28 Jul, 2021 (Wed)Time:
4:00 pmWebinar Link:
SpeakerMr. Zheyuan Yi
Department of Electrical and Electronic Engineering
The University of Hong Kong
Magnetic resonance imaging (MRI) is a highly versatile and widely applied imaging technique. However, data acquisition in the clinical scan is often time-consuming, which compromises the diagnostic value and economic efficiency. Although parallel imaging has been applied routinely to accelerate data acquisition, it so far requires coil calibration for image reconstruction that inevitably prolongs MRI scans. In addition, datasets generally exhibit strong correlations in routine multi-contrast or multi-slice MRI that have rarely been considered. This talk will give an overview of our developed structured low-rank reconstruction technique, with applications to highly undersampled multi-modality MRI. A joint calibrationless reconstruction framework was designed to explore data correlations in multi-contrast or multi-slice MRI and achieve higher acceleration beyond independent reconstruction. During developing this method, a novel data acquisition strategy and deep learning guided reconstruction have also been incorporated to further enhance its robustness.
Zoom Link (during COVID-19 special period):
Meeting ID: 551 190 4598
Zheyuan Yi received his B.E. degrees from the Southern University of Science and Technology, Shenzhen, China in 2017. He is currently pursuing a Ph.D. in Electrical and Electronic Engineering at the University of Hong Kong. His research interests include analytical reconstruction algorithms, data-driven and model-based deep learning methods for improving biomedical imaging quality and efficiency.
OrganizerProf. Ed. X. Wu
Most seminars are open to the general public, free of charge, unless otherwise stated. Registration is not required. Arrangement for car parking facilities on campus please contact us for details.
For enquiries, please contact:
Department of Electrical and Electronic Engineering,
Room 601, Chow Yei Ching Building,
Pokfulam Road, Hong Kong
Tel: (852) 3917 7093