|
Joint SOC & PREMIA Seminar Talk by Prof. Heng Pheng Ann |
|
|
|
|
Wednesday, 29 October 2008 |
 We are pleased to invite you to the following seminar: Statistical Analysis of NeuroImages, by Prof. Heng Pheng Ann, Department of Computer Science & Engineering, The Chinese University of Hong Kong. The seminar is jointly organized by School of Computing (SOC),
NUS and Pattern Recognition and Machine Intelligence Association (PREMIA). (Presentation slides)
Title: Statistical Analysis of NeuroImages
Speaker: Prof. Heng Pheng Ann, Department of Computer Science & Engineering, The Chinese University of Hong Kong
Date & Time: 3 November (Monday) 2.00 - 3.00 pm
Venue: Seminar Room 3 (SR3 COM1/212)
(Refreshment will be provided after the Seminar)
Chaired by Prof. Tan Chew Lim (tancl@comp.nus.edu.sg)
Abstract: The rapid developments in brain imaging and intelligent
computation significantly extend medical examination capabilities and
provide new possibilities in neuroscience research. In particular, with
the plenty of 3D high-resolution images of the living human brains
(e.g., MRI), the statistical morphometry research into the brain
structure in a population becomes attractive and attainable. In this
talk, I will give an overview of our research in statistical
neuroanatomy. Firstly, on the T1-weighted MRI data, the volume-based
morphometry methods were applied to measure the statistical brain
difference between the adolescent idiopathic scoliosis (AIS) patients
and normal controls. Furthermore, we compared volume- and boundary-based morphometric methods on the analysis of 2-D
shapes of the corpus callosum (CC) obtained in patients with
left-thoracic AIS, as well as normal controls. In addition, to detect
the activation regions on functional MRI data, we presented an
extension of the support vector clustering (SVC) to step further toward
a data-sensitive detector, namely ellipsoidal support vector clustering
(ESVC).
Last but not least, I will talk about our recent work on the
statistical surface-based morphometry on vestibular systems by first
exacting the surface boundary of the vestibular system in T2-weigthed
MRI images using a new automatic segmentation pipeline, and then
estimate of the overall labyrinth geometry by measuring the
relationships among the best-fit planes and the best-fit circles.
Biodata: Prof. Heng received his B.Sc in computer science in 1985 from
the National University of Singapore. He received his M.Sc in computer
science, M.A. in applied mathematics, and Ph.D. in computer science
from Indiana University in 1987, 1988, and 1992 respectively. From 1992
to 1995, he worked as a research associate at the ISS-JHU Center for
Information-enhanced Medicine (CIeMed) of the National University of
Singapore. He joined The Chinese University of Hong Kong in 1995 as an
assistant professor and was promoted to the rank of full professor in
2002.
He has served as the Director of Virtual Reality, Visualization and
Imaging Research Centre at CUHK since 1999 and as the Director of
Centre for Human-Computer Interaction at Shenzhen Institute of Advanced
Integration Technology, Chinese Academy of Science/CUHK since 2006. He
has been appointed as a Cheung Kong Scholar Chair Professor by the
Ministry of Education, People Republic of China since 2007, and
currently holds several visiting or adjunct professorships at various
well-known universities in Mainland China. He received the IEEE
Transactions on Multimedia Prize Paper Award in 2005.
His current research interests include virtual reality applications in
medicine, visualization, medical imaging, human-computer interaction,
and computer graphics. |
