Evaluation and comparison of textural feature representation for the detection of early stage cancer in endoscopy

A.A.A. Setio, F. Sommen, van der, S. Zinger, E.J. Schoon, P.H.N. With, de

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

5 Citations (Scopus)
3 Downloads (Pure)

Abstract

Esophageal cancer is the fastest rising type of cancer in the Western world. The novel technology of High Definition (HD) endoscopy enables physicians to find texture patterns related to early cancer. It encourages the development of a Computer-Aided Decision (CAD) system in order to help physicians with faster identification of early cancer and decrease the miss rate. However, an appropriate texture feature extraction, which is needed for classification, has not been studied yet. In this paper, we compare several techniques for texture feature extraction, including co-occurrence matrix features, LBP and Gabor features and evaluate their performance in detecting early stage cancer in HD endoscopic images. In order to exploit more image characteristics, we introduce an efficient combination of the texture and color features. Furthermore, we add a specific preprocessing step designed for endoscopy images, which improves the classification accuracy. After reducing the feature dimensionality using Principal Component Analysis (PCA), we classify selected features with a Support Vector Machine (SVM). The experimental results validated by an expert gastroenterologist show that the proposed feature extraction is promising and reaches a classification accuracy up to 96.48%.
Original languageEnglish
Title of host publicationProceedings of the 8th International Conference on Computer Vision Theory and Applications (VISAPP'13), 21-24 February 2013, Barcelona, Spain
Place of PublicationSetubal
PublisherINSTICC Press
DOIs
Publication statusPublished - 2013

Fingerprint

Endoscopy
Textures
Feature extraction
Principal component analysis
Support vector machines
Color

Cite this

Setio, A. A. A., Sommen, van der, F., Zinger, S., Schoon, E. J., & With, de, P. H. N. (2013). Evaluation and comparison of textural feature representation for the detection of early stage cancer in endoscopy. In Proceedings of the 8th International Conference on Computer Vision Theory and Applications (VISAPP'13), 21-24 February 2013, Barcelona, Spain Setubal: INSTICC Press. https://doi.org/10.5220/0004204502380243
Setio, A.A.A. ; Sommen, van der, F. ; Zinger, S. ; Schoon, E.J. ; With, de, P.H.N. / Evaluation and comparison of textural feature representation for the detection of early stage cancer in endoscopy. Proceedings of the 8th International Conference on Computer Vision Theory and Applications (VISAPP'13), 21-24 February 2013, Barcelona, Spain. Setubal : INSTICC Press, 2013.
@inproceedings{4cc029e6a4874ff085d4dc5c466bbf1c,
title = "Evaluation and comparison of textural feature representation for the detection of early stage cancer in endoscopy",
abstract = "Esophageal cancer is the fastest rising type of cancer in the Western world. The novel technology of High Definition (HD) endoscopy enables physicians to find texture patterns related to early cancer. It encourages the development of a Computer-Aided Decision (CAD) system in order to help physicians with faster identification of early cancer and decrease the miss rate. However, an appropriate texture feature extraction, which is needed for classification, has not been studied yet. In this paper, we compare several techniques for texture feature extraction, including co-occurrence matrix features, LBP and Gabor features and evaluate their performance in detecting early stage cancer in HD endoscopic images. In order to exploit more image characteristics, we introduce an efficient combination of the texture and color features. Furthermore, we add a specific preprocessing step designed for endoscopy images, which improves the classification accuracy. After reducing the feature dimensionality using Principal Component Analysis (PCA), we classify selected features with a Support Vector Machine (SVM). The experimental results validated by an expert gastroenterologist show that the proposed feature extraction is promising and reaches a classification accuracy up to 96.48{\%}.",
author = "A.A.A. Setio and {Sommen, van der}, F. and S. Zinger and E.J. Schoon and {With, de}, P.H.N.",
year = "2013",
doi = "10.5220/0004204502380243",
language = "English",
booktitle = "Proceedings of the 8th International Conference on Computer Vision Theory and Applications (VISAPP'13), 21-24 February 2013, Barcelona, Spain",
publisher = "INSTICC Press",

}

Setio, AAA, Sommen, van der, F, Zinger, S, Schoon, EJ & With, de, PHN 2013, Evaluation and comparison of textural feature representation for the detection of early stage cancer in endoscopy. in Proceedings of the 8th International Conference on Computer Vision Theory and Applications (VISAPP'13), 21-24 February 2013, Barcelona, Spain. INSTICC Press, Setubal. https://doi.org/10.5220/0004204502380243

Evaluation and comparison of textural feature representation for the detection of early stage cancer in endoscopy. / Setio, A.A.A.; Sommen, van der, F.; Zinger, S.; Schoon, E.J.; With, de, P.H.N.

Proceedings of the 8th International Conference on Computer Vision Theory and Applications (VISAPP'13), 21-24 February 2013, Barcelona, Spain. Setubal : INSTICC Press, 2013.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Evaluation and comparison of textural feature representation for the detection of early stage cancer in endoscopy

AU - Setio, A.A.A.

AU - Sommen, van der, F.

AU - Zinger, S.

AU - Schoon, E.J.

AU - With, de, P.H.N.

PY - 2013

Y1 - 2013

N2 - Esophageal cancer is the fastest rising type of cancer in the Western world. The novel technology of High Definition (HD) endoscopy enables physicians to find texture patterns related to early cancer. It encourages the development of a Computer-Aided Decision (CAD) system in order to help physicians with faster identification of early cancer and decrease the miss rate. However, an appropriate texture feature extraction, which is needed for classification, has not been studied yet. In this paper, we compare several techniques for texture feature extraction, including co-occurrence matrix features, LBP and Gabor features and evaluate their performance in detecting early stage cancer in HD endoscopic images. In order to exploit more image characteristics, we introduce an efficient combination of the texture and color features. Furthermore, we add a specific preprocessing step designed for endoscopy images, which improves the classification accuracy. After reducing the feature dimensionality using Principal Component Analysis (PCA), we classify selected features with a Support Vector Machine (SVM). The experimental results validated by an expert gastroenterologist show that the proposed feature extraction is promising and reaches a classification accuracy up to 96.48%.

AB - Esophageal cancer is the fastest rising type of cancer in the Western world. The novel technology of High Definition (HD) endoscopy enables physicians to find texture patterns related to early cancer. It encourages the development of a Computer-Aided Decision (CAD) system in order to help physicians with faster identification of early cancer and decrease the miss rate. However, an appropriate texture feature extraction, which is needed for classification, has not been studied yet. In this paper, we compare several techniques for texture feature extraction, including co-occurrence matrix features, LBP and Gabor features and evaluate their performance in detecting early stage cancer in HD endoscopic images. In order to exploit more image characteristics, we introduce an efficient combination of the texture and color features. Furthermore, we add a specific preprocessing step designed for endoscopy images, which improves the classification accuracy. After reducing the feature dimensionality using Principal Component Analysis (PCA), we classify selected features with a Support Vector Machine (SVM). The experimental results validated by an expert gastroenterologist show that the proposed feature extraction is promising and reaches a classification accuracy up to 96.48%.

U2 - 10.5220/0004204502380243

DO - 10.5220/0004204502380243

M3 - Conference contribution

BT - Proceedings of the 8th International Conference on Computer Vision Theory and Applications (VISAPP'13), 21-24 February 2013, Barcelona, Spain

PB - INSTICC Press

CY - Setubal

ER -

Setio AAA, Sommen, van der F, Zinger S, Schoon EJ, With, de PHN. Evaluation and comparison of textural feature representation for the detection of early stage cancer in endoscopy. In Proceedings of the 8th International Conference on Computer Vision Theory and Applications (VISAPP'13), 21-24 February 2013, Barcelona, Spain. Setubal: INSTICC Press. 2013 https://doi.org/10.5220/0004204502380243