Extended multi-resolution local patterns - A discriminative feature learning approach for colonoscopy image classification

Siyamalan Manivannan; Manuel Trucco

doi:10.1007/978-3-319-54057-3_5

Extended multi-resolution local patterns - A discriminative feature learning approach for colonoscopy image classification

Siyamalan Manivannan (Lead / Corresponding author)
, Manuel Trucco

SCI Computing

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

Abstract

We propose a novel local image descriptor called the Extended Multi-resolution Local Patterns, and a discriminative probabilistic framework for learning its parameters together with a multi-class image classifier. Our approach uses training data with image-level labels to learn the features which are discriminative for multi-class colonoscopy image classification. Experiments on a three class (abnormal, normal, uninformative) white-light colonoscopy image dataset with 2800 images show that the proposed feature perform better than popular hand- designed features used in the medical as well as in the computer vision literature for image classification.

Original language	English
Title of host publication	CARE 2016
Subtitle of host publication	Computer-Assisted and Robotic Endoscopy
Editors	Guang-Zhong Yang, Nassir Navab, Jonathan McLeod, Terry Peters, Kensaku Mori, Xiongbiao Luo, Tobias Reichl
Place of Publication	Switzerland
Publisher	Springer
Pages	48-58
Number of pages	11
Volume	10170
ISBN (Electronic)	9783319540573
ISBN (Print)	9783319540566
DOIs	https://doi.org/10.1007/978-3-319-54057-3_5
Publication status	Published - 2017
Event	2nd International Workshop on Patch-Based Techniques in Medical Imaging, Patch-MI 2016 held in conjunction with 19th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2016 - Athens, Greece Duration: 17 Oct 2016 → 17 Oct 2016

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	10170
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	2nd International Workshop on Patch-Based Techniques in Medical Imaging, Patch-MI 2016 held in conjunction with 19th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2016
Country/Territory	Greece
City	Athens
Period	17/10/16 → 17/10/16

Keywords

Local Binary Pattern
Adenoma Detection Rate
Local Ternary Pattern
Soft Label
Colon Dataset

ASJC Scopus subject areas

Theoretical Computer Science
General Computer Science

Access to Document

10.1007/978-3-319-54057-3_5

Cite this

Manivannan, S., & Trucco, M. (2017). Extended multi-resolution local patterns - A discriminative feature learning approach for colonoscopy image classification. In G.-Z. Yang, N. Navab, J. McLeod, T. Peters, K. Mori, X. Luo, & T. Reichl (Eds.), CARE 2016: Computer-Assisted and Robotic Endoscopy (Vol. 10170, pp. 48-58). (Lecture Notes in Computer Science; Vol. 10170). Springer . https://doi.org/10.1007/978-3-319-54057-3_5

Manivannan, Siyamalan ; Trucco, Manuel. / Extended multi-resolution local patterns - A discriminative feature learning approach for colonoscopy image classification. CARE 2016: Computer-Assisted and Robotic Endoscopy. editor / Guang-Zhong Yang ; Nassir Navab ; Jonathan McLeod ; Terry Peters ; Kensaku Mori ; Xiongbiao Luo ; Tobias Reichl. Vol. 10170 Switzerland : Springer , 2017. pp. 48-58 (Lecture Notes in Computer Science).

@inproceedings{67cd74fd48274dc78edf173255645910,

title = "Extended multi-resolution local patterns - A discriminative feature learning approach for colonoscopy image classification",

abstract = "We propose a novel local image descriptor called the Extended Multi-resolution Local Patterns, and a discriminative probabilistic framework for learning its parameters together with a multi-class image classifier. Our approach uses training data with image-level labels to learn the features which are discriminative for multi-class colonoscopy image classification. Experiments on a three class (abnormal, normal, uninformative) white-light colonoscopy image dataset with 2800 images show that the proposed feature perform better than popular hand- designed features used in the medical as well as in the computer vision literature for image classification.",

keywords = "Local Binary Pattern, Adenoma Detection Rate, Local Ternary Pattern, Soft Label, Colon Dataset",

author = "Siyamalan Manivannan and Manuel Trucco",

year = "2017",

doi = "10.1007/978-3-319-54057-3\_5",

language = "English",

isbn = "9783319540566",

volume = "10170",

series = "Lecture Notes in Computer Science",

publisher = "Springer ",

pages = "48--58",

editor = "Guang-Zhong Yang and Nassir Navab and Jonathan McLeod and Terry Peters and Kensaku Mori and Xiongbiao Luo and Tobias Reichl",

booktitle = "CARE 2016",

note = "2nd International Workshop on Patch-Based Techniques in Medical Imaging, Patch-MI 2016 held in conjunction with 19th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2016 ; Conference date: 17-10-2016 Through 17-10-2016",

}

Manivannan, S & Trucco, M 2017, Extended multi-resolution local patterns - A discriminative feature learning approach for colonoscopy image classification. in G-Z Yang, N Navab, J McLeod, T Peters, K Mori, X Luo & T Reichl (eds), CARE 2016: Computer-Assisted and Robotic Endoscopy. vol. 10170, Lecture Notes in Computer Science, vol. 10170, Springer , Switzerland, pp. 48-58, 2nd International Workshop on Patch-Based Techniques in Medical Imaging, Patch-MI 2016 held in conjunction with 19th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2016, Athens, Greece, 17/10/16. https://doi.org/10.1007/978-3-319-54057-3_5

Extended multi-resolution local patterns - A discriminative feature learning approach for colonoscopy image classification. / Manivannan, Siyamalan (Lead / Corresponding author); Trucco, Manuel.
CARE 2016: Computer-Assisted and Robotic Endoscopy. ed. / Guang-Zhong Yang; Nassir Navab; Jonathan McLeod; Terry Peters; Kensaku Mori; Xiongbiao Luo; Tobias Reichl. Vol. 10170 Switzerland: Springer , 2017. p. 48-58 (Lecture Notes in Computer Science; Vol. 10170).

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

TY - GEN

T1 - Extended multi-resolution local patterns - A discriminative feature learning approach for colonoscopy image classification

AU - Manivannan, Siyamalan

AU - Trucco, Manuel

PY - 2017

Y1 - 2017

N2 - We propose a novel local image descriptor called the Extended Multi-resolution Local Patterns, and a discriminative probabilistic framework for learning its parameters together with a multi-class image classifier. Our approach uses training data with image-level labels to learn the features which are discriminative for multi-class colonoscopy image classification. Experiments on a three class (abnormal, normal, uninformative) white-light colonoscopy image dataset with 2800 images show that the proposed feature perform better than popular hand- designed features used in the medical as well as in the computer vision literature for image classification.

AB - We propose a novel local image descriptor called the Extended Multi-resolution Local Patterns, and a discriminative probabilistic framework for learning its parameters together with a multi-class image classifier. Our approach uses training data with image-level labels to learn the features which are discriminative for multi-class colonoscopy image classification. Experiments on a three class (abnormal, normal, uninformative) white-light colonoscopy image dataset with 2800 images show that the proposed feature perform better than popular hand- designed features used in the medical as well as in the computer vision literature for image classification.

KW - Local Binary Pattern

KW - Adenoma Detection Rate

KW - Local Ternary Pattern

KW - Soft Label

KW - Colon Dataset

UR - https://www.scopus.com/pages/publications/85013941300

U2 - 10.1007/978-3-319-54057-3_5

DO - 10.1007/978-3-319-54057-3_5

M3 - Conference contribution

AN - SCOPUS:85013941300

SN - 9783319540566

VL - 10170

T3 - Lecture Notes in Computer Science

SP - 48

EP - 58

BT - CARE 2016

A2 - Yang, Guang-Zhong

A2 - Navab, Nassir

A2 - McLeod, Jonathan

A2 - Peters, Terry

A2 - Mori, Kensaku

A2 - Luo, Xiongbiao

A2 - Reichl, Tobias

PB - Springer

CY - Switzerland

T2 - 2nd International Workshop on Patch-Based Techniques in Medical Imaging, Patch-MI 2016 held in conjunction with 19th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2016

Y2 - 17 October 2016 through 17 October 2016

ER -

Manivannan S, Trucco M. Extended multi-resolution local patterns - A discriminative feature learning approach for colonoscopy image classification. In Yang GZ, Navab N, McLeod J, Peters T, Mori K, Luo X, Reichl T, editors, CARE 2016: Computer-Assisted and Robotic Endoscopy. Vol. 10170. Switzerland: Springer . 2017. p. 48-58. (Lecture Notes in Computer Science). Epub 2017 Feb 22. doi: 10.1007/978-3-319-54057-3_5

Extended multi-resolution local patterns - A discriminative feature learning approach for colonoscopy image classification

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Multi-modal Retinal Biomarkers for Vascular Dementia; Developing and Enabling Image Analysis Tools (Joint with University of Edinburgh)

Cite this

Extended multi-resolution local patterns - A discriminative feature learning approach for colonoscopy image classification

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Projects

Multi-modal Retinal Biomarkers for Vascular Dementia; Developing and Enabling Image Analysis Tools (Joint with University of Edinburgh)

Cite this