Cable footprint history: Spatio-temporal technique for instrument detection in gastrointestinal endoscopic procedures

Chuanhai Zhang; Wallapak Tavanapong; Johnny Wong; Piet C. De Groen; Jung Hwan Oh

Cable footprint history: Spatio-temporal technique for instrument detection in gastrointestinal endoscopic procedures

Chuanhai Zhang, Wallapak Tavanapong, Johnny Wong, Piet C. De Groen, Jung Hwan Oh

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We propose a new fast spatio-temporal technique that detects an operation scene-a video segment corresponding to a single purpose diagnosis action or a single purpose therapeutic action. The technique utilizes (1) color contrast of the cable region and the background, (2) the new area-based coordinate system to compute spatial features, and (3) the history of locations of detected cables of the instrument in a video to discard false regions. The proposed technique and software are useful for (1) automatic documentation of diagnostic or therapeutic operations at the end of the procedure, (2) a second review for causes of complications due to these operations, and (3) a building block for an effective content-based retrieval system to facilitate endoscopic research and education. On 38 full-length colonoscopy and upper endoscopy video files with different cable colors and four different insertion directions of the instruments, the average percentage of false positive duration is small at 2.23%. The average percentage of true positive duration is high at 92.9%. The average analysis time per image is 13 milliseconds on an inexpensive off-the-shelf PC.

Original language	English (US)
Title of host publication	Proceedings of the 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015
Editors	Hamid R. Arabnia, Leonidas Deligiannidis, Fernando G. Tinetti, George Jandieri, Gerald Schaefer, Ashu M. G. Solo
Publisher	CSREA Press
Pages	308-314
Number of pages	7
ISBN (Electronic)	1601324049, 9781601324047
State	Published - 2015
Externally published	Yes
Event	2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015, at WORLDCOMP 2015 - Las Vegas, United States Duration: Jul 27 2015 → Jul 30 2015

Publication series

Name	Proceedings of the 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015

Conference

Conference	2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015, at WORLDCOMP 2015
Country/Territory	United States
City	Las Vegas
Period	7/27/15 → 7/30/15

Bibliographical note

Publisher Copyright:
© International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015.All right reserved.

Keywords

Colonoscopy
Image analysis
Image features
Instruments
Polypectomy

OpenUrl availability

Full text

Cite this

Zhang, C., Tavanapong, W., Wong, J., De Groen, P. C., & Oh, J. H. (2015). Cable footprint history: Spatio-temporal technique for instrument detection in gastrointestinal endoscopic procedures. In H. R. Arabnia, L. Deligiannidis, F. G. Tinetti, G. Jandieri, G. Schaefer, & A. M. G. Solo (Eds.), Proceedings of the 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015 (pp. 308-314). (Proceedings of the 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015). CSREA Press.

Cable footprint history: Spatio-temporal technique for instrument detection in gastrointestinal endoscopic procedures. / Zhang, Chuanhai; Tavanapong, Wallapak; Wong, Johnny et al.
Proceedings of the 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015. ed. / Hamid R. Arabnia; Leonidas Deligiannidis; Fernando G. Tinetti; George Jandieri; Gerald Schaefer; Ashu M. G. Solo. CSREA Press, 2015. p. 308-314 (Proceedings of the 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Zhang, C, Tavanapong, W, Wong, J, De Groen, PC & Oh, JH 2015, Cable footprint history: Spatio-temporal technique for instrument detection in gastrointestinal endoscopic procedures. in HR Arabnia, L Deligiannidis, FG Tinetti, G Jandieri, G Schaefer & AMG Solo (eds), Proceedings of the 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015. Proceedings of the 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015, CSREA Press, pp. 308-314, 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015, at WORLDCOMP 2015, Las Vegas, United States, 7/27/15.

Zhang C, Tavanapong W, Wong J, De Groen PC, Oh JH. Cable footprint history: Spatio-temporal technique for instrument detection in gastrointestinal endoscopic procedures. In Arabnia HR, Deligiannidis L, Tinetti FG, Jandieri G, Schaefer G, Solo AMG, editors, Proceedings of the 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015. CSREA Press. 2015. p. 308-314. (Proceedings of the 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015).

Zhang, Chuanhai ; Tavanapong, Wallapak ; Wong, Johnny et al. / Cable footprint history : Spatio-temporal technique for instrument detection in gastrointestinal endoscopic procedures. Proceedings of the 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015. editor / Hamid R. Arabnia ; Leonidas Deligiannidis ; Fernando G. Tinetti ; George Jandieri ; Gerald Schaefer ; Ashu M. G. Solo. CSREA Press, 2015. pp. 308-314 (Proceedings of the 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015).

@inproceedings{529f3864f5874a6e9df16d0afb0cdfaa,

title = "Cable footprint history: Spatio-temporal technique for instrument detection in gastrointestinal endoscopic procedures",

abstract = "We propose a new fast spatio-temporal technique that detects an operation scene-a video segment corresponding to a single purpose diagnosis action or a single purpose therapeutic action. The technique utilizes (1) color contrast of the cable region and the background, (2) the new area-based coordinate system to compute spatial features, and (3) the history of locations of detected cables of the instrument in a video to discard false regions. The proposed technique and software are useful for (1) automatic documentation of diagnostic or therapeutic operations at the end of the procedure, (2) a second review for causes of complications due to these operations, and (3) a building block for an effective content-based retrieval system to facilitate endoscopic research and education. On 38 full-length colonoscopy and upper endoscopy video files with different cable colors and four different insertion directions of the instruments, the average percentage of false positive duration is small at 2.23%. The average percentage of true positive duration is high at 92.9%. The average analysis time per image is 13 milliseconds on an inexpensive off-the-shelf PC.",

keywords = "Colonoscopy, Image analysis, Image features, Instruments, Polypectomy",

author = "Chuanhai Zhang and Wallapak Tavanapong and Johnny Wong and {De Groen}, {Piet C.} and Oh, {Jung Hwan}",

note = "Publisher Copyright: {\textcopyright} International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015.All right reserved.; 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015, at WORLDCOMP 2015 ; Conference date: 27-07-2015 Through 30-07-2015",

year = "2015",

language = "English (US)",

series = "Proceedings of the 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015",

publisher = "CSREA Press",

pages = "308--314",

editor = "Arabnia, {Hamid R.} and Leonidas Deligiannidis and Tinetti, {Fernando G.} and George Jandieri and Gerald Schaefer and Solo, {Ashu M. G.}",

booktitle = "Proceedings of the 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015",

}

TY - GEN

T1 - Cable footprint history

T2 - 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015, at WORLDCOMP 2015

AU - Zhang, Chuanhai

AU - Tavanapong, Wallapak

AU - Wong, Johnny

AU - De Groen, Piet C.

AU - Oh, Jung Hwan

PY - 2015

Y1 - 2015

N2 - We propose a new fast spatio-temporal technique that detects an operation scene-a video segment corresponding to a single purpose diagnosis action or a single purpose therapeutic action. The technique utilizes (1) color contrast of the cable region and the background, (2) the new area-based coordinate system to compute spatial features, and (3) the history of locations of detected cables of the instrument in a video to discard false regions. The proposed technique and software are useful for (1) automatic documentation of diagnostic or therapeutic operations at the end of the procedure, (2) a second review for causes of complications due to these operations, and (3) a building block for an effective content-based retrieval system to facilitate endoscopic research and education. On 38 full-length colonoscopy and upper endoscopy video files with different cable colors and four different insertion directions of the instruments, the average percentage of false positive duration is small at 2.23%. The average percentage of true positive duration is high at 92.9%. The average analysis time per image is 13 milliseconds on an inexpensive off-the-shelf PC.

AB - We propose a new fast spatio-temporal technique that detects an operation scene-a video segment corresponding to a single purpose diagnosis action or a single purpose therapeutic action. The technique utilizes (1) color contrast of the cable region and the background, (2) the new area-based coordinate system to compute spatial features, and (3) the history of locations of detected cables of the instrument in a video to discard false regions. The proposed technique and software are useful for (1) automatic documentation of diagnostic or therapeutic operations at the end of the procedure, (2) a second review for causes of complications due to these operations, and (3) a building block for an effective content-based retrieval system to facilitate endoscopic research and education. On 38 full-length colonoscopy and upper endoscopy video files with different cable colors and four different insertion directions of the instruments, the average percentage of false positive duration is small at 2.23%. The average percentage of true positive duration is high at 92.9%. The average analysis time per image is 13 milliseconds on an inexpensive off-the-shelf PC.

KW - Colonoscopy

KW - Image analysis

KW - Image features

KW - Instruments

KW - Polypectomy

UR - http://www.scopus.com/inward/record.url?scp=85029806883&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029806883&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85029806883

T3 - Proceedings of the 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015

SP - 308

EP - 314

BT - Proceedings of the 2015 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2015

A2 - Arabnia, Hamid R.

A2 - Deligiannidis, Leonidas

A2 - Tinetti, Fernando G.

A2 - Jandieri, George

A2 - Schaefer, Gerald

A2 - Solo, Ashu M. G.

PB - CSREA Press

Y2 - 27 July 2015 through 30 July 2015

ER -

Cable footprint history: Spatio-temporal technique for instrument detection in gastrointestinal endoscopic procedures

Abstract

Publication series

Conference

Bibliographical note

Keywords

OpenUrl availability

Other files and links

Fingerprint

Cite this