XClose

UCL Centre for Medical Image Computing

Home
Menu

Jong Chul Ye - CMIC seminar series

12 April 2019, 2:00 pm–3:00 pm

Jong Chul Ye, Professor, Dept. of Bio and Brain Engineering, Dept. Mathematical Sciences, KAIST, Daejeon, Korea - CMIC seminar series

Event Information

Open to

All

Organiser

cmic-seminars-request@cs.ucl.ac.uk

Location

LT 1.02
Malet Place Engineering Building
Malet Place
LONDON
WC1E 6BT

Jong Chul Ye, Professor, Dept. of Bio and Brain Engineering, Dept. Mathematical Sciences, KAIST, Daejeon, Korea

 

Title -  Deep Learning for Fast MR Acquisition: A Brief Review

 

Abstract

Recently, deep learning approaches with various network architectures have achieved significant performance improvement over existing iterative reconstruction methods in accelerated MRI problems.  However, it is still unclear why these deep learning architectures work for specific problems. Moreover, in contrast to the usual evolution of signal processing theory around the classical theories, the link between deep learning and the classical image processing approaches re not yet well understood. In this talk, I review the recent advances of deep learning approaches for accelerated MRI and their link to signal processing.  In particular, we review the variational neural network,  and the  popular feed-forward neural network approaches such as U-Net. Then, we review several advanced approaches such as AUTOMAP, CascadeNet, KiKi-Net, MoDL, etc, and demonstrate that the neural network approaches can be directly implemented in k-space domain to interpolate the missing k-space data.  Finally, we introduce recent results on MR contrast imputation using collaborative GAN (CollaGAN).   In order to explore the theoretical origin of the success of the neural network for accelerated MRI, we review some of the mathematical principles that have been proposed to explain the neural networks for inverse problems, which includes unrolling, convolution framelets, etc.  Then, we introduce recent mathematical discovery of the expressivity, generalization power and optimization landscape that give us hint to understand the power of AI for accelerated MRI.

 

Bio:

Jong Chul Ye is currently KAIST Endowed Chair Professor and Professor of the Dept. of Bio/Brain Engineering and Adjunct Professor at Dept. of Mathematical Sciences of Korea Advanced Institute of Science and Technology (KAIST), Korea. He received the B.Sc. and M.Sc. degrees from Seoul National University, Korea, and the Ph.D. from Purdue University, West Lafayette. Before joining KAIST, he worked at Philips Research and GE Global Research in New York. He has served as an associate editor of IEEE Trans. on Image Processing, and an editorial board member for Magnetic Resonance in Medicine. He is currently an associate editor for IEEE Trans. on Medical Imaging,  a Senior Editor of IEEE Signal Processing Magazine, and Section Editor for BMC Biomedical Engineering. In 2019, he begins his role as  a vice chair of IEEE Technical Committee on  Computational Imaging, and will become a chair in 2020-2021. He is also a General Co-chair for 2020 IEEE Symp. On Biomedical Imaging (ISBI), which will be held in Iowa City. His group was the first place winner of the 2009 Recon Challenge at the ISMRM workshop with k-t FOCUSS algorithm, the second winners at 2016 Low Dose CT Grand Challenge organized by the American Association of Physicists in Medicine (AAPM) with the world’s first deep learning algorithm for low-dose CT, and the third place winner for 2017 CVPR NTIRE challenge on example-based single image super-resolution.