RGP Seminar –
Medical Image Segmentation Jointly Using Data-driven Methods and Model-based Methods
11 Nov, 2020 (Wed)
5:00 pm
Webinar Link:
Meeting ID: 294 451 6509
Password: 1234568

Add to your calendar: iCal, Google Calendar

HKU Campus Map


Mr. Yue Zhang
Department of Electrical and Electronic Engineering
The University of Hong Kong


The repaid growth of medical images brings a vast work burden for radiologists and physicians. Image segmentation, i.e., assigning every single voxel a category, is a critical problem in many applications, such as detecting liver tumors or volumetric analysis of stroke lesions. In this seminar, the speaker investigates how to obtain more accurate segmentation results from 3D medical images, including pancreas segmentation and liver tumor segmentation from CT images, stroke lesion segmentation and brain tumor segmentation from MR images. The classical image segmentation methods, such as level-set methods, are typically based on mathematical model but these model-based methods are typically not fully automatic, which limit their real applications. With the availability of large amounts of imaging data, significant progress has been made in medical image segmentation using data-driven methods, in particular deep learning. However, purely deep learning-based methods sometimes may fail to obtain explainable results. To improve the clinical image segmentation’s efficiency and robustness, the speaker applies some model-based methods before and after the neural network module, i.e., preprocessing and postprocessing.


Biography of the speaker:
Mr. Zhang received a B.S. degree in communication engineering from the Southern University of Science and Technology (SUSTech), in 2016. He is currently pursuing a Ph.D. degree in electrical and electronic engineering with The University of Hong Kong (joint with SUSTech), Hong Kong. He has published three journal papers (including MIA, IEEE JBHI) and several conference papers (including MICCAI, ISBI, IJCNN, and EMBC) in related areas. His research interests include medical image segmentation and reconstruction.


Professor Ed. X. Wu

Most seminars are open to the general public, free of charge, unless otherwise stated. Registration is not required. Arrangement for car parking facilities on campus please contact us for details.

For enquiries, please contact:
Department of Electrical and Electronic Engineering,
Room 601, Chow Yei Ching Building,
Pokfulam Road, Hong Kong
Tel: (852) 3917 7093
Email: seminar@eee.hku.hk