End of Insertion Detection in Colonoscopy Videos

Description:

Colorectal cancer is the second leading cause of cancer-related deaths behind lung cancer in the United States. Colonoscopy is the preferred screening method for detection of diseases like Colorectal Cancer. In the year 2006, American Society for Gastrointestinal Endoscopy (ASGE) and American College of Gastroenterology (ACG) issued guidelines for quality colonoscopy. The guidelines suggest that on average the withdrawal phase during a screening colonoscopy should last a minimum of 6 minutes. My aim is to classify the colonoscopy video into insertion and withdrawal phase. The problem is that currently existing shot detection techniques cannot be applied because colonoscopy is a single camera shot from start to end. An algorithm to detect phase boundary has already been developed by the MIGLAB team. Existing method has acceptable levels of accuracy but the main issue is dependency on MPEG (Moving Pictures Expert Group) 1/2. I implemented exhaustive search for motion estimation to reduce the execution time and improve the accuracy. I took advantages of the C/C++ programming languages with multithreading which helped us get even better performances in terms of execution time. I propose a method for improving the current method of colonoscopy video analysis and also an extension for the same to make it usable for real time videos. The real time version we implemented is capable of handling streams coming directly from the camera in the form of uncompressed bitmap frames. Existing implementation could not be applied to real time scenario because of its dependency on MPEG 1/2. Future direction of this research includes improved motion search and GPU parallel computing techniques.

Creator(s): Malik, Avnish Rajbal
Creation Date: August 2009
Partner(s):
UNT Libraries
Collection(s):
UNT Theses and Dissertations
Usage:
Total Uses: 436
Past 30 days: 3
Yesterday: 0
Creator (Author):
Publisher Info:
Publisher Name: University of North Texas
Place of Publication: Denton, Texas
Date(s):
  • Creation: August 2009
Description:

Colorectal cancer is the second leading cause of cancer-related deaths behind lung cancer in the United States. Colonoscopy is the preferred screening method for detection of diseases like Colorectal Cancer. In the year 2006, American Society for Gastrointestinal Endoscopy (ASGE) and American College of Gastroenterology (ACG) issued guidelines for quality colonoscopy. The guidelines suggest that on average the withdrawal phase during a screening colonoscopy should last a minimum of 6 minutes. My aim is to classify the colonoscopy video into insertion and withdrawal phase. The problem is that currently existing shot detection techniques cannot be applied because colonoscopy is a single camera shot from start to end. An algorithm to detect phase boundary has already been developed by the MIGLAB team. Existing method has acceptable levels of accuracy but the main issue is dependency on MPEG (Moving Pictures Expert Group) 1/2. I implemented exhaustive search for motion estimation to reduce the execution time and improve the accuracy. I took advantages of the C/C++ programming languages with multithreading which helped us get even better performances in terms of execution time. I propose a method for improving the current method of colonoscopy video analysis and also an extension for the same to make it usable for real time videos. The real time version we implemented is capable of handling streams coming directly from the camera in the form of uncompressed bitmap frames. Existing implementation could not be applied to real time scenario because of its dependency on MPEG 1/2. Future direction of this research includes improved motion search and GPU parallel computing techniques.

Degree:
Level: Master's
Discipline: Computer Science
Language(s):
Subject(s):
Keyword(s): multithreading | end of insertion
Contributor(s):
Partner:
UNT Libraries
Collection:
UNT Theses and Dissertations
Identifier:
  • OCLC: 599674022 |
  • LCCN: b3825106
  • ARK: ark:/67531/metadc12159
Resource Type: Thesis or Dissertation
Format: Text
Rights:
Access: Public
License: Copyright
Holder: Malik, Avnish Rajbal
Statement: Copyright is held by the author, unless otherwise noted. All rights reserved.