Detection of quality visualization of appendiceal orifices using local edge cross-section profile features and near pause detection

Yi Wang; Wallapak Tavanapong; Johnny S. Wong; Junghwan Oh; Piet C. De Groen

doi:10.1109/TBME.2009.2034466

Detection of quality visualization of appendiceal orifices using local edge cross-section profile features and near pause detection

Yi Wang, Wallapak Tavanapong, Johnny S. Wong, Junghwan Oh, Piet C. De Groen

Research output: Contribution to journal › Article › peer-review

19 Scopus citations

Abstract

Colonoscopy is an endoscopic technique that allows a physician to inspect the inside of the human colon. The appearance of the appendiceal orifice during colonoscopy indicates a complete traversal of the colon, which is an important quality indicator of the colon examination. In this paper, we present two new algorithms. The first algorithm determines whether an image shows the clearly seen appendiceal orifice. This algorithm uses our new local features based on geometric shape, illumination difference, and intensity changes along the norm direction (cross section) of an edge. The second algorithm determines whether the video is an appendix video (the video showing at least 3 s of the appendiceal orifice inspection). Such a video indicates good visualization of the appendiceal orifice. This algorithm utilizes frame intensity histograms to detect a near camera pause during the apendiceal orifice inspection. We tested our algorithms on 23 videos captured from two types of endoscopy procedures. The average sensitivity and specificity for the detection of appendiceal orifice images with the often seen crescent appendiceal orifice shape are 96.86% and 90.47%, respectively. The average accuracy for the detection of appendix videos is 91.30%.

Original language	English (US)
Article number	5290066
Pages (from-to)	685-695
Number of pages	11
Journal	IEEE Transactions on Biomedical Engineering
Volume	57
Issue number	3
DOIs	https://doi.org/10.1109/TBME.2009.2034466
State	Published - Mar 2010
Externally published	Yes

Bibliographical note

Funding Information:
Manuscript received January 5, 2009; revised July 18, 2009 and September 4, 2009. First published October 20, 2009; current version published February 17, 2010. This work was supported in part by the U.S. National Science Foundation under Grant STTR-0740596, Agency for Healthcare Research and Quality, the Mayo Clinic, Grow Iowa Values Fund, and Iowa State University Research Foundation. The work of J. S. Wong, W. Tavanapong, and J. Oh was supported by EndoMetric, LLC, Ames, IA. Asterisk indicates corresponding author.

Keywords

Appendiceal orifice detection
Appendix video detection
Colonoscopy
Edge cross section
Medical video analysis

Access

10.1109/TBME.2009.2034466

OpenUrl availability

Full text

Cite this

@article{fd4c4a3d6034422abbfbf1468d072a93,

title = "Detection of quality visualization of appendiceal orifices using local edge cross-section profile features and near pause detection",

abstract = "Colonoscopy is an endoscopic technique that allows a physician to inspect the inside of the human colon. The appearance of the appendiceal orifice during colonoscopy indicates a complete traversal of the colon, which is an important quality indicator of the colon examination. In this paper, we present two new algorithms. The first algorithm determines whether an image shows the clearly seen appendiceal orifice. This algorithm uses our new local features based on geometric shape, illumination difference, and intensity changes along the norm direction (cross section) of an edge. The second algorithm determines whether the video is an appendix video (the video showing at least 3 s of the appendiceal orifice inspection). Such a video indicates good visualization of the appendiceal orifice. This algorithm utilizes frame intensity histograms to detect a near camera pause during the apendiceal orifice inspection. We tested our algorithms on 23 videos captured from two types of endoscopy procedures. The average sensitivity and specificity for the detection of appendiceal orifice images with the often seen crescent appendiceal orifice shape are 96.86% and 90.47%, respectively. The average accuracy for the detection of appendix videos is 91.30%.",

keywords = "Appendiceal orifice detection, Appendix video detection, Colonoscopy, Edge cross section, Medical video analysis",

author = "Yi Wang and Wallapak Tavanapong and Wong, {Johnny S.} and Junghwan Oh and {De Groen}, {Piet C.}",

note = "Funding Information: Manuscript received January 5, 2009; revised July 18, 2009 and September 4, 2009. First published October 20, 2009; current version published February 17, 2010. This work was supported in part by the U.S. National Science Foundation under Grant STTR-0740596, Agency for Healthcare Research and Quality, the Mayo Clinic, Grow Iowa Values Fund, and Iowa State University Research Foundation. The work of J. S. Wong, W. Tavanapong, and J. Oh was supported by EndoMetric, LLC, Ames, IA. Asterisk indicates corresponding author.",

year = "2010",

month = mar,

doi = "10.1109/TBME.2009.2034466",

language = "English (US)",

volume = "57",

pages = "685--695",

journal = "IEEE Transactions on Biomedical Engineering",

issn = "0018-9294",

publisher = "IEEE Computer Society",

number = "3",

}

TY - JOUR

T1 - Detection of quality visualization of appendiceal orifices using local edge cross-section profile features and near pause detection

AU - Wang, Yi

AU - Tavanapong, Wallapak

AU - Wong, Johnny S.

AU - Oh, Junghwan

AU - De Groen, Piet C.

N1 - Funding Information: Manuscript received January 5, 2009; revised July 18, 2009 and September 4, 2009. First published October 20, 2009; current version published February 17, 2010. This work was supported in part by the U.S. National Science Foundation under Grant STTR-0740596, Agency for Healthcare Research and Quality, the Mayo Clinic, Grow Iowa Values Fund, and Iowa State University Research Foundation. The work of J. S. Wong, W. Tavanapong, and J. Oh was supported by EndoMetric, LLC, Ames, IA. Asterisk indicates corresponding author.

PY - 2010/3

Y1 - 2010/3

N2 - Colonoscopy is an endoscopic technique that allows a physician to inspect the inside of the human colon. The appearance of the appendiceal orifice during colonoscopy indicates a complete traversal of the colon, which is an important quality indicator of the colon examination. In this paper, we present two new algorithms. The first algorithm determines whether an image shows the clearly seen appendiceal orifice. This algorithm uses our new local features based on geometric shape, illumination difference, and intensity changes along the norm direction (cross section) of an edge. The second algorithm determines whether the video is an appendix video (the video showing at least 3 s of the appendiceal orifice inspection). Such a video indicates good visualization of the appendiceal orifice. This algorithm utilizes frame intensity histograms to detect a near camera pause during the apendiceal orifice inspection. We tested our algorithms on 23 videos captured from two types of endoscopy procedures. The average sensitivity and specificity for the detection of appendiceal orifice images with the often seen crescent appendiceal orifice shape are 96.86% and 90.47%, respectively. The average accuracy for the detection of appendix videos is 91.30%.

AB - Colonoscopy is an endoscopic technique that allows a physician to inspect the inside of the human colon. The appearance of the appendiceal orifice during colonoscopy indicates a complete traversal of the colon, which is an important quality indicator of the colon examination. In this paper, we present two new algorithms. The first algorithm determines whether an image shows the clearly seen appendiceal orifice. This algorithm uses our new local features based on geometric shape, illumination difference, and intensity changes along the norm direction (cross section) of an edge. The second algorithm determines whether the video is an appendix video (the video showing at least 3 s of the appendiceal orifice inspection). Such a video indicates good visualization of the appendiceal orifice. This algorithm utilizes frame intensity histograms to detect a near camera pause during the apendiceal orifice inspection. We tested our algorithms on 23 videos captured from two types of endoscopy procedures. The average sensitivity and specificity for the detection of appendiceal orifice images with the often seen crescent appendiceal orifice shape are 96.86% and 90.47%, respectively. The average accuracy for the detection of appendix videos is 91.30%.

KW - Appendiceal orifice detection

KW - Appendix video detection

KW - Colonoscopy

KW - Edge cross section

KW - Medical video analysis

UR - http://www.scopus.com/inward/record.url?scp=77649164367&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77649164367&partnerID=8YFLogxK

U2 - 10.1109/TBME.2009.2034466

DO - 10.1109/TBME.2009.2034466

M3 - Article

C2 - 19846366

AN - SCOPUS:77649164367

SN - 0018-9294

VL - 57

SP - 685

EP - 695

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

IS - 3

M1 - 5290066

ER -

Detection of quality visualization of appendiceal orifices using local edge cross-section profile features and near pause detection

Abstract

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this