Automatic Translational Correction of Multi-View Coronary Angiography Based on Auto-Annotation Data Generation

Multi-view automatic translational correction (ATC) in coronary angiography (CAG) is a fundamental step for intraoperative diagnosis and downstream 3D reconstruction. However, learning-based ATC methods require large-scale annotated datasets, which are difficult to obtain due to heartbeat-induced vascular deformation and high labeling costs. Synthetic datasets have been widely adopted to supplement, but fail to provide sufficient supervision for clinical models, due to a significant gap in both style and structure. To address this, we propose a novel annotation-free framework for high-quality CAG data synthesis and robust ATC training. Our approach generates a fully labeled, high-fidelity dataset by simulating realistic dense continuous view CAG sequences without manual annotation. Furthermore, to mitigate cross-view matching errors caused by non-rigid motion, we introduce an evolutionary epipolar optimization algorithm that refines geometric consistency under large viewpoint variations. Meanwhile, theoretical analysis shows that our proposed neighboring-view error propagation strategy leads to reduced matching error compared to conventional cross-view computation. Extensive experiments on real clinical datasets demonstrate that our annotation-free approach significantly outperforms weakly supervised baselines and achieves performance in parallel with fully supervised models trained on real annotations. The method also generalizes well on multi-center datasets, highlighting its robustness and clinical potential. Code is available in Supplementary Material.