Polyp-Alert: Near real-time feedback during colonoscopy

Yi Wang, Wallapak Tavanapong, Johnny Wong, Jung Hwan Oh, Piet C. de Groen

Research output: Contribution to journalArticle

35 Citations (Scopus)

Abstract

We present a software system called "Polyp-Alert" to assist the endoscopist find polyps by providing visual feedback during colonoscopy. Polyp-Alert employs our previous edge-cross-section visual features and a rule-based classifier to detect a polyp edge-an edge along the contour of a polyp. The technique employs tracking of detected polyp edge(s) to group a sequence of images covering the same polyp(s) as one polyp shot. In our experiments, the software correctly detected 97.7% (42 of 43) of polyp shots on 53 randomly selected video files of entire colonoscopy procedures. However, Polyp-Alert incorrectly marked only 4.3% of a full-length colonoscopy procedure as showing a polyp when they do not. The test data set consists of about 18. h worth of video data from Olympus and Fujinon endoscopes. The technique is extensible to other brands of colonoscopes. Furthermore, Polyp-Alert can provide as high as ten feedbacks per second for a smooth display of feedback. The performance of our system is by far the most promising to potentially assist the endoscopist find more polyps in clinical practice during a routine screening colonoscopy.

Original languageEnglish (US)
Pages (from-to)164-179
Number of pages16
JournalComputer Methods and Programs in Biomedicine
Volume120
Issue number3
DOIs
StatePublished - Jul 1 2015

Fingerprint

Colonoscopy
Polyps
Feedback
Endoscopy
Screening
Classifiers
Display devices
Experiments
Software
Colonoscopes
Sensory Feedback
Endoscopes

Keywords

  • Colonoscopy
  • Medical imaging/video
  • Near Real-time
  • Polyp detection

ASJC Scopus subject areas

  • Computer Science Applications
  • Software
  • Health Informatics

Cite this

Wang, Y., Tavanapong, W., Wong, J., Oh, J. H., & de Groen, P. C. (2015). Polyp-Alert: Near real-time feedback during colonoscopy. Computer Methods and Programs in Biomedicine, 120(3), 164-179. https://doi.org/10.1016/j.cmpb.2015.04.002

Polyp-Alert : Near real-time feedback during colonoscopy. / Wang, Yi; Tavanapong, Wallapak; Wong, Johnny; Oh, Jung Hwan; de Groen, Piet C.

In: Computer Methods and Programs in Biomedicine, Vol. 120, No. 3, 01.07.2015, p. 164-179.

Research output: Contribution to journalArticle

Wang, Y, Tavanapong, W, Wong, J, Oh, JH & de Groen, PC 2015, 'Polyp-Alert: Near real-time feedback during colonoscopy', Computer Methods and Programs in Biomedicine, vol. 120, no. 3, pp. 164-179. https://doi.org/10.1016/j.cmpb.2015.04.002
Wang, Yi ; Tavanapong, Wallapak ; Wong, Johnny ; Oh, Jung Hwan ; de Groen, Piet C. / Polyp-Alert : Near real-time feedback during colonoscopy. In: Computer Methods and Programs in Biomedicine. 2015 ; Vol. 120, No. 3. pp. 164-179.
@article{a0d595b0139d45a9b850eab7d2530535,
title = "Polyp-Alert: Near real-time feedback during colonoscopy",
abstract = "We present a software system called {"}Polyp-Alert{"} to assist the endoscopist find polyps by providing visual feedback during colonoscopy. Polyp-Alert employs our previous edge-cross-section visual features and a rule-based classifier to detect a polyp edge-an edge along the contour of a polyp. The technique employs tracking of detected polyp edge(s) to group a sequence of images covering the same polyp(s) as one polyp shot. In our experiments, the software correctly detected 97.7{\%} (42 of 43) of polyp shots on 53 randomly selected video files of entire colonoscopy procedures. However, Polyp-Alert incorrectly marked only 4.3{\%} of a full-length colonoscopy procedure as showing a polyp when they do not. The test data set consists of about 18. h worth of video data from Olympus and Fujinon endoscopes. The technique is extensible to other brands of colonoscopes. Furthermore, Polyp-Alert can provide as high as ten feedbacks per second for a smooth display of feedback. The performance of our system is by far the most promising to potentially assist the endoscopist find more polyps in clinical practice during a routine screening colonoscopy.",
keywords = "Colonoscopy, Medical imaging/video, Near Real-time, Polyp detection",
author = "Yi Wang and Wallapak Tavanapong and Johnny Wong and Oh, {Jung Hwan} and {de Groen}, {Piet C.}",
year = "2015",
month = "7",
day = "1",
doi = "10.1016/j.cmpb.2015.04.002",
language = "English (US)",
volume = "120",
pages = "164--179",
journal = "Computer Methods and Programs in Biomedicine",
issn = "0169-2607",
publisher = "Elsevier Ireland Ltd",
number = "3",

}

TY - JOUR

T1 - Polyp-Alert

T2 - Near real-time feedback during colonoscopy

AU - Wang, Yi

AU - Tavanapong, Wallapak

AU - Wong, Johnny

AU - Oh, Jung Hwan

AU - de Groen, Piet C.

PY - 2015/7/1

Y1 - 2015/7/1

N2 - We present a software system called "Polyp-Alert" to assist the endoscopist find polyps by providing visual feedback during colonoscopy. Polyp-Alert employs our previous edge-cross-section visual features and a rule-based classifier to detect a polyp edge-an edge along the contour of a polyp. The technique employs tracking of detected polyp edge(s) to group a sequence of images covering the same polyp(s) as one polyp shot. In our experiments, the software correctly detected 97.7% (42 of 43) of polyp shots on 53 randomly selected video files of entire colonoscopy procedures. However, Polyp-Alert incorrectly marked only 4.3% of a full-length colonoscopy procedure as showing a polyp when they do not. The test data set consists of about 18. h worth of video data from Olympus and Fujinon endoscopes. The technique is extensible to other brands of colonoscopes. Furthermore, Polyp-Alert can provide as high as ten feedbacks per second for a smooth display of feedback. The performance of our system is by far the most promising to potentially assist the endoscopist find more polyps in clinical practice during a routine screening colonoscopy.

AB - We present a software system called "Polyp-Alert" to assist the endoscopist find polyps by providing visual feedback during colonoscopy. Polyp-Alert employs our previous edge-cross-section visual features and a rule-based classifier to detect a polyp edge-an edge along the contour of a polyp. The technique employs tracking of detected polyp edge(s) to group a sequence of images covering the same polyp(s) as one polyp shot. In our experiments, the software correctly detected 97.7% (42 of 43) of polyp shots on 53 randomly selected video files of entire colonoscopy procedures. However, Polyp-Alert incorrectly marked only 4.3% of a full-length colonoscopy procedure as showing a polyp when they do not. The test data set consists of about 18. h worth of video data from Olympus and Fujinon endoscopes. The technique is extensible to other brands of colonoscopes. Furthermore, Polyp-Alert can provide as high as ten feedbacks per second for a smooth display of feedback. The performance of our system is by far the most promising to potentially assist the endoscopist find more polyps in clinical practice during a routine screening colonoscopy.

KW - Colonoscopy

KW - Medical imaging/video

KW - Near Real-time

KW - Polyp detection

UR - http://www.scopus.com/inward/record.url?scp=84929963303&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84929963303&partnerID=8YFLogxK

U2 - 10.1016/j.cmpb.2015.04.002

DO - 10.1016/j.cmpb.2015.04.002

M3 - Article

C2 - 25952076

AN - SCOPUS:84929963303

VL - 120

SP - 164

EP - 179

JO - Computer Methods and Programs in Biomedicine

JF - Computer Methods and Programs in Biomedicine

SN - 0169-2607

IS - 3

ER -