广州数学大讲坛第二期
第十八讲——英国伯明翰大学端金鸣博士学术报告
题目：Machine Learning for Medical Image Computing: Reconstruction, Segmentation and Registration
时间：2024年3月26日（星期二）上午9:30-12:30
地点：文新楼413
报告人：端金鸣 博士
摘 要:This talk has three parts. In Part 1, I will provide an introduction to magnetic resonance (MR) image reconstruction and diffuse optical tomography (DOT) image reconstruction. Both of these procedures involve the resolution of an inverse problem, with MR image reconstruction being a linear inverse problem and DOT image reconstruction classified as a nonlinear inverse problem. In Part 2, I will discuss image segmentation, focusing on two specific modalities: optical coherence tomography (OCT) and cardiac MR (cMRI). In both scenarios, I will present both model- and data-driven approaches for achieving accurate segmentations. Then in part 3, I will introduce unsupervised learning for medical image registration, specifically focusing on how to register high-dimensional medical images in a fast, precise and data efficient manner. Throughout the presentation, I will showcase various real-world applications derived from segmentation and registration results.
报告人简介：
Dr. Duan iscurrently an Assistant Professor within School of Computer Science at University of Birmingham (UoB), a Turing Fellow at Alan Turing Institute and a Visiting Researcher at Imperial College London (ICL). From 2018 to 2020, he was a Research Associate jointly within Department of Computing and Institute of Clinical Sciences at ICL. There, he has been working closely with Prof Daniel Rueckert and Prof Declan O’Regan, developing cutting-edge machine learning methods for cardiovascular imaging. From 2014 to 2018, he was studying PhD degree in Computer Science at University of Nottingham under the supervision of Dr Li Bai, and PhD thesis titled "Variational and Partial Differential Equation (PDE)-based Methods for Image Processing". In 2023, his team developed a deep learning algorithm which won the second place in ISBI Robust Nonrigid Registration Challenge for Expansion Microscopy (RnR-ExM). In 2022, his team developed a machine learning algorithm for image registration which won the first place in the ‘Learn2Reg’ competition. In 2019, he developed an MRI reconstruction algorithm using deep learning which won 2nd place in the "fastMRI" competition organised by Facebook. In 2016, he was awarded the "Chinese Government Award for Outstanding Self-financed Students Abroad" issued by Xiaoming Liu, the ambassador of Chinese Ministry of Education. In 2015, his master's thesis titled "A Study on Generalised Variational Level Set Methods and Their Fast Projection Algorithms" won the "Best Master Thesis Award" across the whole Shandong Province in China. In 2014, he was granted a full studentship from EPSRC to study PhD at University of Nottingham. His work since then has appeared across 100+ peer-reviewed publications, including proceedings such as AAAI, MICCAI, CVPR, ECCV, etc, and journals such as The Lancet, Nature Machine Intelligence, IEEE Transactions on Medical Imaging, IEEE Transactions on Image Processing, etc.
