Wang Jia, Xiong Xing, Zou Jinzhao, Fu Jianxiong, Yin Yili, Ye Jing
Department of Radiology, Northern Jiangsu People's Hospital, 225001, Yangzhou, China.
Department of Radiology, The First Affiliated Hospital of Soochow University, 215006, Suzhou, Jiangsu, China.
Clin Neuroradiol. 2023 Mar;33(1):199-209. doi: 10.1007/s00062-022-01201-x. Epub 2022 Aug 9.
The aim is to explore the potential value of CT-based radiomics in predicting perihematomal edema (PHE) volumes after acute intracerebral hemorrhage (ICH) from admission to 24 h.
A total of 231 patients newly diagnosed with acute ICH at two institutes were analyzed retrospectively. The patients were randomly divided into training (N = 117) and internal validation cohort (N = 45) from institute 1 with a ratio of 7:3. According to radiomics features extracted from baseline CT, the radiomics signatures were constructed. Multiple logistic regression analysis was used for clinical radiological factors and then the nomogram model was generated to predict the extent of PHE according to the optimal radiomics signature and the clinical radiological factors. The receiver operating characteristic (ROC) curve was used to evaluate the discrimination performance. The calibration curve and Hosmer-Lemeshow test were used to evaluate the consistency between the predicted and actual probability. The support vector regression (SVR) model was constructed to predict the overall value of follow-up PHE. The performance of the models was evaluated on the internal and independent validation cohorts.
The perihematoma 5 mm radiomics signature (AUC: 0.875) showed good ability to discriminate the small relative PHE(rPHE) from large rPHE volumes, comparing to intrahematoma radiomics signature (AUC: 0.711) or perihematoma 10 mm radiomics signature (AUC: 0.692) on the training cohort. The AUC of the combined nomogram model was 0.922 for the training cohort, 0.945 and 0.902 for the internal and independent validation cohorts, respectively. The calibration curves and Hosmer-Lemeshow test of the nomogram model suggested that the predictive performance and actual outcome were in favorable agreement. The SVR model also predicted the overall value of follow-up rPHE (root mean squared error, 0.60 and 0.45; Pearson correlation coefficient, 0.73 and 0.68; P < 0.001).
Among patients with acute ICH, the established nomogram and SVR model with favorable performance can offer a noninvasive tool for the prediction of PHE after ICH.
探讨基于CT的影像组学在预测急性脑出血（ICH）患者入院至24小时后血肿周围水肿（PHE）体积方面的潜在价值。
回顾性分析两家机构新诊断为急性ICH的231例患者。将机构1的患者按7:3的比例随机分为训练组（N = 117）和内部验证队列（N = 45）。根据从基线CT中提取的影像组学特征构建影像组学特征标签。采用多元逻辑回归分析临床放射学因素，然后根据最佳影像组学特征标签和临床放射学因素生成列线图模型，以预测PHE的范围。采用受试者操作特征（ROC）曲线评估鉴别性能。采用校准曲线和Hosmer-Lemeshow检验评估预测概率与实际概率之间的一致性。构建支持向量回归（SVR）模型以预测随访PHE的总体值。在内部和独立验证队列中评估模型的性能。
在训练队列中，血肿周围5mm影像组学特征标签（AUC：0.875）在区分小相对PHE（rPHE）和大rPHE体积方面表现出良好的能力，优于血肿内影像组学特征标签（AUC：0.711）或血肿周围10mm影像组学特征标签（AUC：0.692）。训练队列中联合列线图模型的AUC为0.922，内部验证队列和独立验证队列的AUC分别为0.945和0.902。列线图模型的校准曲线和Hosmer-Lemeshow检验表明预测性能与实际结果具有良好的一致性。SVR模型也预测出随访rPHE的总体值（均方根误差分别为0.60和0.45；Pearson相关系数分别为0.73和0.68；P < 0.001）。
在急性ICH患者中，性能良好的列线图和SVR模型可为预测ICH后PHE提供一种非侵入性工具。
