Doctoral course - Annotation-Efficient Medical Image Segmentation

This short course is designed for research students who are interested in on medical image segmentation. It is well known that annotation of medical images from medical experts are expensive and time consuming while deep learning methods for medical images require large amount of label images. This course will focus on how to perform medical image segmentation with limited number of labeled images. After completion of this short course, students will have a good understanding of the problems, existing approaches, and current state of the art of annotation-efficient medical image segmentation.
Pre-requisite: Basic concept of algorithm, image processing, deep learning, linear algebra, and calculus.

Event information

Time

-

Location

Linnanmaa

Add event to calendar

External teacher(s): Pong Chi YUEN
External teacher(s) organization: Hong Kong Baptist University
ECTS -credits: 2
Grade: Pass or Fail

Assessment:

  • Students with a group of 2-3 need to
  1. Design an algorithm to solve a specific liver CT tumor segmentation problem(s) which will be announced during the lecture on 31 January 2024;
  2. Prepare submit a 10-min presentation video; and
  3. Submit a (max) 6-page report on the design (no implementation is required), including all figures, table and references. The report includes one section stating the contributions of each member.
  • Pass or fail grade, based on the project presentation and report (algorithm design)
  • Project presentation video and report submission:
    • Due: 16 Feb 2024
    • Email a link to PC Yuen (pcyuen@comp.hkbu.edu.hk) for downloading the presentation video and report.

(Estimated) Date of the course

The eight face-to-face lectures will be conducted in three mornings as follows.

  • Date: 29 January 2024 Time: 9:30 -12:30 Venue: TL102
  • Date: 31 January 2024 Time: 9:30 -12:30 Venue: TL102
  • Date: 2 February 2024 Time: 10:30 – 12:30 Venue: AT117

Learning objectives and contents:

This short course is designed for research students who are interested in on medical image segmentation. It is well known that annotation of medical images from medical experts are expensive and time consuming while deep learning methods for medical images require large amount of label images. This course will focus on how to perform medical image segmentation with limited number of labelled images. After completion of this short course, students will have a good understanding on the problems, existing approaches and current state of the art of annotation-efficient medical image segmentation.

Pre-requisite: Basic concept on algorithm, image processing, deep learning, linear algebra and calculus.

Tentative topics:

  • Introduction to Artificial Intelligence in Medicine (one lecture)
  • Medical Image Semantic Segmentation Methods (two lectures)
  • Annotation-efficient Strategies for Medical Image Semantic Segmentation (two lectures
  • Group project on CT image Segmentation (one lecture)
  • Case Study (two lectures)
    • Liver Tumor Segmentation
    • Lung and cross-disease Lesion Segmentation

Key methods:

  • Deep learning based medical image segmentation models
  • Domain adaption
  • Self-supervised learning
  • Weakly supervised learning
  • Semi-supervised learning
  • Medical image generation

Amount of contact teaching hours:

  • 8 hours (including one hour for introducing group project and assessment)

Bio of the lecturer:

Pong C Yuen received his B.Sc. degree in Electronic Engineering with first class honours in 1989 from City Polytechnic of Hong Kong, and his Ph.D. degree in Electrical and Electronic Engineering in 1993 from The University of Hong Kong. He joined the Hong Kong Baptist University in 1993, and served as the Head of Department of Computer Science from 2011 – 2017. Currently, he is a Chair Professor at the Department of Computer Science and Associate Dean of Science Faculty, Hong Kong Baptist University.

Dr. Yuen was a recipient of the University Fellowship to visit The University of Sydney. Dr. Yuen spent his sabbatical and visited a number of universities/research institutes, including The University of Maryland at College Park, INRIA Rhone Alpes, ETH Zurich, and The University of Bologna. Dr. Yuen was the director of Croucher Advanced Study Institute (ASI) on biometric authentication in 2004 and the director of Croucher ASI on Biometric Security and Privacy in 2007. He has been serving the Director of IAPR/IEEE Winter School on Biometrics since 2017.

Dr. Yuen has been actively involved in many international conferences and professional community. He was the track co-chair of the International Conference on Pattern Recognition (ICPR) 2006, the program co-chair of the IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems (BTAS) 2012, the IEEE International Conference on Identity, Security and Behavior Analysis (ISBA) 2016, the International Workshop on Information, Forensics and Security (WIFS) 2018, International Joint Conference on Biometrics (IJCB) 2021. He served as Associate Editor of IEEE Transactions on Information Forensics and Security (2014 – 2018), and received the Outstanding Editorial Board Service Award in 2018. Dr. Yuen has also served as the Vice President (Technical Activities) of the IEEE Biometrics Council (2017-2019), and Associate Editor/Senior Editor of SPIE Journal of Electronic Imaging (2012-2019). Currently, Dr. Yuen is serving as the Senior Area Editor of IEEE Transactions on Information Forensics and Security, Editorial Board Member of Pattern Recognition, and Associate Editor of IEEE Transactions on Biometrics, Behavior and Identity Science. He received the first-prize and second-prize Natural Science Awards from the Guangdong Province and the Ministry of Education, China, respectively. He is a Fellow of IAPR.

Dr. Yuen's current research interests include biometric security and privacy, video surveillance and medical informatics.

Last updated: 23.1.2024