CARDINAL Predicts Cardiovascular Risk From Non-contrast Cardiac CT
The developed CARDINAL (Cardiovascular Assessment via Representation learning from Deep Imaging with Nested Anatomical Latent embeddings), a clinically grounded framework that learns compact representations from routine non-contrast cardiac CT for major adverse cardiovascular event (MACE) prediction, suggests that non-contrast cardiac CT contains prognostic information beyond conventional risk equations, CAC scoring, and engineered imaging biomarkers.
Roy M. Gabriel, Nattakorn Kittisut, Jamshid Hassanpour et al.
· 0 citations