基于视觉和人工智能的COVID-19肺炎评估:已建立的半量化胸部CT评分系统的可行性和可重现性
Eugen Neumann1, Anna Movlilishvili1, Simon T Scherfeld1
1Department of Diagnostic and Interventional Radiology, Klinikum Lippe, Medical School and University Medical Center OWL, Bielefeld University, 32756 Detmold, Germany.
评估COVID-19肺部影响的Pan-score系统显示了人类读者与人工智能之间的高度一致. 尽管有些主观性,但它提供了一种可靠的方法来评估肺部疾病的严重程度.
科学领域:
- 放射学
- 人工智能
- 传染性疾病
背景情况:
- 评估COVID-19肺部感染的严重程度对于患者管理至关重要.
- 泛评分是一种半定量系统,用于评估胸部CT的肺部疾病.
- 视觉和基于人工智能的评分需求评估的评审者间协议.
研究的目的:
- 为了确定Pan-score系统的评价者之间的协议.
- 将人类读者的视觉评估与基于人工智能的评估进行比较.
- 评估COVID-19患者的泛评分的可靠性.
主要方法:
- 对569名COVID-19患者进行胸部CT扫描后期研究.
- 由放射科医生,助理医生,医学学生和人工智能软件分配的泛评分.
- 权衡的科恩卡帕 (κ) 计算为评价者之间的一致性.
主要成果:
- 在人类读者 (κ = 0.710.86) 和人类与人工智能 (κ = 0.83) 之间观察到高互评分一致性.
- 基于人工智能的分数明显高于人类评估的分数 (p < 0. 001).
- 图像切片厚度没有影响共识;对比介质的使用增加了分数.
结论:
- 泛评分是用户友好的,但可能是主观的,导致潜在的不准确.
- 较高的互评分协议支持COVID-19肺部参与的泛评分的可靠性.
- 人类读者和人工智能都表现出Pan-score系统的一致性.
更多相关视频
02:09Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
Published on: April 12, 2024
03:38Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models
Published on: June 20, 2025
相关概念视频
Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
Pneumonia III: Complications and Assessment
Chronic Obstructive Pulmonary Disease-IV: Assessement and Diagnostic Studies
Medical History
Imaging Studies for Cardiovascular System V: CT
Pulmonary Embolism II: Diagnostic Studies and Interprofessional Care
Radiological Investigation III: Pulmonary Angiogram and PET Scan
Pulmonary Angiogram
A Pulmonary Angiogram is an invasive procedure involving injecting a contrast medium through a catheter threaded into the pulmonary artery or the right side of the heart to visualize the pulmonary vasculature. Computed Tomography (CT) scans have mainly replaced this...
