研究生通知
研究生通知
当前位置: 网站首页  >  研究生通知  >  正文

讲座预告|一种复拟牛顿近端法在压缩感知核磁共振成像中的应用

来源:51白菜网 作者:审核人:发布时间:2023-04-07点击数:

讲座题目:A Complex Quasi-Newton Proximal Method for Image Reconstruction in Compressive Sensing MRI

一种复拟牛顿近端法在压缩感知核磁共振成像中的应用

讲座时间:2023年4月11日(周二)9:45

讲座地点:9号楼404会议室

讲座摘要:

Modern Compressive Sensing (CS) MRI scanners use multi-coil to acquire the k-space data that dramatically reducing the time of patients stay in the scan room. However, such a system brings new difficulties of the reconstruction algorithms that developing an efficient algorithm to reconstruct the image is highly demand. It is known that high-order methods converge faster than first-order methods. But it is hard to use high-order methods for real applications because high-order methods require much higher computation than first-order methods at each iteration. In this talk, we will discuss a specifical high-order method and see how we can reduce the computation at each iteration. Our numerical experiments in CS MRI demonstrate the efficiency of our method.

At the end of the talk, we will discuss some open problems and future directions.

现代压缩感知核磁共振成像系统多使用多线圈来获得k-space数据。这大大的降低了病人的扫描时间。但这样的系统需要一个更高效的图像重构算法。相比于一阶算法,高阶算法收敛更快。但高阶算法在实际应用中困难重重。因为相比于一阶算法,高阶算法的每一步迭代需要更多的计算量,这往往使得其没有实际应用背景。今天,我们讨论一种特殊的高阶算法并且提出一种高效的方法去降低其每一步的运算量。基于压缩感知核磁共振成像的重构实验表明,相比于一阶方法,我们的方法更加的高效。

讲座专家介绍:

Tao Hong (洪涛) is a postdoctoral fellow in the functional MRI lab and EECS at the University of Michigan, Ann Arbor. He received his B.Eng. degree in communication engineering in 2012 from Zhejiang University of Technology, Hangzhou, China, and his Ph.D. degree in the Faculty of Computer Science in 2021 from Technion – Israel Institute of Technology, Haifa, Israel. His main research interests are numerical optimization and multigrid computational methods. He is especially interested in designing efficient computational methods to reduce the computational burden of the problems arising in scientific computing, signal processing, machine learning, and computational imaging. Recently, he focuses on computational MRI imaging, optical diffraction tomography, and machine learning.

洪涛目前是美国密歇根大学安娜堡分校fMRI实验室和电子工程系的博士后。他于2012年在浙江工业大学取得通信工程学士学位并于2021年获得以色列理工学院计算机系的博士学位。洪涛博士的主要研究兴趣是数值优化和多重网格计算方法。特别的洪涛博士的主要工作是设计高效算法来解决在科学计算,信号处理,机器学习和计算成像中形成的计算问题。目前洪涛博士的主要研究方向是计算核磁共振成像,光学衍射断层扫描和机器学习等。

关闭