Contourlet Transform for Texture Representation of Ultrasound Thyroid Images

Stamos Katsigiannis, Eystratios G. Keramidas, Dimitris Maroulis

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

Abstract

Texture representation of ultrasound (US) images is currently considered a major issue in medical image analysis. This paper investigates the texture representation of thyroid tissue via features based on the Contourlet Transform (CT) using different types of filter banks. A variety of statistical texture features based on CT coefficients, have been considered through a selection schema. The Sequential Float Feature Selection (SFFS) algorithm with a k-NN classifier has been applied in order to investigate the most representative set of CT features. For the experimental evaluation a set of normal and nodular ultrasound thyroid textures have been utilized. The maximum classification accuracy was 93%, showing that CT based texture features can be successfully applied for the representation of different types of texture in US thyroid images.
Original languageEnglish
Title of host publicationArtificial Intelligence Applications and Innovations
Subtitle of host publication6th IFIP WG 12.5 International Conference, AIAI 2010, Larnaca, Cyprus, October 6-7, 2010. Proceedings
EditorsHarris Papadopoulos, Andreas S. Andreou, Max Bramer
Place of PublicationBerlin, Heidelberg
PublisherSpringer Berlin Heidelberg
Pages138-145
Number of pages8
ISBN (Print)978-3-642-16239-8
DOIs
Publication statusPublished - 2010
Externally publishedYes

Fingerprint

Textures
Ultrasonics
Mathematical transformations
Filter banks
Image analysis
Feature extraction
Classifiers
Tissue

Keywords

  • contourlet transform
  • ultrasound images
  • feature extraction
  • thyroid
  • feature selection

Cite this

Katsigiannis, S., Keramidas, E. G., & Maroulis, D. (2010). Contourlet Transform for Texture Representation of Ultrasound Thyroid Images. In H. Papadopoulos, A. S. Andreou, & M. Bramer (Eds.), Artificial Intelligence Applications and Innovations: 6th IFIP WG 12.5 International Conference, AIAI 2010, Larnaca, Cyprus, October 6-7, 2010. Proceedings (pp. 138-145). Berlin, Heidelberg: Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-642-16239-8_20
Katsigiannis, Stamos ; Keramidas, Eystratios G. ; Maroulis, Dimitris. / Contourlet Transform for Texture Representation of Ultrasound Thyroid Images. Artificial Intelligence Applications and Innovations: 6th IFIP WG 12.5 International Conference, AIAI 2010, Larnaca, Cyprus, October 6-7, 2010. Proceedings. editor / Harris Papadopoulos ; Andreas S. Andreou ; Max Bramer. Berlin, Heidelberg : Springer Berlin Heidelberg, 2010. pp. 138-145
@inproceedings{a86454ace7ae4e3d9d7a6c0e28681056,
title = "Contourlet Transform for Texture Representation of Ultrasound Thyroid Images",
abstract = "Texture representation of ultrasound (US) images is currently considered a major issue in medical image analysis. This paper investigates the texture representation of thyroid tissue via features based on the Contourlet Transform (CT) using different types of filter banks. A variety of statistical texture features based on CT coefficients, have been considered through a selection schema. The Sequential Float Feature Selection (SFFS) algorithm with a k-NN classifier has been applied in order to investigate the most representative set of CT features. For the experimental evaluation a set of normal and nodular ultrasound thyroid textures have been utilized. The maximum classification accuracy was 93{\%}, showing that CT based texture features can be successfully applied for the representation of different types of texture in US thyroid images.",
keywords = "contourlet transform, ultrasound images, feature extraction, thyroid , feature selection",
author = "Stamos Katsigiannis and Keramidas, {Eystratios G.} and Dimitris Maroulis",
year = "2010",
doi = "10.1007/978-3-642-16239-8_20",
language = "English",
isbn = "978-3-642-16239-8",
pages = "138--145",
editor = "Harris Papadopoulos and Andreou, {Andreas S.} and Max Bramer",
booktitle = "Artificial Intelligence Applications and Innovations",
publisher = "Springer Berlin Heidelberg",
address = "Germany",

}

Katsigiannis, S, Keramidas, EG & Maroulis, D 2010, Contourlet Transform for Texture Representation of Ultrasound Thyroid Images. in H Papadopoulos, AS Andreou & M Bramer (eds), Artificial Intelligence Applications and Innovations: 6th IFIP WG 12.5 International Conference, AIAI 2010, Larnaca, Cyprus, October 6-7, 2010. Proceedings. Springer Berlin Heidelberg, Berlin, Heidelberg, pp. 138-145. https://doi.org/10.1007/978-3-642-16239-8_20

Contourlet Transform for Texture Representation of Ultrasound Thyroid Images. / Katsigiannis, Stamos; Keramidas, Eystratios G.; Maroulis, Dimitris.

Artificial Intelligence Applications and Innovations: 6th IFIP WG 12.5 International Conference, AIAI 2010, Larnaca, Cyprus, October 6-7, 2010. Proceedings. ed. / Harris Papadopoulos; Andreas S. Andreou; Max Bramer. Berlin, Heidelberg : Springer Berlin Heidelberg, 2010. p. 138-145.

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

TY - GEN

T1 - Contourlet Transform for Texture Representation of Ultrasound Thyroid Images

AU - Katsigiannis, Stamos

AU - Keramidas, Eystratios G.

AU - Maroulis, Dimitris

PY - 2010

Y1 - 2010

N2 - Texture representation of ultrasound (US) images is currently considered a major issue in medical image analysis. This paper investigates the texture representation of thyroid tissue via features based on the Contourlet Transform (CT) using different types of filter banks. A variety of statistical texture features based on CT coefficients, have been considered through a selection schema. The Sequential Float Feature Selection (SFFS) algorithm with a k-NN classifier has been applied in order to investigate the most representative set of CT features. For the experimental evaluation a set of normal and nodular ultrasound thyroid textures have been utilized. The maximum classification accuracy was 93%, showing that CT based texture features can be successfully applied for the representation of different types of texture in US thyroid images.

AB - Texture representation of ultrasound (US) images is currently considered a major issue in medical image analysis. This paper investigates the texture representation of thyroid tissue via features based on the Contourlet Transform (CT) using different types of filter banks. A variety of statistical texture features based on CT coefficients, have been considered through a selection schema. The Sequential Float Feature Selection (SFFS) algorithm with a k-NN classifier has been applied in order to investigate the most representative set of CT features. For the experimental evaluation a set of normal and nodular ultrasound thyroid textures have been utilized. The maximum classification accuracy was 93%, showing that CT based texture features can be successfully applied for the representation of different types of texture in US thyroid images.

KW - contourlet transform

KW - ultrasound images

KW - feature extraction

KW - thyroid

KW - feature selection

U2 - 10.1007/978-3-642-16239-8_20

DO - 10.1007/978-3-642-16239-8_20

M3 - Conference contribution

SN - 978-3-642-16239-8

SP - 138

EP - 145

BT - Artificial Intelligence Applications and Innovations

A2 - Papadopoulos, Harris

A2 - Andreou, Andreas S.

A2 - Bramer, Max

PB - Springer Berlin Heidelberg

CY - Berlin, Heidelberg

ER -

Katsigiannis S, Keramidas EG, Maroulis D. Contourlet Transform for Texture Representation of Ultrasound Thyroid Images. In Papadopoulos H, Andreou AS, Bramer M, editors, Artificial Intelligence Applications and Innovations: 6th IFIP WG 12.5 International Conference, AIAI 2010, Larnaca, Cyprus, October 6-7, 2010. Proceedings. Berlin, Heidelberg: Springer Berlin Heidelberg. 2010. p. 138-145 https://doi.org/10.1007/978-3-642-16239-8_20