The research in our lab focuses on the development of new MRI acquisition technologies that can dramatically improve the speed, sensitivity and specificity of brain imaging. Our research explores approaches in designing tailored data acquisition & reconstruction algorithms using signal processing/optimization/ML methods, to take advantage of the underlying MR Physics and emerging hardware.
The goal is to create new imaging strategies that can help address important clinical & neuroscientific questions. The technologies that we have developed have enabled highly detailed brain data at unprecedented temporal and spatial resolutions, that have helped extract a wealth of quantitative information about brain structure and physiology. Some of these technologies have now been successfully translated as FDA-approved product, that are now being used daily in the clinic on the Siemens, GE and Phillips MRI scanners worldwide.
- – NeuroImage
High-fidelity mesoscale in-vivo diffusion MRI through gSlider-BUDA and circular EPI with S-LORAKS reconstruction
Purpose: To develop a high-fidelity diffusion MRI acquisition and reconstruction framework with reduced echo-train-length for less T2* image blurring compared to typical highly accelerated echo-planar imaging (EPI) acquisitions at sub-millimeter isotropic resolution.
- – PubMed Central (PMC)
Deep Learning Initialized Compressed Sensing (Deli-CS) in Volumetric Spatio-Temporal Subspace Reconstruction
Spatio-temporal MRI methods enable whole-brain multi-parametric mapping at ultra-fast acquisition times through efficient k-space encoding, but can have very long reconstruction times, which limit their integration into clinical practice.
- – UCSF Radiology
Congrats Congyu Liao on new position at UCSF!
- – The Setsompop Laboratory
Congrats Congyu Liao on R01 Award!
- – The Setsompop Laboratory
Congrats Nan Wang on K99 Award!