Video-specific SVMs for colonoscopy image classification

Siyamalan Manivannan; Ruixuan Wang; Maria P. Trujillo; Jesus Arbey Hoyos; Emanuele Trucco

doi:10.1007/978-3-319-13410-9_2

Video-specific SVMs for colonoscopy image classification

Siyamalan Manivannan (Lead / Corresponding author), Ruixuan Wang, Maria P. Trujillo, Jesus Arbey Hoyos, Emanuele Trucco

Computing

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

2 Citations (Scopus)

Abstract

We propose a novel classification framework called the videospecific SVM (V-SVM) for normal-vs-abnormal white-light colonoscopy image classification. V-SVM is an ensemble of linear SVMs, with each trained to separate the abnormal images in a particular video from all the normal images in all the videos. Since V-SVM is designed to capture lesion-specific properties as well as intra-class variations it is expected to perform better than SVM. Experiments on a colonoscopy image dataset with about 10,000 images show that V-SVM significantly improves the performance over SVM and other baseline classifiers.

Original language	English
Title of host publication	Computer-Assisted and Robotic Endoscopy
Subtitle of host publication	First International Workshop, CARE 2014, held in conjunction with MICCAI 2014, Boston, MA, USA, September 18, 2014. Revised selected papers
Editors	Xiongbiao Luo, Tobias Reichl , Daniel Mirota, Timothy Soper
Publisher	Springer International Publishing
Pages	11-21
Number of pages	11
ISBN (Electronic)	9783319134109
ISBN (Print)	9783319134093
DOIs	https://doi.org/10.1007/978-3-319-13410-9_2
Publication status	Published - 23 Nov 2014
Event	1st International Workshop on Computer-Assisted and Robotic Endoscopy - MIT Campus and at Harvard Medical School, Boston, United States Duration: 18 Sept 2014 → … http://care2014.imaging.robarts.ca/

Publication series

Name	Lecture notes in computer science
Publisher	Springer
Volume	8899
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Workshop

Workshop	1st International Workshop on Computer-Assisted and Robotic Endoscopy
Abbreviated title	CARE 2014
Country/Territory	United States
City	Boston
Period	18/09/14 → …
Other	Held in Conjunction with MICCAI 2014
Internet address	http://care2014.imaging.robarts.ca/

ASJC Scopus subject areas

General Computer Science
Theoretical Computer Science

Access to Document

10.1007/978-3-319-13410-9_2

Cite this

Manivannan, S., Wang, R., Trujillo, M. P., Hoyos, J. A., & Trucco, E. (2014). Video-specific SVMs for colonoscopy image classification. In X. Luo, T. Reichl , D. Mirota, & T. Soper (Eds.), Computer-Assisted and Robotic Endoscopy: First International Workshop, CARE 2014, held in conjunction with MICCAI 2014, Boston, MA, USA, September 18, 2014. Revised selected papers (pp. 11-21). (Lecture notes in computer science ; Vol. 8899). Springer International Publishing. https://doi.org/10.1007/978-3-319-13410-9_2

Manivannan, Siyamalan ; Wang, Ruixuan ; Trujillo, Maria P. et al. / Video-specific SVMs for colonoscopy image classification. Computer-Assisted and Robotic Endoscopy: First International Workshop, CARE 2014, held in conjunction with MICCAI 2014, Boston, MA, USA, September 18, 2014. Revised selected papers. editor / Xiongbiao Luo ; Tobias Reichl ; Daniel Mirota ; Timothy Soper. Springer International Publishing, 2014. pp. 11-21 (Lecture notes in computer science ).

@inproceedings{6c0fd2b775c542c9b85d09a384d0c730,

title = "Video-specific SVMs for colonoscopy image classification",

abstract = "We propose a novel classification framework called the videospecific SVM (V-SVM) for normal-vs-abnormal white-light colonoscopy image classification. V-SVM is an ensemble of linear SVMs, with each trained to separate the abnormal images in a particular video from all the normal images in all the videos. Since V-SVM is designed to capture lesion-specific properties as well as intra-class variations it is expected to perform better than SVM. Experiments on a colonoscopy image dataset with about 10,000 images show that V-SVM significantly improves the performance over SVM and other baseline classifiers.",

author = "Siyamalan Manivannan and Ruixuan Wang and Trujillo, {Maria P.} and Hoyos, {Jesus Arbey} and Emanuele Trucco",

year = "2014",

month = nov,

day = "23",

doi = "10.1007/978-3-319-13410-9_2",

language = "English",

isbn = "9783319134093",

series = "Lecture notes in computer science ",

publisher = "Springer International Publishing",

pages = "11--21",

editor = "Xiongbiao Luo and {Reichl }, Tobias and Mirota, {Daniel } and Timothy Soper",

booktitle = "Computer-Assisted and Robotic Endoscopy",

address = "Switzerland",

note = "1st International Workshop on Computer-Assisted and Robotic Endoscopy, CARE 2014 ; Conference date: 18-09-2014",

url = "http://care2014.imaging.robarts.ca/",

}

Manivannan, S, Wang, R, Trujillo, MP, Hoyos, JA & Trucco, E 2014, Video-specific SVMs for colonoscopy image classification. in X Luo, T Reichl , D Mirota & T Soper (eds), Computer-Assisted and Robotic Endoscopy: First International Workshop, CARE 2014, held in conjunction with MICCAI 2014, Boston, MA, USA, September 18, 2014. Revised selected papers. Lecture notes in computer science , vol. 8899, Springer International Publishing, pp. 11-21, 1st International Workshop on Computer-Assisted and Robotic Endoscopy, Boston, United States, 18/09/14. https://doi.org/10.1007/978-3-319-13410-9_2

Video-specific SVMs for colonoscopy image classification. / Manivannan, Siyamalan (Lead / Corresponding author); Wang, Ruixuan; Trujillo, Maria P. et al.
Computer-Assisted and Robotic Endoscopy: First International Workshop, CARE 2014, held in conjunction with MICCAI 2014, Boston, MA, USA, September 18, 2014. Revised selected papers. ed. / Xiongbiao Luo; Tobias Reichl ; Daniel Mirota; Timothy Soper. Springer International Publishing, 2014. p. 11-21 (Lecture notes in computer science ; Vol. 8899).

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

TY - GEN

T1 - Video-specific SVMs for colonoscopy image classification

AU - Manivannan, Siyamalan

AU - Wang, Ruixuan

AU - Trujillo, Maria P.

AU - Hoyos, Jesus Arbey

AU - Trucco, Emanuele

PY - 2014/11/23

Y1 - 2014/11/23

N2 - We propose a novel classification framework called the videospecific SVM (V-SVM) for normal-vs-abnormal white-light colonoscopy image classification. V-SVM is an ensemble of linear SVMs, with each trained to separate the abnormal images in a particular video from all the normal images in all the videos. Since V-SVM is designed to capture lesion-specific properties as well as intra-class variations it is expected to perform better than SVM. Experiments on a colonoscopy image dataset with about 10,000 images show that V-SVM significantly improves the performance over SVM and other baseline classifiers.

AB - We propose a novel classification framework called the videospecific SVM (V-SVM) for normal-vs-abnormal white-light colonoscopy image classification. V-SVM is an ensemble of linear SVMs, with each trained to separate the abnormal images in a particular video from all the normal images in all the videos. Since V-SVM is designed to capture lesion-specific properties as well as intra-class variations it is expected to perform better than SVM. Experiments on a colonoscopy image dataset with about 10,000 images show that V-SVM significantly improves the performance over SVM and other baseline classifiers.

UR - http://www.scopus.com/inward/record.url?scp=84912060884&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-13410-9_2

DO - 10.1007/978-3-319-13410-9_2

M3 - Conference contribution

AN - SCOPUS:84912060884

SN - 9783319134093

T3 - Lecture notes in computer science

SP - 11

EP - 21

BT - Computer-Assisted and Robotic Endoscopy

A2 - Luo, Xiongbiao

A2 - Reichl , Tobias

A2 - Mirota, Daniel

A2 - Soper, Timothy

PB - Springer International Publishing

T2 - 1st International Workshop on Computer-Assisted and Robotic Endoscopy

Y2 - 18 September 2014

ER -

Manivannan S, Wang R, Trujillo MP, Hoyos JA, Trucco E. Video-specific SVMs for colonoscopy image classification. In Luo X, Reichl T, Mirota D, Soper T, editors, Computer-Assisted and Robotic Endoscopy: First International Workshop, CARE 2014, held in conjunction with MICCAI 2014, Boston, MA, USA, September 18, 2014. Revised selected papers. Springer International Publishing. 2014. p. 11-21. (Lecture notes in computer science ). doi: 10.1007/978-3-319-13410-9_2

Video-specific SVMs for colonoscopy image classification

Abstract

Publication series

Workshop

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this