Deep Learning and Subtyping of Post-COVID-19 Lung Progression Phenotypes

COVID-19 后肺部进展表型的深度学习和亚型分析

基本信息

批准号：
10634998
负责人：
CHING-LONG LIN
金额：
$ 75.67万
依托单位：
UNIVERSITY OF IOWA
依托单位国家：
美国
项目类别：
财政年份：
2023
资助国家：
美国
起止时间：
2023-06-01 至 2028-02-29
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10634998
关键词：
Air Alveolus Biological Markers COVID-19 COVID-19 patient COVID-19 survivors Characteristics Chronic Obstructive Pulmonary Disease Classification Clinic Clinical Clinical Data Clinical assessments Data Data Analyses Dedications Development Dimensions Disease Exhibits Exposure to Goals Health Healthcare Image Iowa Knowledge Learning Liquid substance Long-Term Effects Lung Modeling Outcome Patient Care Patients Phenotype Public Health Pulmonary Emphysema Radiation Dose Unit Recommendation Research Resolution SARS-CoV-2 infection Site Structure of parenchyma of lung Study Subject Techniques Testing Thoracic Radiography Time Training Universities Validation Virus Diseases Visit X-Ray Computed Tomography X-Ray Medical Imaging clinical biomarkers cohort cost deep learning deep learning algorithm deep learning model experience fibrotic lung follow-up human subject imaging biomarker improved in silico in vivo learning algorithm learning strategy long-term sequelae lung imaging novel coronavirus particle phenotypic biomarker post-COVID-19 prototype pulmonary function small airways disease supervised learning transfer learning

项目摘要

PROJECT SUMMARY Patients who recover from the novel coronavirus disease 2019 (COVID-19) may experience a range of long- term health consequences. Since the lung is the primary site of viral infection, pulmonary sequelae may present persistently in COVID-19 survivors. Thus, clinical assessment of COVID-19 survivors in conjunction with chest X-ray (CXR) and computed tomography (CT) is recommended. CXR is more accessible, whereas CT provides more detailed information. Our long-term goal is to develop an integrated deep learning model that can assess lung images to assist with the management and treatment of long-term sequelae of post-COVID-19 subjects. The primary objective of the proposed research is to advance contrastive self-supervised learning models that take advantage of the accessibility of CXR scanners and the accuracy of CT images, identify the subtypes in patients with post-COVID-19, and characterize clinical, imaging and mechanistic biomarkers within subtypes. Our central hypothesis is that post-COVID-19 subtypes exist and they are characterized by distinct progression phenotypes. To test this hypothesis and achieve the primary objective, we will perform the following four specific aims. In Aim 1, we will advance contrastive learning methods to handle large-scale images with low training costs, and fine-tune the classifier and the encoder network on large-scale CXR images to detect post-COVID- 19 subjects. In Aim 2, we will advance contrastive learning methods that learn from CT images acquired at different volumes and different times to differentiate post-COVID-19 subjects from other cohorts and identify subtypes. In Aim 3, we will apply computational fluid and particle dynamics techniques to derive mechanistic biomarkers to explain the associations between clinical and imaging biomarkers in post-COVID-19 subtypes. In Aim 4, we will conduct a human subject study that examines post-COVID-19 subjects at 36-48 months after initial follow-up visits to assess the progression features of their clinical and imaging biomarkers. In summary, we will advance contrastive self-supervised learning algorithms based on CXR and CT images, respectively, for accessibility (Aim 1) and accuracy (Aim 2). We will generate in silico data for feature interpretability (Aim 3) and gather in vivo data for model training and validation (Aim 4). The pre-trained model from Aim 2 will be fine-tuned via transfer learning to input CXR images that are classified as post-COVID-19 by the model from Aim 1. An integrated deep learning model based on the two models from Aim 1 and 2 will take CXR images as inputs to provide CT-based detailed phenotypic information together with mechanistically and clinically meaningful interpretation. If successful, our study will not only advance contrastive learning algorithms, but also elucidate the pulmonary sequelae of post-COVID-19 patients in subtypes and associated clinical, imaging and mechanistic biomarkers. The ability to identify progression subtypes and associated phenotypic biomarkers will have a positive impact on the management and treatment of patients with post-COVID-19.

项目概要从 2019 年新型冠状病毒病 (COVID-19) 中康复的患者可能会经历一系列长期的术语健康后果。由于肺部是病毒感染的主要部位，因此可能会出现肺部后遗症持续存在于 COVID-19 幸存者中。因此，结合胸部检查对 COVID-19 幸存者进行临床评估建议进行 X 射线 (CXR) 和计算机断层扫描 (CT)。 CXR 更容易接近，而 CT 提供更详细的信息。我们的长期目标是开发一个集成的深度学习模型，可以评估肺部图像有助于管理和治疗 COVID-19 后受试者的长期后遗症。拟议研究的主要目标是推进对比自我监督学习模型利用 CXR 扫描仪的可访问性和 CT 图像的准确性，识别以下疾病的亚型患有后 COVID-19 的患者，并表征亚型内的临床、影像和机械生物标志物。我们的中心假设是，后 COVID-19 亚型存在，并且它们的特点是明显的进展表型。为了检验这一假设并实现主要目标，我们将执行以下四个具体步骤目标。在目标 1 中，我们将推进对比学习方法来处理低训练量的大规模图像成本，并在大规模 CXR 图像上微调分类器和编码器网络以检测新冠病毒后的情况 19 个科目。在目标 2 中，我们将推进对比学习方法，从以下位置获取的 CT 图像中学习：不同的容量和不同的时间来区分 COVID-19 后受试者与其他队列并识别亚型。在目标 3 中，我们将应用计算流体和粒子动力学技术来推导机械生物标志物来解释 COVID-19 后亚型中临床和影像生物标志物之间的关联。在目标 4，我们将进行一项人类受试者研究，检查 COVID-19 后 36-48 个月的受试者初次随访以评估其临床和影像生物标志物的进展特征。总之，我们将分别推进基于 CXR 和 CT 图像的对比自监督学习算法，可访问性（目标 1）和准确性（目标 2）。我们将生成计算机数据以实现特征可解释性（目标 3）和收集体内数据用于模型训练和验证（目标 4）。 Aim 2 的预训练模型将进行微调通过迁移学习输入 CXR 图像，这些图像被 Aim 1 的模型分类为 post-COVID-19。基于 Aim 1 和 2 的两个模型的集成深度学习模型将 CXR 图像作为输入提供基于 CT 的详细表型信息以及机械和临床意义解释。如果成功，我们的研究不仅将推进对比学习算法，还将阐明 COVID-19 后患者肺部后遗症的亚型及相关临床、影像学和机制生物标志物。识别进展亚型和相关表型生物标志物的能力将具有对 COVID-19 后患者的管理和治疗产生积极影响。