04/01/2022 to 12/31/2024

Contact PI/Project Leader: LIU, FANG

This project will develop a novel deep learning reconstruction technique for multi-component relaxometry. The proposed reconstruction technique can offer a unique opportunity to explore the acceleration of multi-component relaxation mapping by leveraging the latest deep learning techniques, resulting in an accurate, efficient, and reliable model that is widely generalizable to different relaxation types in many body regions. Successful completion of the project will provide a clinically applicable multi-component relaxometry technique that can help better study, understand and stage diseases such as osteoarthritis and multiple sclerosis from the tissue microstructural and biochemical level.

07/01/2021 to 03/31/2025

Contact PI/Project Leader: FENG, LI (ICAHN SCHOOL OF MEDICINE AT MOUNT SINAI)

MGH Consortium PI: LIU, FANG

The objective of this application is to develop and evaluate a rapid motion-robust and easy-to-use dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) framework for liver perfusion quantification. This new imaging framework is expected to promote the utilization, efficacy and clinical translation of liver perfusion MRI for improved management of hepatocellular carcinoma (HCC) and other diseases of high clinical impact.

09/03/2021 to 09/02/2025

Contact PI/Project Leader: FENG, LI (ICAHN SCHOOL OF MEDICINE AT MOUNT SINAI)

MGH Consortium PI: LIU, FANG

The objective of this application is to develop novel rapid free-breathing four-dimensional (4D=3D+time) lung MRI techniques that will enable non-invasive radiation-free evaluation of lung anatomy and pulmonary function in the longitudinal follow-ups of post-COVID-19 patients. This novel imaging framework could provide a unique opportunity to augment post-COVID care, particularly for identifying COVID-19-induced lung abnormality in a timely manner and for studying the longitudinal changes of lung anatomy and global/regional pulmonary function.

06/01/2022 to 05/31/2027

Contact PI/Project Leader: LIU, FANG

This project will develop, optimize and evaluate a rapid 5-minute knee MRI protocol consisting of all clinical sequences and additional T2 mapping sequences, enabling imaging of the whole knee for both morphological and quantitative assessment of joint pathology. The proposed technique explores the acceleration of knee MRI by leveraging the latest deep learning technology combined with novel image acquisition and automatic processing. Given the increasing prevalence of knee osteoarthritis and the overall cumulative knee injuries, our novel imaging methods would offer a unique opportunity to improve joint health care, reduce healthcare costs, and benefit a large population that suffers knee pain and joint discomfort in the United States.

07/15/2022 to 05/31/2027

Contact PI/Project Leader: LIU, FANG

This proposal will develop a rapid multi-relaxation imaging technique that can provide simultaneous three-dimensional T1, T2, and T1ρ relaxation mapping for quantifying tissue composition and ultra-structure using magnetic resonance imaging. The imaging technique incorporates a novel multi-relaxation mapping sequence using 3D golden-angle rapid acquisition and a novel physics-informed deep learning reconstruction and will be evaluated in a knee disease model. Our novel proposal would provide a new rapid imaging approach to non-invasively monitor disease-related and treatment-related changes in tissue composition and ultra-structure through multi-relaxation assessment and will have broad clinical applications for various diseases.

09/21/2023 to 08/31/2024

Contact PI/Project Leader: LIU, FANG

This proposal will develop a simultaneous multi-component T2 relaxation and cross-relaxation imaging technique that can provide sensitive and specific imaging biomarkers to assess cartilage proteoglycan and collagen content and their ultra-structures in a unified imaging framework. The imaging technique will be optimized using rigorous statistical methods and accelerated through a novel deep learning method that leverages self-supervised learning and MR physics-informed tissue modeling. Successful completion of the proposal will provide the osteoarthritis research community with a new set of MR biomarkers to non-invasively monitor disease-related and treatment-related changes in tissue composition and ultra-structure in human subjects.