Cardiac Magnetic Resonance
Cardiac magnetic resonance (CMR) imaging is a gold-standard technique for non-invasive cardiac assessment, aiming to provide comprehensive information on heart structure and function. Current research heavily utilizes deep learning, employing architectures like U-Nets, Transformers, and diffusion models, to improve image reconstruction from undersampled data, automate segmentation of cardiac structures (especially the challenging right ventricle), and enable efficient biomarker quantification. These advancements enhance diagnostic accuracy, streamline clinical workflows, and facilitate personalized medicine by enabling more precise and efficient analysis of cardiac data, including the development of cardiac digital twins.
Papers
Two-Phase Segmentation Approach for Accurate Left Ventricle Segmentation in Cardiac MRI using Machine Learning
Maria Tamoor, Abbas Raza Ali, Philemon Philip, Ruqqayia Adil, Rabia Shahid, Asma Naseer
Classification, Regression and Segmentation directly from k-Space in Cardiac MRI
Ruochen Li, Jiazhen Pan, Youxiang Zhu, Juncheng Ni, Daniel Rueckert