Meeting Banner
Abstract #0450

Deep-learning based super-resolution reconstruction for 3D isotropic coronary MR angiography in a one-minute scan

Thomas Küstner1,2, Alina Psenicny1, Camila Munoz1, Niccolo Fuin3, Aurelien Bustin4, Haikun Qi1, Radhouene Neji1,5, Karl P Kunze1,5, Reza Hajhosseiny1, Claudia Prieto1, and René M Botnar1
1School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom, 2Department of Radiology, Medical Image and Data Analysis (MIDAS), University Hospital of Tübingen, Tübingen, Germany, 3Ixico, London, United Kingdom, 4IHU LIRYC, Electrophysiology and Heart Modeling Institute, Université de Bordeaux, INSERM, Centre de recherche Cardio-Thoracuique de Bordeaux, Bordeaux, France, 5MR Research Collaborations, Siemens Healthcare Limited, Frimley, United Kingdom

3D whole‐heart coronary MR angiography (CMRA) has shown significant potential for the diagnosis of coronary artery disease. Undersampled motion corrected reconstruction approaches have enabled free-breathing isotropic 3D CMRA in ~5-10min scan time. However, spatial resolution is still limited compared to coronary CT angiography and scan time remains relatively long. In this work, we propose a deep-learning based super-resolution (SR) framework, combined with non-rigid respiratory motion compensation (SR-CMRA), to shorten the acquisition time to <1min. A 16-fold increase in spatial resolution is achieved by reconstructing a high-resolution CMRA (1.2mm3) from a low-resolution acquisition (1.2x4.8x4.8mm3, 50s scan).

This abstract and the presentation materials are available to members only; a login is required.

Join Here