A Survey on 3D Vessel Segmentation

PhD Qualifying Examination


Title: "A Survey on 3D Vessel Segmentation"

by

Miss Ning ZHU


Abstract:

In recent years, vessel disease, which is one of the major causes of death 
around the world, has become an important health problem. Vessel segmentation 
is an important technique, and it can help the diagnosis, visualization, 
treatment and surgery planning for vessel diseases. In this survey, we 
introduce different types of commonly used 3D vessel segmentation methods, 
features, and some related issues and applications. Both semi-automatic methods 
and fully automatic methods are included. As for semi-automatic methods, 
approaches based on region growing, active contours, centerline, graph cuts and 
particles filters are described. As for automatic methods, tubular detection is 
introduced because it is one of the most important approaches belong to this 
category.

Feature is also an important factor for the segmentation methods. Hessian 
filter, a popular tool for vessel enhancement and tubular structure detection 
is briefly described. A unique kind of feature for vessel, the 2D cross 
sectional feature is also mentioned. Preprocessing and postprocessing, together 
with the methods and features, complete the overview of the whole procedure of 
vessel segmentation. We then also talk about the important applications, such 
as the detection of bifurcation, stenosis and aneurysms. Last but not least, we 
briefly introduce two public available data sets and several evaluation tools.


Date:                   Tuesday, 22 May 2012

Time:                   2:00pm - 4:00pm

Venue:                  Room 1505
                         lifts 25/26

Committee Members:	Dr. Albert Chung (Supervisor)
                         Prof. Chi-Keung Tang (Chairperson)
 			Prof. Dit-Yan Yeung
 			Dr. Weichuan Yu (ECE)


**** ALL are Welcome ****