Dynamic Cardiac Late Gadolinium Enhancement Imaging Using Deep Equilibrium Models

Motivation: Long scan time of phase sensitive inversion recovery (PSIR) for cardiac late gadolinium enhancement imaging significantly hinders the widespread applications of time-sensitive clinical scenarios. Goal(s): This study aims to accelerate PSIR acquisition and enhance reconstruction performance using deep equilibrium models. Approach: To reduce cardiac motion-induced blurring, segmented undersampled PSIR k-space data was divided into multiple shots instead of a single dataset. Using a deep learning approach with deep equilibrium models, dynamic inversion recovery and proton density reference images were reconstructed from each shot's highly undersampled k-space data. Results: This approach enables accurate dynamic PSIR image reconstruction with acceleration rates up to 12.5. Impact: The proposed method could greatly reduce the scan time of PSIR data acquisition and achieve high quality images, therefore has a broad spectrum of potential clinical applications.