Automatic real-time detection of endoscopic procedures using temporal features

Sean R. Stanek; Wallapak Tavanapong; Johnny Wong; Jung Hwan Oh; Piet C. de Groen

doi:10.1016/j.cmpb.2011.04.003

Automatic real-time detection of endoscopic procedures using temporal features

Sean R. Stanek, Wallapak Tavanapong, Johnny Wong, Jung Hwan Oh, Piet C. de Groen

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

24 Scopus citations

Abstract

Endoscopy is used for inspection of the inner surface of organs such as the colon. During endoscopic inspection of the colon or colonoscopy, a tiny video camera generates a video signal, which is displayed on a monitor for interpretation in real-time by physicians. In practice, these images are not typically captured, which may be attributed by lack of fully automated tools for capturing, analysis of important contents, and quick and easy retrieval of these contents. This paper presents the description and evaluation results of our novel software that uses new metrics based on image color and motion over time to automatically record all images of an individual endoscopic procedure into a single digitized video file. The software automatically discards out-patient video frames between different endoscopic procedures. We validated our software system on 2464. h of live video (over 265 million frames) from endoscopy units where colonoscopy and upper endoscopy were performed. Our previous classification method achieved a frame-based sensitivity of 100.00%, but only a specificity of 89.22%. Our new method achieved a frame-based sensitivity and specificity of 99.90% and 99.97%, a significant improvement. Our system is robust for day-to-day use in medical practice.

Original language	English (US)
Pages (from-to)	524-535
Number of pages	12
Journal	Computer Methods and Programs in Biomedicine
Volume	108
Issue number	2
DOIs	https://doi.org/10.1016/j.cmpb.2011.04.003
State	Published - Nov 2012
Externally published	Yes

Bibliographical note

Funding Information:
This work was supported in part by the National Science Foundation grant nos. 0740596 , IIP-0956847 , Agency for Healthcare Research and Quality grant no. HS17537 and National Institute of Diabetes and Digestive and Kidney Diseases DK083745 , the Mayo Clinic, Grow Iowa Values Fund, and Iowa State University Research Foundation. Wong, Tavanapong and Oh hold positions at EndoMetric Corporation, Ames, IA 50014, USA, a for profit company that markets endoscopy-related software. Wong, Tavanapong, Oh and Mayo Clinic own stock in EndoMetric. Wong, Tavanapong and de Groen have received royalty payments from EndoMetric. Findings, opinions, and conclusions expressed in this paper do not necessarily reflect the view of the funding agencies.

Keywords

Colonoscopy
Endoscopy
Image analysis
Real-time
Video capture
Video content analysis

Access

10.1016/j.cmpb.2011.04.003

OpenUrl availability

Full text

Cite this

@article{847f74dcd6134fde95eb64aee017c6e0,

title = "Automatic real-time detection of endoscopic procedures using temporal features",

abstract = "Endoscopy is used for inspection of the inner surface of organs such as the colon. During endoscopic inspection of the colon or colonoscopy, a tiny video camera generates a video signal, which is displayed on a monitor for interpretation in real-time by physicians. In practice, these images are not typically captured, which may be attributed by lack of fully automated tools for capturing, analysis of important contents, and quick and easy retrieval of these contents. This paper presents the description and evaluation results of our novel software that uses new metrics based on image color and motion over time to automatically record all images of an individual endoscopic procedure into a single digitized video file. The software automatically discards out-patient video frames between different endoscopic procedures. We validated our software system on 2464. h of live video (over 265 million frames) from endoscopy units where colonoscopy and upper endoscopy were performed. Our previous classification method achieved a frame-based sensitivity of 100.00%, but only a specificity of 89.22%. Our new method achieved a frame-based sensitivity and specificity of 99.90% and 99.97%, a significant improvement. Our system is robust for day-to-day use in medical practice.",

keywords = "Colonoscopy, Endoscopy, Image analysis, Real-time, Video capture, Video content analysis",

author = "Stanek, {Sean R.} and Wallapak Tavanapong and Johnny Wong and Oh, {Jung Hwan} and {de Groen}, {Piet C.}",

note = "Funding Information: This work was supported in part by the National Science Foundation grant nos. 0740596 , IIP-0956847 , Agency for Healthcare Research and Quality grant no. HS17537 and National Institute of Diabetes and Digestive and Kidney Diseases DK083745 , the Mayo Clinic, Grow Iowa Values Fund, and Iowa State University Research Foundation. Wong, Tavanapong and Oh hold positions at EndoMetric Corporation, Ames, IA 50014, USA, a for profit company that markets endoscopy-related software. Wong, Tavanapong, Oh and Mayo Clinic own stock in EndoMetric. Wong, Tavanapong and de Groen have received royalty payments from EndoMetric. Findings, opinions, and conclusions expressed in this paper do not necessarily reflect the view of the funding agencies. ",

year = "2012",

month = nov,

doi = "10.1016/j.cmpb.2011.04.003",

language = "English (US)",

volume = "108",

pages = "524--535",

journal = "Computer Methods and Programs in Biomedicine",

issn = "0169-2607",

publisher = "Elsevier Ireland Ltd",

number = "2",

}

TY - JOUR

T1 - Automatic real-time detection of endoscopic procedures using temporal features

AU - Stanek, Sean R.

AU - Tavanapong, Wallapak

AU - Wong, Johnny

AU - Oh, Jung Hwan

AU - de Groen, Piet C.

N1 - Funding Information: This work was supported in part by the National Science Foundation grant nos. 0740596 , IIP-0956847 , Agency for Healthcare Research and Quality grant no. HS17537 and National Institute of Diabetes and Digestive and Kidney Diseases DK083745 , the Mayo Clinic, Grow Iowa Values Fund, and Iowa State University Research Foundation. Wong, Tavanapong and Oh hold positions at EndoMetric Corporation, Ames, IA 50014, USA, a for profit company that markets endoscopy-related software. Wong, Tavanapong, Oh and Mayo Clinic own stock in EndoMetric. Wong, Tavanapong and de Groen have received royalty payments from EndoMetric. Findings, opinions, and conclusions expressed in this paper do not necessarily reflect the view of the funding agencies.

PY - 2012/11

Y1 - 2012/11

N2 - Endoscopy is used for inspection of the inner surface of organs such as the colon. During endoscopic inspection of the colon or colonoscopy, a tiny video camera generates a video signal, which is displayed on a monitor for interpretation in real-time by physicians. In practice, these images are not typically captured, which may be attributed by lack of fully automated tools for capturing, analysis of important contents, and quick and easy retrieval of these contents. This paper presents the description and evaluation results of our novel software that uses new metrics based on image color and motion over time to automatically record all images of an individual endoscopic procedure into a single digitized video file. The software automatically discards out-patient video frames between different endoscopic procedures. We validated our software system on 2464. h of live video (over 265 million frames) from endoscopy units where colonoscopy and upper endoscopy were performed. Our previous classification method achieved a frame-based sensitivity of 100.00%, but only a specificity of 89.22%. Our new method achieved a frame-based sensitivity and specificity of 99.90% and 99.97%, a significant improvement. Our system is robust for day-to-day use in medical practice.

AB - Endoscopy is used for inspection of the inner surface of organs such as the colon. During endoscopic inspection of the colon or colonoscopy, a tiny video camera generates a video signal, which is displayed on a monitor for interpretation in real-time by physicians. In practice, these images are not typically captured, which may be attributed by lack of fully automated tools for capturing, analysis of important contents, and quick and easy retrieval of these contents. This paper presents the description and evaluation results of our novel software that uses new metrics based on image color and motion over time to automatically record all images of an individual endoscopic procedure into a single digitized video file. The software automatically discards out-patient video frames between different endoscopic procedures. We validated our software system on 2464. h of live video (over 265 million frames) from endoscopy units where colonoscopy and upper endoscopy were performed. Our previous classification method achieved a frame-based sensitivity of 100.00%, but only a specificity of 89.22%. Our new method achieved a frame-based sensitivity and specificity of 99.90% and 99.97%, a significant improvement. Our system is robust for day-to-day use in medical practice.

KW - Colonoscopy

KW - Endoscopy

KW - Image analysis

KW - Real-time

KW - Video capture

KW - Video content analysis

UR - http://www.scopus.com/inward/record.url?scp=84867403697&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867403697&partnerID=8YFLogxK

U2 - 10.1016/j.cmpb.2011.04.003

DO - 10.1016/j.cmpb.2011.04.003

M3 - Article

C2 - 21621870

AN - SCOPUS:84867403697

SN - 0169-2607

VL - 108

SP - 524

EP - 535

JO - Computer Methods and Programs in Biomedicine

JF - Computer Methods and Programs in Biomedicine

IS - 2

ER -

Automatic real-time detection of endoscopic procedures using temporal features

Abstract

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this