Beijing Anzhen Hospital, Capital Medical University / Sun Yat-Sen University
Model weights not public. Contact creators for more information.
End-to-end deep learning framework that predicts the procedural outcome of percutaneous coronary intervention (PCI) for chronic total occlusion (CTO) lesions directly from preprocedural coronary CT angiography, aiming to replace slower manual scoring systems (J-CTO, CT-RECTOR, KCCT). The pipeline first segments the coronary artery tree (Patch-UCTNet), detects candidate CTO lesions along the delineated vessel, extracts pathological lesion features with a Swin Transformer, and classifies two outcomes: successful guidewire crossing within 30 minutes and overall PCI success. In the original study, the model completed reconstruction and analysis 85% faster than manual scores (73.7s vs. 418-467s) and was more accurate than the manual CT-RECTOR, KCCT, and J-CTO_CCTA_ scores, reaching an AUROC of 0.97 on the internal test set and 0.96 on an independent external validation cohort (186 patients, 189 CTO lesions).
Architecture
Hybrid
Multi-stage pipeline: Patch-UCTNet (patch-based U-Net) for coronary artery delineation, rule-based CTO lesion detection along the segmented vessel, a Swin Transformer for CTO pathological feature extraction, and a classification head predicting guidewire-crossing and PCI success
Framework
PyTorch
Added to catalog
2026-08-12
Beijing Anzhen Hospital CTO Coronary CTA Cohort
Patients with angiographically confirmed coronary chronic total occlusion (CTO) undergoing preprocedural coronary CT angiography prior to attempted percutaneous coronary intervention (PCI), plus an independent external validation cohort.
Two binary predictions per chronic total occlusion (CTO) lesion from preprocedural coronary CTA: successful guidewire crossing within 30 minutes, and overall percutaneous coronary intervention (PCI) procedural success