Dynamic MR

Dynamic magnetic resonance imaging (dMRI) reconstruction aims to accelerate image acquisition and improve image quality by efficiently processing undersampled k-space data. Current research heavily utilizes deep learning, employing architectures like convolutional neural networks (CNNs), transformers (e.g., Swin Transformers), and iterative neural networks (INNs), often combined with techniques like low-rank plus sparse decomposition and tensor nuclear norm regularization to leverage spatiotemporal correlations. These advancements enable faster scan times and improved diagnostic capabilities in applications such as cardiac imaging and focused ultrasound therapy, ultimately enhancing patient care and clinical workflow.