A framework for parsing colonoscopy videos for semantic units

Yu Cao, Wallapak Tavanapong, Kihwan Kim, Johnny Wong, JungHwan Oh, Piet C. De Groen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

Colonoscopy is an important screening procedure for colorectal cancer. During this procedure, the endoscopist visually inspects the colon. Currently, there is no content-based analysis and retrieval system that automatically analyzes videos captured from colonoscopic procedures and provides a user-friendly and efficient access to important content. Such a system will be valuable for endoscopic research and education. The first necessary step for the analysis is parsing for semantic units. Since the characteristics of colonoscopy videos differ from those of videos studied in the literature, we introduce a new video parsing framework that includes (i) a new scene definition and a new video parsing paradigm and (ii) a novel scene segmentation algorithm using audio analysis and finite state automata to recognize scenes and associated boundaries. Our experimental results show average precision and recall of 95% and 81 % for parsing scenes, respectively. The framework is extensible to videos captured from other endoscopic procedures such as upper gastrointestinal endoscopy, enteroscopy, cystoscopy, and laparoscopy.

Original languageEnglish (US)
Title of host publication2004 IEEE International Conference on Multimedia and Expo (ICME)
Pages1879-1882
Number of pages4
Volume3
StatePublished - 2004
Event2004 IEEE International Conference on Multimedia and Expo (ICME) - Taipei, Taiwan, Province of China
Duration: Jun 27 2004Jun 30 2004

Other

Other2004 IEEE International Conference on Multimedia and Expo (ICME)
CountryTaiwan, Province of China
CityTaipei
Period6/27/046/30/04

Fingerprint

Laparoscopy
Endoscopy
Finite automata
Screening
Education
Semantics

Keywords

  • Content-based analysis
  • Medical image processing
  • Scene segmentation

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Cao, Y., Tavanapong, W., Kim, K., Wong, J., Oh, J., & De Groen, P. C. (2004). A framework for parsing colonoscopy videos for semantic units. In 2004 IEEE International Conference on Multimedia and Expo (ICME) (Vol. 3, pp. 1879-1882)

A framework for parsing colonoscopy videos for semantic units. / Cao, Yu; Tavanapong, Wallapak; Kim, Kihwan; Wong, Johnny; Oh, JungHwan; De Groen, Piet C.

2004 IEEE International Conference on Multimedia and Expo (ICME). Vol. 3 2004. p. 1879-1882.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Cao, Y, Tavanapong, W, Kim, K, Wong, J, Oh, J & De Groen, PC 2004, A framework for parsing colonoscopy videos for semantic units. in 2004 IEEE International Conference on Multimedia and Expo (ICME). vol. 3, pp. 1879-1882, 2004 IEEE International Conference on Multimedia and Expo (ICME), Taipei, Taiwan, Province of China, 6/27/04.
Cao Y, Tavanapong W, Kim K, Wong J, Oh J, De Groen PC. A framework for parsing colonoscopy videos for semantic units. In 2004 IEEE International Conference on Multimedia and Expo (ICME). Vol. 3. 2004. p. 1879-1882
Cao, Yu ; Tavanapong, Wallapak ; Kim, Kihwan ; Wong, Johnny ; Oh, JungHwan ; De Groen, Piet C. / A framework for parsing colonoscopy videos for semantic units. 2004 IEEE International Conference on Multimedia and Expo (ICME). Vol. 3 2004. pp. 1879-1882
@inproceedings{a097623bcb414c25ba1853e7cbd40dfb,
title = "A framework for parsing colonoscopy videos for semantic units",
abstract = "Colonoscopy is an important screening procedure for colorectal cancer. During this procedure, the endoscopist visually inspects the colon. Currently, there is no content-based analysis and retrieval system that automatically analyzes videos captured from colonoscopic procedures and provides a user-friendly and efficient access to important content. Such a system will be valuable for endoscopic research and education. The first necessary step for the analysis is parsing for semantic units. Since the characteristics of colonoscopy videos differ from those of videos studied in the literature, we introduce a new video parsing framework that includes (i) a new scene definition and a new video parsing paradigm and (ii) a novel scene segmentation algorithm using audio analysis and finite state automata to recognize scenes and associated boundaries. Our experimental results show average precision and recall of 95{\%} and 81 {\%} for parsing scenes, respectively. The framework is extensible to videos captured from other endoscopic procedures such as upper gastrointestinal endoscopy, enteroscopy, cystoscopy, and laparoscopy.",
keywords = "Content-based analysis, Medical image processing, Scene segmentation",
author = "Yu Cao and Wallapak Tavanapong and Kihwan Kim and Johnny Wong and JungHwan Oh and {De Groen}, {Piet C.}",
year = "2004",
language = "English (US)",
isbn = "0780386035",
volume = "3",
pages = "1879--1882",
booktitle = "2004 IEEE International Conference on Multimedia and Expo (ICME)",

}

TY - GEN

T1 - A framework for parsing colonoscopy videos for semantic units

AU - Cao, Yu

AU - Tavanapong, Wallapak

AU - Kim, Kihwan

AU - Wong, Johnny

AU - Oh, JungHwan

AU - De Groen, Piet C.

PY - 2004

Y1 - 2004

N2 - Colonoscopy is an important screening procedure for colorectal cancer. During this procedure, the endoscopist visually inspects the colon. Currently, there is no content-based analysis and retrieval system that automatically analyzes videos captured from colonoscopic procedures and provides a user-friendly and efficient access to important content. Such a system will be valuable for endoscopic research and education. The first necessary step for the analysis is parsing for semantic units. Since the characteristics of colonoscopy videos differ from those of videos studied in the literature, we introduce a new video parsing framework that includes (i) a new scene definition and a new video parsing paradigm and (ii) a novel scene segmentation algorithm using audio analysis and finite state automata to recognize scenes and associated boundaries. Our experimental results show average precision and recall of 95% and 81 % for parsing scenes, respectively. The framework is extensible to videos captured from other endoscopic procedures such as upper gastrointestinal endoscopy, enteroscopy, cystoscopy, and laparoscopy.

AB - Colonoscopy is an important screening procedure for colorectal cancer. During this procedure, the endoscopist visually inspects the colon. Currently, there is no content-based analysis and retrieval system that automatically analyzes videos captured from colonoscopic procedures and provides a user-friendly and efficient access to important content. Such a system will be valuable for endoscopic research and education. The first necessary step for the analysis is parsing for semantic units. Since the characteristics of colonoscopy videos differ from those of videos studied in the literature, we introduce a new video parsing framework that includes (i) a new scene definition and a new video parsing paradigm and (ii) a novel scene segmentation algorithm using audio analysis and finite state automata to recognize scenes and associated boundaries. Our experimental results show average precision and recall of 95% and 81 % for parsing scenes, respectively. The framework is extensible to videos captured from other endoscopic procedures such as upper gastrointestinal endoscopy, enteroscopy, cystoscopy, and laparoscopy.

KW - Content-based analysis

KW - Medical image processing

KW - Scene segmentation

UR - http://www.scopus.com/inward/record.url?scp=11244281757&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=11244281757&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:11244281757

SN - 0780386035

SN - 9780780386037

VL - 3

SP - 1879

EP - 1882

BT - 2004 IEEE International Conference on Multimedia and Expo (ICME)

ER -