Flux-based Curvilinear Structure Analysis

PhD Thesis Proposal Defence


Title: "Flux-based Curvilinear Structure Analysis"

by

Mr. Jierong WANG


Abstract:

The curvilinear structure is a vital clue in many vessel diseases. During 
curvilinear structure analysis, high-level information such as 
eccentricity, scale, structural orientation, and abnormality can be 
collected for disease diagnosis and pathology quantification. Among a wide 
range of techniques for curvilinear structure analysis, linear descriptors 
based on various assumptions and prior knowledge of the target structures 
have been drawing attention for decades.

In the first proposed method, we extend the flux descriptor using an 
oriented cylindrical model whose centerline is curvilinear and the model 
orientation is homogeneous with the object orientation. Then, higher-order 
tensor construction and decomposition framework is adopted to further 
improve orientation coherence. Our second method is an efficient 
manipulation of the higher-order tensor combined with the oriented flux. 
We construct the higher-order tensor in the frequency domain with the help 
of spherical harmonics transform and calculate fiber orientation 
distribution function for vascular responses.  In our third work, we 
improve the optimally oriented flux in two aspects:  normal plane 
(eccentricity), and orientation. While the first three proposed methods 
concentrate on the improvement of the low-level descriptors, the last 
presented method contribute to the graphical framework. Concretely, in our 
fourth work, the random walks framework is improved by a modified Forman's 
curvature function, which is modeled in sub-pixel resolution and can 
capture details in a higher order.


Date:			Tuesday, 3 May 2022

Time:                  	4:00pm - 6:00pm

Zoom Meeting:
https://hkust.zoom.us/j/93717337886?pwd=L25DS3ZiNUc3ZUZlSUllRzdSUVhYZz09

Committee Members:	Prof. Albert Chung (Supervisor)
  			Prof. Chi-Keung Tang (Supervisor)
 			Dr. Xiaojuan Ma (Chairperson)
 			Prof. Pedro Sander


**** ALL are Welcome ****