Department of Biochemistry and Molecular Biology, National Clinical Research Center for Cancer, Key Laboratory of Cancer Prevention and Therapy, Key Laboratory of Breast Cancer Prevention and Therapy, Ministry of Education, Tianjin Clinical Research Center for Cancer, Tianjin Medical University Cancer Institute and Hospital, Tianjin, 300060, China.
Department of Hepatobiliary Oncology, Tianjin Medical University Cancer Institute and Hospital, National Clinical Research Center for Cancer, Tianjin, 300060, China.
Eur Radiol. 2021 Aug;31(8):6096-6104. doi: 10.1007/s00330-021-07715-1. Epub 2021 Feb 24.
OBJECTIVE: The outbreak of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-COV-2) has caused more than 26 million cases of Corona virus disease (COVID-19) in the world so far. To control the spread of the disease, screening large numbers of suspected cases for appropriate quarantine and treatment are a priority. Pathogenic laboratory testing is typically the gold standard, but it bears the burden of significant false negativity, adding to the urgent need of alternative diagnostic methods to combat the disease. Based on COVID-19 radiographic changes in CT images, this study hypothesized that artificial intelligence methods might be able to extract specific graphical features of COVID-19 and provide a clinical diagnosis ahead of the pathogenic test, thus saving critical time for disease control. METHODS: We collected 1065 CT images of pathogen-confirmed COVID-19 cases along with those previously diagnosed with typical viral pneumonia. We modified the inception transfer-learning model to establish the algorithm, followed by internal and external validation. RESULTS: The internal validation achieved a total accuracy of 89.5% with a specificity of 0.88 and sensitivity of 0.87. The external testing dataset showed a total accuracy of 79.3% with a specificity of 0.83 and sensitivity of 0.67. In addition, in 54 COVID-19 images, the first two nucleic acid test results were negative, and 46 were predicted as COVID-19 positive by the algorithm, with an accuracy of 85.2%. CONCLUSION: These results demonstrate the proof-of-principle for using artificial intelligence to extract radiological features for timely and accurate COVID-19 diagnosis. KEY POINTS: • The study evaluated the diagnostic performance of a deep learning algorithm using CT images to screen for COVID-19 during the influenza season. • As a screening method, our model achieved a relatively high sensitivity on internal and external CT image datasets. • The model was used to distinguish between COVID-19 and other typical viral pneumonia, both of which have quite similar radiologic characteristics.
目的：截至目前，严重急性呼吸综合征冠状病毒 2（SARS-CoV-2）的爆发已在全球导致超过 2600 万例冠状病毒病（COVID-19）病例。为控制疾病传播，对大量疑似病例进行适当的隔离和治疗是当务之急。病原体实验室检测通常是金标准，但存在显著假阴性的负担，这增加了对抗疾病的替代诊断方法的迫切需求。基于 COVID-19 在 CT 图像中的放射学变化，本研究假设人工智能方法可能能够提取 COVID-19 的特定图形特征，并在病原体检测之前提供临床诊断，从而为疾病控制节省关键时间。
方法：我们收集了 1065 例经病原体证实的 COVID-19 病例以及先前诊断为典型病毒性肺炎的 CT 图像。我们修改了 inception 迁移学习模型来建立算法，然后进行内部和外部验证。
结果：内部验证的总准确率为 89.5%，特异性为 0.88，敏感性为 0.87。外部测试数据集的总准确率为 79.3%，特异性为 0.83，敏感性为 0.67。此外，在 54 例 COVID-19 图像中，前两次核酸检测结果均为阴性，而算法预测为 COVID-19 阳性的有 46 例，准确率为 85.2%。
结论：这些结果证明了使用人工智能提取放射学特征进行 COVID-19 及时准确诊断的原理验证。
关键点：• 本研究评估了一种深度学习算法使用 CT 图像在流感季节筛选 COVID-19 的诊断性能。• 作为一种筛选方法，我们的模型在内部和外部 CT 图像数据集上均实现了较高的敏感性。• 该模型用于区分 COVID-19 和其他具有相似放射学特征的典型病毒性肺炎。
Cochrane Database Syst Rev. 2020-9-30
J Crit Care Med (Targu Mures). 2025-7-31
Diagnostics (Basel). 2025-7-21
Quant Imaging Med Surg. 2025-1-2
PeerJ Comput Sci. 2021-6-15
Zotero 插件
