Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva, 1211, Switzerland.
Imaging Department, Qom University of Medical Sciences, Qum, Iran.
Comput Biol Med. 2022 Jun;145:105467. doi: 10.1016/j.compbiomed.2022.105467. Epub 2022 Mar 29.
We aimed to analyze the prognostic power of CT-based radiomics models using data of 14,339 COVID-19 patients.
Whole lung segmentations were performed automatically using a deep learning-based model to extract 107 intensity and texture radiomics features. We used four feature selection algorithms and seven classifiers. We evaluated the models using ten different splitting and cross-validation strategies, including non-harmonized and ComBat-harmonized datasets. The sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were reported.
In the test dataset (4,301) consisting of CT and/or RT-PCR positive cases, AUC, sensitivity, and specificity of 0.83 ± 0.01 (CI95%: 0.81-0.85), 0.81, and 0.72, respectively, were obtained by ANOVA feature selector + Random Forest (RF) classifier. Similar results were achieved in RT-PCR-only positive test sets (3,644). In ComBat harmonized dataset, Relief feature selector + RF classifier resulted in the highest performance of AUC, reaching 0.83 ± 0.01 (CI95%: 0.81-0.85), with a sensitivity and specificity of 0.77 and 0.74, respectively. ComBat harmonization did not depict statistically significant improvement compared to a non-harmonized dataset. In leave-one-center-out, the combination of ANOVA feature selector and RF classifier resulted in the highest performance.
Lung CT radiomics features can be used for robust prognostic modeling of COVID-19. The predictive power of the proposed CT radiomics model is more reliable when using a large multicentric heterogeneous dataset, and may be used prospectively in clinical setting to manage COVID-19 patients.
我们旨在使用来自 14339 例 COVID-19 患者的数据，分析基于 CT 的放射组学模型的预后能力。
使用基于深度学习的模型自动进行全肺分段，以提取 107 个强度和纹理放射组学特征。我们使用了四种特征选择算法和七种分类器。我们使用十种不同的分割和交叉验证策略（包括非协调和 ComBat 协调数据集）评估模型。报告了灵敏度、特异性和接收器操作特征曲线（AUC）下的面积。
在包含 CT 和/或 RT-PCR 阳性病例的测试数据集（4301 例）中，通过方差分析特征选择器+随机森林（RF）分类器，AUC、灵敏度和特异性分别为 0.83±0.01（95%CI：0.81-0.85）、0.81 和 0.72。在仅 RT-PCR 阳性的测试集中也得到了类似的结果（3644 例）。在 ComBat 协调数据集中，Relief 特征选择器+RF 分类器的 AUC 性能最高，达到 0.83±0.01（95%CI：0.81-0.85），灵敏度和特异性分别为 0.77 和 0.74。与非协调数据集相比，ComBat 协调并未显示出统计学上的显著改善。在留一中心外，使用方差分析特征选择器和 RF 分类器的组合可获得最高性能。
肺部 CT 放射组学特征可用于稳健预测 COVID-19 的预后。当使用大型多中心异质数据集时，所提出的 CT 放射组学模型的预测能力更可靠，并且可能在临床环境中前瞻性地用于管理 COVID-19 患者。
