Dual-energy CT clot and peri-clot radiomics for predicting complete reperfusion and clinical outcome following endovascular therapy in acute ischemic stroke.
Authors
Affiliations (7)
Affiliations (7)
- Department of Diagnostic and Interventional Radiology, Shanghai Sixth People's Hospital, Shanghai, China.
- Faculty of Medical Imaging Technology, College of Health Science and Technology, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
- Department of Radiology, Renji Hospital, Affiliated with Shanghai Jiao Tong University, Shanghai, China.
- School of Computer Science and Technology, Donghua University, Shanghai, China.
- Shenyang University of Technology, Shenyang, China.
- Department of Diagnostic and Interventional Radiology, Shanghai Sixth People's Hospital, Shanghai, China. [email protected].
- Department of Radiology, Affiliated Hospital of Nantong University, Nantong, China. [email protected].
Abstract
Complete reperfusion is the optimal technical goal of endovascular therapy (EVT) and is closely linked to favorable outcomes in acute ischemic stroke (AIS). This study developed and validated clot- and peri-clot-based radiomics models on pre-interventional dual-energy CT angiography (DE-CTA) to predict complete reperfusion and clinical outcome after EVT. A total of 371 patients from three centers were retrospectively enrolled and assigned to training (nā=ā154), test (nā=ā66), and validation (nā=ā151) cohorts. Radiomics features from clot and peri-clot regions were extracted, and three machine learning models-clot-based, peri-clot-based, and combined-were constructed. Model performance for predicting complete reperfusion and 90-day outcome was assessed using AUC. Small, optimized feature subsets were selected for each model (11/11, 17/10, and 13/10 features for clot-based, peri-clot-based, and combined models for reperfusion and outcome prediction, respectively). For complete reperfusion, the peri-clot model showed the best performance with AUCs of 0.885 (95% CI: 0.834-0.937), 0.860 (95% CI: 0.771-0.948), and 0.847 (95% CI: 0.778-0.916) in the training, test, and validation cohorts, outperforming the clot-based (0.809, 0.759, 0.719) and combined models (0.867, 0.840, 0.820). A similar advantage was observed for outcome prediction, where the peri-clot model achieved the highest AUCs (0.854, 0.817, 0.850), exceeding the combined (0.839, 0.763, 0.804) and clot-based models (0.826, 0.709, 0.734). DE-CTA peri-clot radiomics provides superior prediction of both complete reperfusion and functional outcome after EVT, underscoring the clinical relevance of peri-clot microenvironment imaging and its potential to enhance pre-EVT patient selection and individualized prognostic evaluation. The trial registration number (Chinese Clinical Trial Registry, ChiCTR2400092800) and date of registration (2024.11.22) were retrospectively registered. Peri-clot dual-energy computed tomography angiography radiomics outperformed clot-based models in multicenter external validation for predicting complete reperfusion and good 90-day functional outcome after endovascular therapy for acute ischemic stroke, supporting improved preprocedural risk stratification and patient selection. Complete reperfusion and functional recovery after endovascular thrombectomy remain hard to predict using thrombus features alone. Peri-clot radiomics on dual-energy computed tomography angiography achieved an external validation performance of 0.847 for complete reperfusion prediction. The same peri-clot model predicted 90-day functional outcome with 0.850 performance, supporting microenvironment-informed risk stratification. Peri-clot signatures consistently outperformed clot-only and combined models across multicenter cohorts, supporting robustness.