Cine Cardiac Magnetic Resonance
Cine cardiac magnetic resonance (CMR) imaging aims to rapidly and accurately assess heart function and structure. Current research heavily focuses on accelerating acquisition times through techniques like k-space undersampling and free-breathing scans, often employing deep learning models (e.g., convolutional neural networks, neural fields, and attention mechanisms) for image reconstruction and segmentation. These advancements improve patient comfort and workflow efficiency while addressing challenges like motion artifacts and race bias in AI-driven analysis, ultimately leading to more efficient and reliable cardiac assessments.
Papers
Joint image reconstruction and segmentation of real-time cardiac MRI in free-breathing using a model based on disentangled representation learning
Tobias Wech, Oliver Schad, Simon Sauer, Jonas Kleineisel, Nils Petri, Peter Nordbeck, Thorsten A. Bley, Bettina Baeßler, Bernhard Petritsch, Julius F. Heidenreich
SRE-CNN: A Spatiotemporal Rotation-Equivariant CNN for Cardiac Cine MR Imaging
Yuliang Zhu, Jing Cheng, Zhuo-Xu Cui, Jianfeng Ren, Chengbo Wang, Dong Liang