20200108 Guozhi Dong Quantitative MRI: From fingerprinting to learning-informed integrated physics-based models

报告题目： Quantitative MRI: From fingerprinting to learning-informed integrated physics-based models

报告人：Guozhi Dong （Humboldt University of Berlin & Weierstrass Institute for Applied Analysis and Stochastics）

时间：2020年1月8日（周三）下午16:00-17:00

地 点：数学院425

摘要: In this talk, we introduce a novel method for quantitative MRI which asks for precise estimation of physical parameters, e.g., T1, T2 relaxation times and so on. The proposed approach uses data-driven
models and respects the physical law characterized by Bloch equations as the recently developed method magnetic resonance fingerprinting (MRF). However, in comparison with MRF, the new method does not rely on the discretization size in the dictionary, and shows much higher accuracy for the estimated parameters.

报告人介绍：Guozhi Dong，主要从事反问题正则化理论、核磁共振成像方面的研究，相关成果发表在《Inverse Probl. Imaging 》、《 SIAM J. Imaging Sci.》