时间：2025年4月16日（星期三）16:30-18:00
地点：E4-233
主讲人: 香港中文大学 曾铁勇
主讲人简介：曾铁勇博士，教授，香港中文大学数学人工智能中心主任，科技部战略性科技创新合作重点专项首席科学家，Pattern Recognition 编委会成员，2021年香港数学会青年学者奖获得者。2000年本科毕业于北京大学，2004年获得巴黎理工学院硕士学位，2007年获得巴黎第十三大学博士学位。2007-2008, 法国巴黎卡尚高等师范学校博士后。2008-2018年，香港浸会大学数学系助理教授、副教授。2018年入职香港中文大学数学系，任副教授、教授。主要研究领域包括数据科学，优化理论，图像处理，反问题等。在SIAM Journal on Imaging Sciences, SIAM Journal on Scientific Computing, International Journal of Computer Vision, Journal of Scientific Computing，IEEE PAMI, IEEE TNNLS, IEEE Transactions on Image Processing，Pattern Recognition，Journal of Mathematical Imaging and Vision等杂志和会议发表两百篇学术论文。
讲座主题：Fast and Reliable Score-Based Generative Model for Parallel MRI
讲座摘要: The score-based generative model (SGM) can gen erate high-quality samples, which have been successfully adopted for magnetic resonance imaging (MRI) reconstruction. However, the recent SGMs may take thousands of steps to generate a high quality image. Besides, SGMs neglect to exploit the redundancy in k space. To overcome the above two drawbacks, in this talk, we propose a fast and reliable SGM (FRSGM). First, we propose deep ensemble denoisers (DEDs) consisting of SGM and the deep denoiser, which are used to solve the proximal problem of the implicit regularization term. Second, we propose a spatially adaptive self-consistency (SASC) term as the regularization term of the k-space data. We use the alternating direction method of multipliers (ADMM) algorithm to solve the minimization model of compressed sensing (CS)-MRI incorporating the image prior term and the SASC term, which is significantly faster than the related works based on SGM. Meanwhile, we can prove that the iterating sequence of the proposed algorithm has a unique fixed point. In addition, the DED and the SASC term can significantly improve the generalization ability of the algorithm. The features mentioned above make our algorithm reliable, including the f ixed-point convergence guarantee, the exploitation of the k space, and the powerful generalization ability.
