CT-based intrathrombus and perithrombus radiomics for predicting complete recanalization after endovascular thrombectomy in acute ischemic stroke.
Authors
Affiliations (5)
Affiliations (5)
- Institute of Diagnostic and Interventional Radiology, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China.
- Department of Radiology, The Eighth People's Hospital of Jinan, Jinan, Shandong, China.
- Department of Radiology, Huadong Hospital, Fudan University, Shanghai, China.
- Department of Radiology, Affiliated Hospital of Nantong University, Nantong, China.
- Department of Radiology, Shanghai Fengxian Central Hospital, Shanghai, China.
Abstract
To develop and validate CT-based radiomics models incorporating intrathrombus and perithrombus features for predicting complete recanalization [modified Thrombolysis in Cerebral Infarction (mTICI)2c/3] after endovascular thrombectomy (EVT) in acute ischemic stroke (AIS), and to identify the optimal machine learning classifier. This retrospective study included 406 AIS patients with anterior circulation large-vessel occlusion from three centers (December 2018-April 2024). Patients were allocated to training (<i>n</i> = 178), internal testing (<i>n</i> = 77), and external validation (<i>n</i> = 151) cohorts. Complete recanalization was defined as mTICI 2c/3. A total of 428 radiomics features were extracted from non-contrast CT and CT angiography (CTA). Least absolute shrinkage and selection operator (LASSO) regression and eleven classifiers were employed. The combined intrathrombus-perithrombus model with logistic regression achieved area under the curve (AUC) values of 0.93 (training), 0.88 (testing), and 0.86 (validation), outperforming single-region models. Decision curve analysis confirmed superior clinical utility. The perithrombus region contributed dominantly (10 of 15 features) to the combined model. The combined CT-based radiomics model effectively predicts complete recanalization, providing an objective tool for patient selection and treatment optimization.