CORA: A Pathology Synthesis Driven Foundation Model for Coronary CT Angiography Analysis and MACE Risk Assessment

TL;DR

CORA is a novel 3D vision foundation model trained on unlabeled coronary CT angiography data, using pathology synthesis to improve detection of coronary abnormalities and MACE risk prediction, outperforming existing models.

Contribution

The paper introduces CORA, a pathology synthesis driven self-supervised framework for CCTA analysis, enabling improved detection of coronary disease features and risk assessment.

Findings

CORA outperforms state-of-the-art models by up to 29% in diagnostic tasks.

CORA achieves significant improvements in plaque characterization, stenosis detection, and artery segmentation.

Coupling with a language model enhances 30-day MACE risk stratification.

Abstract

Coronary artery disease, the leading cause of cardiovascular mortality worldwide, can be assessed non-invasively by coronary computed tomography angiography (CCTA). Despite progress in automated CCTA analysis using deep learning, clinical translation is constrained by the scarcity of expert-annotated datasets. Furthermore, widely adopted label-free pretraining strategies, such as masked image modeling, are intrinsically biased toward global anatomical statistics, frequently failing to capture the spatially localized pathological features of coronary plaques. Here, we introduce CORA, a 3D vision foundation model for comprehensive cardiovascular risk assessment. CORA learns directly from volumetric CCTA via a pathology-centric, synthesis-driven self-supervised framework. By utilizing an anatomy-guided lesion synthesis engine, the model is explicitly trained to detect simulated vascular abnormalities, biasing representation learning toward clinically relevant disease features rather than dominant background anatomy. We trained CORA on a large-scale cohort of 12,801 unlabeled CCTA volumes and comprehensively evaluated the model across multi-center datasets from nine independent hospitals. Across diagnostic and anatomical tasks, including plaque characterization, stenosis detection, and coronary artery segmentation, CORA consistently outperformed the state-of-the-art 3D vision foundation models, achieving up to a 29\% performance gain. Crucially, by coupling the imaging encoder with a large language model, we extended CORA into a multimodal framework that significantly improved 30-day major adverse cardiac event (MACE) risk stratification. Our results establish CORA as a scalable and extensible foundation for unified anatomical assessment and cardiovascular risk prediction.