CTSL: Codebook-based Temporal-Spatial Learning for Accurate Non-Contrast Cardiac Risk Prediction Using Cine MRIs
This provides a rapid, non-invasive solution for cardiac risk assessment, enabling timely and accessible heart disease diagnosis in clinical settings.
The paper tackled the challenge of predicting Major Adverse Cardiac Events (MACE) from Cine MRI sequences without contrast agents, introducing a self-supervised framework called CTSL that learns spatiotemporal representations from raw data and outperforms traditional contrast-dependent methods.
Accurate and contrast-free Major Adverse Cardiac Events (MACE) prediction from Cine MRI sequences remains a critical challenge. Existing methods typically necessitate supervised learning based on human-refined masks in the ventricular myocardium, which become impractical without contrast agents. We introduce a self-supervised framework, namely Codebook-based Temporal-Spatial Learning (CTSL), that learns dynamic, spatiotemporal representations from raw Cine data without requiring segmentation masks. CTSL decouples temporal and spatial features through a multi-view distillation strategy, where the teacher model processes multiple Cine views, and the student model learns from reduced-dimensional Cine-SA sequences. By leveraging codebook-based feature representations and dynamic lesion self-detection through motion cues, CTSL captures intricate temporal dependencies and motion patterns. High-confidence MACE risk predictions are achieved through our model, providing a rapid, non-invasive solution for cardiac risk assessment that outperforms traditional contrast-dependent methods, thereby enabling timely and accessible heart disease diagnosis in clinical settings.