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

• URL: http://arxiv.org/abs/2603.24847v1
• Date: Wed, 25 Mar 2026 22:28:31 GMT
• Title: CORA: A Pathology Synthesis Driven Foundation Model for Coronary CT Angiography Analysis and MACE Risk Assessment
• Abstract summary: CORA is a 3D vision foundation model for comprehensive cardiovascular risk assessment.<n>We trained CORA on a large-scale cohort of 12,801 unlabeled coronary computed tomography angiography volumes.<n> CORA consistently outperformed state-of-the-art 3D vision foundation models, achieving up to a 29% performance gain.
• Score: 7.00689933116151
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• A Latent ODE Approach to Spatiotemporal Modeling of Cine Cardiac MRI [35.84205082882139]
  We present a latent dynamical model that encodes bi-ventricular anatomy and full-cycle cine motion as a continuous trajectory.<n>We studied 72,386 UK Biobank participants without baseline cardiovascular disease, including 367 incident heart failure events.
  arXiv  Detail & Related papers  (2026-06-25T07:53:45Z)
• Multi-View Stenosis Classification Leveraging Transformer-Based Multiple-Instance Learning Using Real-World Clinical Data [76.89269238957593]
  Coronary artery stenosis is a leading cause of cardiovascular disease, diagnosed by analyzing the coronary arteries from multiple angiography views.<n>We propose SegmentMIL, a transformer-based multi-view multiple-instance learning framework for patient-level stenosis classification.
  arXiv  Detail & Related papers  (2026-02-02T13:07:52Z)
• A multimodal vision foundation model for generalizable knee pathology [40.03838145472935]
  Musculoskeletal disorders represent an urgent demand for precise interpretation of medical imaging.<n>Current artificial intelligence approaches in orthopedics rely on task-specific, supervised learning paradigms.<n>We introduce OrthoFoundation, a multimodal vision foundation model optimized for musculoskeletal pathology.
  arXiv  Detail & Related papers  (2026-01-26T08:14:51Z)
• Cardiac-CLIP: A Vision-Language Foundation Model for 3D Cardiac CT Images [29.39287623923477]
  We present Cardiac-CLIP, a multi-modal foundation model designed for 3D cardiac CT images.<n>CLIP is developed through a two-stage pre-training strategy.<n>CLIP is evaluated across multiple tasks, including cardiovascular abnormality classification, information retrieval and clinical analysis.
  arXiv  Detail & Related papers  (2025-07-29T17:20:32Z)
• Depth-Sequence Transformer (DST) for Segment-Specific ICA Calcification Mapping on Non-Contrast CT [38.85617601239779]
  Conventional 3D models are forced to process downsampled volumes or isolated patches.<n>We reformulate the 3D challenge as a textbfParallel Probabilistic Landmark localization task along the 1D axial dimension.<n>We propose the textbfDepth-Sequence Transformer (DST), a framework that processes full-resolution CT volumes as sequences of 2D slices.
  arXiv  Detail & Related papers  (2025-07-10T23:12:12Z)
• Encoding of Demographic and Anatomical Information in Chest X-Ray-based Severe Left Ventricular Hypertrophy Classifiers [36.052936348670634]
  We introduce a direct classification framework that predicts severe left ventricular hypertrophy from chest X-rays.<n>Our approach achieves high AUROC and AUPRC, and employs Mutual Information Neural Estimation to quantify feature expressivity.
  arXiv  Detail & Related papers  (2025-05-31T13:30:04Z)
• Myocardial Region-guided Feature Aggregation Net for Automatic Coronary artery Segmentation and Stenosis Assessment using Coronary Computed Tomography Angiography [13.885760158090692]
  Myocardial Region-guided Feature Aggregation Net is a novel U-shaped dual-encoder architecture that integrates anatomical prior knowledge to enhance robustness in coronary artery segmentation.<n>Our framework incorporates three key innovations: (1) a Myocardial Region-guided Module that directs attention to coronary regions via bridging expansion and multi-scale feature fusion, (2) a Residual Feature Extraction Module that combines parallel spatial channel attention with residual blocks to enhance local-global feature discrimination, and (3) a Multi-scale Feature Fusion Module for adaptive aggregation of hierarchical vascular features.
  arXiv  Detail & Related papers  (2025-04-27T16:43:52Z)
• AGFA-Net: Attention-Guided and Feature-Aggregated Network for Coronary Artery Segmentation using Computed Tomography Angiography [5.583495103569884]
  We propose an attention-guided, feature-aggregated 3D deep network (AGFA-Net) for coronary artery segmentation using CCTA images. AGFA-Net leverages attention mechanisms and feature refinement modules to capture salient features and enhance segmentation accuracy. Evaluation on a dataset comprising 1,000 CCTA scans demonstrates AGFA-Net's superior performance, achieving an average Dice coefficient similarity of 86.74% and a Hausdorff distance of 0.23 mm.
  arXiv  Detail & Related papers  (2024-06-13T01:04:47Z)
• MPSeg : Multi-Phase strategy for coronary artery Segmentation [9.767759441883008]
  We present MPSeg, an innovative multi-phase strategy designed for coronary artery segmentation. Our approach specifically accommodates these structural complexities and adheres to the principles of the SYNTAX Score. Notably, our approach demonstrated exceptional effectiveness when evaluated in the Automatic Region-based Coronary Artery Disease diagnostics.
  arXiv  Detail & Related papers  (2023-11-17T03:33:09Z)
• SSASS: Semi-Supervised Approach for Stenosis Segmentation [9.767759441883008]
  The complexity of coronary artery structures combined with the inherent noise in X-ray images poses a considerable challenge to this task. We introduce a semi-supervised approach for cardiovascular stenosis segmentation. Our approach demonstrated an exceptional performance in the Automatic Region-based Coronary Artery Disease diagnostics.
  arXiv  Detail & Related papers  (2023-11-17T02:01:19Z)
• Successive Subspace Learning for Cardiac Disease Classification with Two-phase Deformation Fields from Cine MRI [36.044984400761535]
  This work proposes a lightweight successive subspace learning framework for CVD classification. It is based on an interpretable feedforward design, in conjunction with a cardiac atlas. Compared with 3D CNN-based approaches, our framework achieves superior classification performance with 140$times$ fewer parameters.
  arXiv  Detail & Related papers  (2023-01-21T15:00:59Z)
• A Global Benchmark of Algorithms for Segmenting Late Gadolinium-Enhanced Cardiac Magnetic Resonance Imaging [90.29017019187282]
  " 2018 Left Atrium Challenge" using 154 3D LGE-MRIs, currently the world's largest cardiac LGE-MRI dataset. Analyse of the submitted algorithms using technical and biological metrics was performed. Results show the top method achieved a dice score of 93.2% and a mean surface to a surface distance of 0.7 mm.
  arXiv  Detail & Related papers  (2020-04-26T08:49:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.