Jiang Jingxuan, Wei Jianyong, Zhu Yueqi, Wei Liming, Wei Xiaoer, Tian Hao, Zhang Lei, Wang Tianle, Cheng Yue, Zhao Qianqian, Sun Zheng, Du Haiyan, Huang Yu, Liu Hui, Li Yuehua
Institute of Diagnostic and Interventional Radiology, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, No. 600 Yishan Road, Shanghai, 200233, China.
Department of Radiology, Affiliated Hospital of Nantong University, Nantong, 226001, China.
Eur Radiol. 2023 Feb;33(2):970-980. doi: 10.1007/s00330-022-09116-4. Epub 2022 Sep 6.
To develop a clot-based radiomics model using CT imaging radiomic features and machine learning to identify cardioembolic (CE) stroke before mechanical thrombectomy (MTB) in patients with acute ischemic stroke (AIS).
This retrospective four-center study consecutively included 403 patients with AIS who sequentially underwent CT and MTB between April 2016 and July 2021. These were grouped into training, testing, and external validation cohorts. Thrombus-extracted radiomic features and basic information were gathered to construct a machine learning model to predict CE stroke. The radiological characteristics and basic information were used to build a routine radiological model. A combined radiomics and radiological features model was also developed. The performances of all models were evaluated and compared in the validation cohort. A histological analysis helped further assess the proposed model in all patients.
The radiomics model yielded an area under the curve (AUC) of 0.838 (95% confidence interval [CI], 0.771-0.891) for predicting CE stroke in the validation cohort, significantly higher than the radiological model (AUC, 0.713; 95% CI, 0.636-0.781; p = 0.007) but similar to the combined model (AUC, 0.855; 95% CI, 0.791-0.906; p = 0.14). The thrombus radiomic features achieved stronger correlations with red blood cells (|r|, 0.74 vs. 0.32) and fibrin and platelet (|r|, 0.68 vs. 0.18) than radiological characteristics.
The proposed CT-based radiomics model could reliably predict CE stroke in AIS, performing better than the routine radiological method.
• Admission CT imaging could offer valuable information to identify the acute ischemic stroke source by radiomics analysis. • The proposed CT imaging-based radiomics model yielded a higher area under the curve (0.838) than the routine radiological method (0.713; p = 0.007). • Several radiomic features showed significantly stronger correlations with two main thrombus constituents (red blood cells, |r|, 0.74; fibrin and platelet, |r|, 0.68) than routine radiological characteristics.
利用CT成像的放射组学特征和机器学习方法，开发一种基于血栓的放射组学模型，以在急性缺血性卒中（AIS）患者进行机械取栓术（MTB）前识别心源性栓塞（CE）性卒中。
这项回顾性四中心研究连续纳入了2016年4月至2021年7月间依次接受CT检查和MTB的403例AIS患者。这些患者被分为训练、测试和外部验证队列。收集血栓提取的放射组学特征和基本信息，构建用于预测CE性卒中的机器学习模型。利用放射学特征和基本信息构建常规放射学模型。还开发了一个放射组学与放射学特征相结合的模型。在验证队列中评估并比较所有模型的性能。组织学分析有助于在所有患者中进一步评估所提出的模型。
在验证队列中，放射组学模型预测CE性卒中的曲线下面积（AUC）为0.838（95%置信区间[CI]，0.771 - 0.891），显著高于放射学模型（AUC，0.713；95%CI，0.636 - 0.781；p = 0.007），但与联合模型相似（AUC，0.855；95%CI，0.791 - 0.906；p = 0.14）。与放射学特征相比，血栓的放射组学特征与红细胞（|r|，0.74对0.32）以及纤维蛋白和血小板（|r|，0.68对0.18）的相关性更强。
所提出的基于CT的放射组学模型能够可靠地预测AIS中的CE性卒中，表现优于常规放射学方法。
• 入院时的CT成像可通过放射组学分析提供有价值的信息，以识别急性缺血性卒中的来源。• 所提出的基于CT成像的放射组学模型的曲线下面积（0.838）高于常规放射学方法（0.713；p = 0.007）。• 与常规放射学特征相比，几个放射组学特征与血栓的两种主要成分（红细胞，|r|，0.74；纤维蛋白和血小板，|r|，0.68）的相关性显著更强。
