在使用VGG-16深度学习的慢性阻塞性肺病患者中预测急性恶化现象型
Shengchuan Feng1, Ran Zhang2, Wenxiu Zhang3
1State Key Laboratory of Respiratory Disease, National Clinical Research Center for Respiratory Disease, National Center for Respiratory Medicine, Department of Respiratory Medicine, Guangzhou Institute of Respiratory Health, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China, fengsc2022@163.com.
来自HRCT扫描的深度学习功能有效地预测慢性阻塞性肺病 (COPD) 患者急性恶化. 该模型在识别易患COPD急性恶化 (AECOPD) 的患者方面表现出强的表现.
科学领域:
- 肺部医学 肺部医学
- 放射学 放射学是一门学科.
- 医疗保健中的人工智能
背景情况:
- 慢性阻塞性肺病 (COPD) 的急性恶化严重导致住院,发病率和死亡率.
- 预测这些恶化对于及时干预和改善患者结果至关重要.
- 深度学习 (DL) 方法为呼吸系统疾病的增强预测建模提供了潜力.
研究的目的:
- 开发和验证COPD患者急性恶化预测模型 (AECOPD).
- 利用来自高分辨率计算机断层扫描 (HRCT) 扫描的深度学习功能.
- 用定量CT参数和临床特征来评估模型的性能.
主要方法:
- 追溯分析了219名COPD患者的呼吸和呼吸HRCT扫描.
- 使用VGG-16提取69个定量CT (QCT) 参数和2000个深度学习 (DL) 特性.
- 在29名患者的外部队列上开发和验证后勤回归模型.
主要成果:
- 综合临床数据,QCT参数和DL特征的7-B模型实现了最高的AUC0.979 (测试) 和0.932 (外部验证).
- 仅DL特征 (3-B模型) 已表现出强大的预测能力,AUC为0.933 (测试) 和0.865 (外部验证).
- 这些模型显示了强大的可预测性,用于识别AECOPD表型.
结论:
- 从HRCT扫描中提取的深度学习特征是COPD急性恶化表型的有效预测因素.
- 将DL特征与QCT参数和临床数据相结合,可以获得优异的预测性能.
- 开发的模型显示,在治疗COPD患者的临床应用方面具有前景.
相关概念视频
COPD: Pathogenesis and Clinical Features
The primary cause for the onset of COPD is cigarette smoking and exposure to air pollution. These hazardous factors initiate a chain reaction within the lungs, resulting in chronic inflammation, damage to the airways, and a...
Chronic Obstructive Pulmonary Disease-IV: Assessement and Diagnostic Studies
Medical History
Chronic Obstructive Pulmonary Disease
Smoking is a primary risk factor for COPD, with over 80% of patients having a history of it. Patients typically experience progressive dyspnea or labored breathing, frequent coughing, and recurrent pulmonary infections. Many eventually succumb to respiratory failure, characterized by...
Chronic Obstructive Pulmonary Disease-II: Pathophysiology
Chronic Inflammation
Chronic Obstructive Pulmonary Disease-I: Introduction
COPD: Management Using Bronchodilators and Corticosteroids


