0450

View Abstract / View Presentation

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

Thomas Küstner^1,2, Alina Psenicny¹, Camila Munoz¹, Niccolo Fuin³, Aurelien Bustin⁴, Haikun Qi¹, Radhouene Neji^1,5, Karl P Kunze^1,5, 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

The proposed deep learning-based super-resolution reconstructs a high-resolution image (1.2mm³) from a low-resolution input (1.2x4.8x4.8mm³) enabling coronary MR angiography acquisitions in a one-minute scan.

Fig. 1: Proposed generative adversarial super-resolution (SR) framework with cascaded Enhanced Deep Residual Network for SR (EDSR) generator, trainable discriminator and perceptual loss network. Non-rigid motion-compensated CMRA data is acquired to form the low-resolution (1.2x3.6x3.6mm³ or 1.2x4.8x4.8mm³; superior-inferior x left-right x anterior-posterior) input image/patch which is reconstructed to the high-resolution output (0.9mm³ or 1.2mm³).

Fig. 2 [animated]: Prospective SR reconstruction: Coronal and coronary reformat of low-resolution acquisition (1.2x4.8x4.8mm³) acquired in ~50s, high-resolution acquisition (1.2mm³) acquired in ~7min, bicubic interpolation (1.2mm³), and proposed super-resolution reconstruction (1.2mm³) in a patient with suspected CAD for a prospective acquired low-resolution scan of ~50s scan time (prospective cohort).