基于多类放射组学方法的WHO严重程度量表用于改善CT扫描对COVID-19患者的评估与疾病表征
本研究在回顾性设计中开发了AssessNet-19,一种基于多类肺病变放射组学的COVID-19严重程度分类模型,依据世界卫生组织临床进展量表进行分级。在由2个中心90例患者组成的全自动评估集中,模型F1分数为0.76±0.02,优于3位胸部放射科专家(F1=0.63±0.02)和单类病变模型(F1=0.64±0.02)。多类病变自动分割的平均Dice分数为磨玻璃影0.70、实变0.68、胸腔积液0.65、带状结构0.30。
要点
- AssessNet-19在评估集中严重程度分类F1为0.76±0.02,高于3位胸部放射科专家的0.63±0.02。
- 多类病变模型F1为0.76±0.02,优于单类病变分割模型的0.64±0.02。
- 模型与放射科医生量化病变范围高度一致,Cohen κ分别为0.94、0.92、0.95。
核心结论
- 包含4种肺病变的多类放射组学人工智能模型依据世界卫生组织临床进展量表评估疾病严重程度,比单类模型和放射科医生评估更准确地判断COVID-19患者的严重程度。
研究设计与样本
- 回顾性研究,AssessNet-19分两阶段开发;开发队列为来自3个中心的145例COVID-19阳性患者,用于训练和测试基于手动分割肺病变的严重程度预测模型;评估集为来自2个中心的90例COVID-19阳性患者,用于全自动方式评估AssessNet-19。
关键影像表现/征象
- 手动分割4种COVID-19所致组织病变以训练2D-U-Net网络进行多类分割,并从肺病变中广泛提取放射组学特征。
- 使用LASSO回归缩减特征集,训练XGBoost算法基于世界卫生组织临床进展量表对疾病严重程度进行分类。
- AssessNet-19自动多类病变分割与真实值相比,磨玻璃影平均Dice分数为0.70,实变为0.68,胸腔积液为0.65,带状结构为0.30。
诊断标准与关键数值
- 评估集中严重程度分类F1分数:AssessNet-19为0.76±0.02,3位专家胸部放射科医生为0.63±0.02,单类病变分割模型为0.64±0.02。
- 自动多类病变分割平均Dice分数:磨玻璃影0.70,实变0.68,胸腔积液0.65,带状结构0.30。
- 与放射科医生量化疾病范围的Cohen κ分别为0.94、0.92、0.95。
临床应用与阅片要点
- 模型可基于世界卫生组织临床进展量表对COVID-19患者进行严重程度分类,并自动分割磨玻璃影、实变、胸腔积液和带状结构。
- 带状结构的自动分割Dice分数为0.30,低于其他三类病变。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVES: The aim of this study was to evaluate the severity of COVID-19 patients' disease by comparing a multiclass lung lesion model to a single-class lung lesion model and radiologists' assessments in chest computed tomography scans.
MATERIALS AND METHODS: The proposed method, AssessNet-19, was developed in 2 stages in this retrospective study. Four COVID-19-induced tissue lesions were manually segmented to train a 2D-U-Net network for a multiclass segmentation task followed by extensive extraction of radiomic features from the lung lesions. LASSO regression was used to reduce the feature set, and the XGBoost algorithm was trained to classify disease severity based on the World Health Organization Clinical Progression Scale. The model was evaluated using 2 multicenter cohorts: a development cohort of 145 COVID-19-positive patients from 3 centers to train and test the severity prediction model using manually segmented lung lesions. In addition, an evaluation set of 90 COVID-19-positive patients was collected from 2 centers to evaluate AssessNet-19 in a fully automated fashion.
RESULTS: AssessNet-19 achieved an F1-score of 0.76 ± 0.02 for severity classification in the evaluation set, which was superior to the 3 expert thoracic radiologists (F1 = 0.63 ± 0.02) and the single-class lesion segmentation model (F1 = 0.64 ± 0.02). In addition, AssessNet-19 automated multiclass lesion segmentation obtained a mean Dice score of 0.70 for ground-glass opacity, 0.68 for consolidation, 0.65 for pleural effusion, and 0.30 for band-like structures compared with ground truth. Moreover, it achieved a high agreement with radiologists for quantifying disease extent with Cohen κ of 0.94, 0.92, and 0.95.
CONCLUSIONS: A novel artificial intelligence multiclass radiomics model including 4 lung lesions to assess disease severity based on the World Health Organization Clinical Progression Scale more accurately determines the severity of COVID-19 patients than a single-class model and radiologists' assessment.
引用
- Henao JAG, Depotter A, Bower DV, et al. A Multiclass Radiomics Method-Based WHO Severity Scale for Improving COVID-19 Patient Assessment and Disease Characterization From CT Scans. Invest Radiol. 2023. PMID: 37493348. doi:10.1097/RLI.0000000000001005
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。