxmedicine.com 上。
翻译自: https://medium.com/@rachel.draelos/covid-19-chest-ct-scan-analysis-e45cf196a4fb
1077
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
