Date and time: Tuesday 28 October 2025, 11:00-12:00 CET
Speaker: Albert Chi Shing Chuang, The Hong Kong University of Science and Technology
Title: Deep Learning for Medical Image Analysis in Neuroimaging
Where: Digital Futures hub, Osquars Backe 5, floor 2 at KTH main campus OR Zoom
Directions: https://www.digitalfutures.kth.se/contact/how-to-get-here/
OR
Zoom: https://kth-se.zoom.us/j/69560887455
Host: Ruoli Wang, ruoli@kth.se
Bio: Professor Chung received his BEngg degree (First-Class Honors) in Computer Engineering from the University of Hong Kong in 1995. He obtained his M.Phil. degree in Computer Science in 1998 at HKUST. He joined the Medical Vision Laboratory, Robotics Research Group at the University of Oxford, UK as a doctoral research student in 1998, and graduated in 2001 with DPhil degree in Engineering Science. Prof Chung was a Croucher scholar (1998 – 2001) with the Croucher Foundation Scholarship. He was a visiting scientist at the Artificial Intelligence Laboratory, Massachusetts Institute of Technology, USA (Sept 2001 – Feb 2002).
He founded the Lo Kwee-Seong Medical Image Analysis Laboratory in 2005 with a generous donation from the K.S. Lo Foundation, Hong Kong. The laboratory conducts interdisciplinary research on developing and applying computational and engineering techniques for medical image analysis, aiming to enhance healthcare quality in Hong Kong and beyond. His research lies at the intersection of medical image analysis, image processing, computer vision, and medical imaging, with a particular focus on image segmentation and registration.
Abstract: Deep Learning has revolutionized the methodology for analysing medical images, e.g., brain mapping of MRI images and super-resolution of brain cell images. In this talk, I will discuss our recent work on deep learning-based image registration and its applications on brain tumour image registration and atlas generation for a group of brain images. I will also illustrate our recent development on brain cell image super-resolution which is self- supervised and allows image upscaling at any arbitrary scale. Finally, some remaining challenges in medical image analysis will be listed and discussed.
