Li Frank, Zhang Xuan, Comellas Alejandro P, Hoffman Eric A, Yang Tianbao, Lin Ching-Long
Roy J. Carver Department of Biomedical Engineering, University of Iowa, Iowa City, IA, United States.
IIHR-Hydroscience and Engineering, University of Iowa, Iowa City, IA, United States.
Front Physiol. 2022 Oct 11;13:999263. doi: 10.3389/fphys.2022.999263. eCollection 2022.
Patients who recovered from the novel coronavirus disease 2019 (COVID-19) may experience a range of long-term symptoms. Since the lung is the most common site of the infection, pulmonary sequelae may present persistently in COVID-19 survivors. To better understand the symptoms associated with impaired lung function in patients with post-COVID-19, we aimed to build a deep learning model which conducts two tasks: to differentiate post-COVID-19 from healthy subjects and to identify post-COVID-19 subtypes, based on the latent representations of lung computed tomography (CT) scans. CT scans of 140 post-COVID-19 subjects and 105 healthy controls were analyzed. A novel contrastive learning model was developed by introducing a lung volume transform to learn latent features of disease phenotypes from CT scans at inspiration and expiration of the same subjects. The model achieved 90% accuracy for the differentiation of the post-COVID-19 subjects from the healthy controls. Two clusters (C1 and C2) with distinct characteristics were identified among the post-COVID-19 subjects. C1 exhibited increased air-trapping caused by small airways disease (4.10%, = 0.008) and diffusing capacity for carbon monoxide %predicted (DLCO %predicted, 101.95%, < 0.001), while C2 had decreased lung volume (4.40L, < 0.001) and increased ground glass opacity (GGO%, 15.85%, < 0.001). The contrastive learning model is able to capture the latent features of two post-COVID-19 subtypes characterized by air-trapping due to small airways disease and airway-associated interstitial fibrotic-like patterns, respectively. The discovery of post-COVID-19 subtypes suggests the need for different managements and treatments of long-term sequelae of patients with post-COVID-19.
从2019年新型冠状病毒病（COVID-19）中康复的患者可能会出现一系列长期症状。由于肺部是最常见的感染部位，COVID-19幸存者可能会持续出现肺部后遗症。为了更好地了解COVID-19后患者肺功能受损相关的症状，我们旨在构建一个深度学习模型，该模型执行两项任务：基于肺部计算机断层扫描（CT）图像的潜在表征，将COVID-19后患者与健康受试者区分开来，并识别COVID-19后亚型。分析了140名COVID-19后患者和105名健康对照者的CT图像。通过引入肺容积变换，开发了一种新型对比学习模型，以从同一受试者吸气和呼气时的CT图像中学习疾病表型的潜在特征。该模型区分COVID-19后患者与健康对照者的准确率达到90%。在COVID-19后患者中识别出两个具有不同特征的聚类（C1和C2）。C1表现出由小气道疾病引起的气体潴留增加（4.10%， = 0.008）和一氧化碳弥散量预测值（DLCO %预测值，101.95%， < 0.001），而C2的肺容积减小（4.40L， < 0.001）且磨玻璃影增加（GGO%，15.85%， < 0.001）。对比学习模型能够捕捉分别以小气道疾病导致的气体潴留和气道相关的间质纤维化样模式为特征的两种COVID-后亚型的潜在特征。COVID-19后亚型的发现表明，需要对COVID-19后患者的长期后遗症进行不同的管理和治疗。
