Conductivity Imaging using Deep Neural Networks

Time:Fri., 4:00-5:00pm June 2, 2023

Venue:Zoom ID: 271 534 5558 Passcode: YMSC

Speaker:金邦梯 Bangti Jin The Chinese University of Hong Kong


Dr. Bangti Jin received his PhD degree in applied mathematics from the Chinese University of Hong Kong, Hong Kong, in 2008. Currently he is a professor of mathematics at Department of Mathematics, The Chinese University of Hong Kong. Previously he was a lecturer, reader and professor of inverse problems at Department of Computer Science, University College London (2014-2022), an assistant professor of Mathematics at University of California, Riverside (2013-2014), a visiting assistant professor at Texas A&M University (2010-2013), an Alexandre von Humboldt postdoctoral researcher at the University of Bremen (2009-2010). His research interests include computational inverse problems and numerical analysis of differential equations.


Conductivity imaging is one fundamental task in medical imaging and provides a valuable tool for medical diagnosis. It is commonly formulated as recovering the conductivity coefficient in second-order elliptic PDEs from various observational data. We discuss several classes of numerical methods for the problem. Commonly, a regularized formulation consists of a data fidelity and a regularizer is employed, and then it is discretized using finite difference method, finite element methods or deep neural networks. One key issue is to establish a priori error estimates for the recovered conductivity distribution. In this talk, we discuss our recent findings on using deep neural networks for this class of problems, by effectively utilizing relevant stability estimates.

DATEJune 2, 2023
Related News
    • 0

      Road to conquer the hardness - solving hard computational problems with generic tensor networks

      AbstractI will introduce a tensor network-based method to compute the solution space properties of a broad class of combinatorial optimization problems (e.g. spin glasses and hard core lattice gases). These properties include finding one of the optimum solutions, counting the number of solutions of a given size, and enumeration and sampling of solutions of a given size. Using the hard core latt...

    • 1

      Causal Inference using Multivariate Generalized Linear Mixed-Effects Models

      AbstractDynamic prediction of causal effects under different treatment regimens is an essential problem in precision medicine. It is challenging because the actual mechanisms of treatment assignment and effects are unknown in observational studies. We propose a multivariate generalized linear mixed-effects model and a Bayesian g-computation algorithm to calculate the posterior distribution of s...