Aurelien Bustin

TL;DR: A novel 4D (3D + time) deep learning-based reconstruction network, termed 4D CINENet, for prospectively undersampled 3D Cartesian CINE imaging, which outperforms iterative reconstructions in visual image quality and contrast and finds good agreement in LV function.

TL;DR: An overview of the recent developments in the area of artificial intelligence for CMR image reconstruction is provided, focusing on approaches that exploit neural networks as implicit or explicit priors for 2D dynamic cardiac imaging and 3D whole-heart CMR imaging.

TL;DR: To develop a new high‐dimensionality undersampled patch‐based reconstruction (HD‐PROST) for highly accelerated 2D and 3D multi‐contrast MRI.

TL;DR: To enable whole‐heart 3D coronary magnetic resonance angiography (CMRA) with isotropic sub‐millimeter resolution in a clinically feasible scan time by combining respiratory motion correction with highly accelerated variable density sampling in concert with a novel 3D patch‐based undersampled reconstruction (3D‐PROST).

TL;DR: In this paper, the authors proposed a method to automatically detect the presence of motion-related artefacts in cardiac magnetic resonance (CMR) cine images, and compared two deep learning architectures to classify poor quality CMR images: 1) 3D spatio-temporal convolutional neural networks (3D-CNN), 2) Long-term Recurrent Convolutional Network (LRCN).