Free-breathing Cardiovascular MRI Using a Plug-and-Play Method with Learned Denoiser
This work addresses the challenge of accelerating real-time cardiac MRI for clinical use, representing an incremental improvement by combining existing plug-and-play and deep learning techniques.
The paper tackled the problem of long acquisition times in cardiac MRI by proposing a plug-and-play method with a learned denoiser for reconstructing undersampled data, achieving over one dB advantage over compressed sensing for breath-held datasets and higher qualitative scores for free-breathing datasets.
Cardiac magnetic resonance imaging (CMR) is a noninvasive imaging modality that provides a comprehensive evaluation of the cardiovascular system. The clinical utility of CMR is hampered by long acquisition times, however. In this work, we propose and validate a plug-and-play (PnP) method for CMR reconstruction from undersampled multi-coil data. To fully exploit the rich image structure inherent in CMR, we pair the PnP framework with a deep learning (DL)-based denoiser that is trained using spatiotemporal patches from high-quality, breath-held cardiac cine images. The resulting "PnP-DL" method iterates over data consistency and denoising subroutines. We compare the reconstruction performance of PnP-DL to that of compressed sensing (CS) using eight breath-held and ten real-time (RT) free-breathing cardiac cine datasets. We find that, for breath-held datasets, PnP-DL offers more than one dB advantage over commonly used CS methods. For RT free-breathing datasets, where ground truth is not available, PnP-DL receives higher scores in qualitative evaluation. The results highlight the potential of PnP-DL to accelerate RT CMR.