Real-time phase boundary detection for colonoscopy videos using motion vector templates

Authors:
Ruwan Nawarathna;JungHwan Oh;Jayantha Muthukudage;Wallapak Tavanapong;Johnny Wong;Piet C. de Groen
Affiliations:
Department of Computer Science and Engineering, University of North Texas, Denton, Texas;Department of Computer Science and Engineering, University of North Texas, Denton, Texas;Department of Computer Science and Engineering, University of North Texas, Denton, Texas;Department of Computer Science, Iowa State University, Ames, Iowa;Department of Computer Science, Iowa State University, Ames, Iowa;Department of Medicine, Division of Gastroenterology and Hepatology, Mayo Clinic, Rochester, Minnesota
Venue:
MICCAI'12 Proceedings of the 4th international conference on Abdominal Imaging: computational and clinical applications
Year:
2012

Citing 4
Cited 0

A robust method for camera motion estimation in movies based on optical flow

International Journal of Intelligent Systems Technologies and Applications
Endoscopic video manifolds

MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part II
Color based stool region detection in colonoscopy videos for quality measurements

PSIVT'11 Proceedings of the 5th Pacific Rim conference on Advances in Image and Video Technology - Volume Part I
SAPPHIRE middleware and software development kit for medical video analysis

CBMS '11 Proceedings of the 2011 24th International Symposium on Computer-Based Medical Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Colonoscopy is the preferred screening method currently available for detection of colorectal cancer and its precursor lesions, colorectal polyps. However, recent data suggest that there is a significant miss rate for the detection of polyps in the colon during colonoscopy. Therefore, techniques for real-time quality measurement and feedback are necessary to aid the endoscopist towards optimal inspection to improve the overall quality of colonoscopy during the procedure. A typical colonoscopy procedure consists of two phases: an insertion phase and a withdrawal phase. One of the most essential tasks in real-time fully automated quality measurement is to find the location of the boundary between insertion and withdrawal phases. In this paper, we present a method based on motion vector templates to detect the phase boundary in real-time. The proposed method detects the phase boundary with a better accuracy and a faster speed compared to our previous method.