Ming_Jinjie.pdf (6.96 MB)
Download file

Improved diagnosis and navigation for CT colonography

Download (6.96 MB)
thesis
posted on 08.06.2021, 07:46 by Jinjie Ming
This project describes the development of an automatic segmentation method and a novel navigation system that detect polyps using advanced image processing and computer graphics tecniques. The colon wall segmentation method from the CT data set of abdomen is achieved by combining the contouring model - level set method and the minima detection using mathematical morphology theory. Polyp detection is attained by analyzing surface curvature and texture information along on the colon wall. Adding texture analysis provides a new feature for improving currently existing methods. As such, polyp candidates are examined not only by their shape and size but also by their texture appearance.

History

Language

eng

Program

Electrical and Computer Engineering

Granting Institution

Ryerson University

Thesis Advisor

Y Jiang

Usage metrics

Exports