DocumentCode
3405630
Title
3D reconstruction of GI tract texture surface using Capsule Endoscopy Images
Author
Zhao, Qian ; Meng, Max Q -H
Author_Institution
Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Hong Kong, China
fYear
2012
fDate
15-17 Aug. 2012
Firstpage
277
Lastpage
282
Abstract
Wireless Capsule Endoscopy (CE) is a novel technique to screen the entire gastrointestinal (GI) tract, especially the small bowel. It was invented by Given Imaging in 2000 to solve the problem that the conventional tools cannot explore the entire small bowel. As it is non-invasive, reliable, and safe, it has been widely applied around the world. Although the clinical findings of CE are promising, there still exist some limitations. The main problem is that it produces over 50,000 images during one examination. It is a highly time-consuming and labor-intensive task to inspect such long video for clinicians. Moreover, CE images are lack of prominent characteristics, which make it difficult to diagnose diseases even for an experienced clinician. So it is desirable and necessary to develop a tool to assist clinicians during diagnosis. In this paper, we propose a method to reconstruct the 3D texture surface of GI tract using single CE image. We applied Shape from Shading (SfS) technique to represent the surface of GI tract using 2D CE images. It is a novel way to view the abnormalities, especially for polyp, which can lead to a more efficient examination. Preliminary experiments on real CE images have been conducted. The results show that our method achieved promising performance.
Keywords
diseases; endoscopes; image reconstruction; image segmentation; image texture; medical image processing; 2D CE images; 3D reconstruction; 3D texture surface; GI tract texture surface; SfS technique; capsule endoscopy image; gastrointestinal tract; polyp; shape from shading; wireless capsule endoscopy; Endoscopes; Hemorrhaging; Image reconstruction; Mathematical model; Shape; Surface reconstruction; Three dimensional displays;
fLanguage
English
Publisher
ieee
Conference_Titel
Automation and Logistics (ICAL), 2012 IEEE International Conference on
Conference_Location
Zhengzhou
ISSN
2161-8151
Print_ISBN
978-1-4673-0362-0
Electronic_ISBN
2161-8151
Type
conf
DOI
10.1109/ICAL.2012.6308211
Filename
6308211
Link To Document