Texture Segmentation in Mammograms

Reyer Zwiggelaar; Lilian Blot; David Raba; Erika R. E. Denton

Texture Segmentation in Mammograms

Reyer Zwiggelaar
, Lilian Blot
, David Raba
, Erika R. E. Denton

University of East Anglia
Universitat de Girona
Norfolk and Norwich University Hospitals NHS Foundation Trust

Research output: Contribution to conference › Paper › peer-review

Abstract

We have investigated a combination of statistical modelling and expectation maximisation for a texture based approach to the segmentation of mammographic images. Texture modelling is based on the implicit incorporation of spatial information through the introduction of a set-permutation-occurrence matrix. Statistical modelling is used for dimensionality reduction, data generalisation and noise removal purposes. Expectation maximisation modelling of the resulting feature vector provides the basis for image segmentation. The developed segmentation results are used for automatic mammographic risk assessment

Original language	English
Pages	137-140
Number of pages	4
Publication status	Published - 10 Jul 2003
Externally published	Yes
Event	Medical Image Understanding and Analysis 2003 - University of Sheffield, Sheffield, United Kingdom of Great Britain and Northern Ireland Duration: 10 Jul 2003 → 11 Jul 2003

Conference

Conference	Medical Image Understanding and Analysis 2003
Abbreviated title	MIUA 2003
Country/Territory	United Kingdom of Great Britain and Northern Ireland
City	Sheffield
Period	10 Jul 2003 → 11 Jul 2003

Permanent link

Persistent link

Cite this

@conference{12e8b64c1c0a498383b7ceace9268290,

title = "Texture Segmentation in Mammograms",

abstract = "We have investigated a combination of statistical modelling and expectation maximisation for a texture based approach to the segmentation of mammographic images. Texture modelling is based on the implicit incorporation of spatial information through the introduction of a set-permutation-occurrence matrix. Statistical modelling is used for dimensionality reduction, data generalisation and noise removal purposes. Expectation maximisation modelling of the resulting feature vector provides the basis for image segmentation. The developed segmentation results are used for automatic mammographic risk assessment",

author = "Reyer Zwiggelaar and Lilian Blot and David Raba and Denton, \{Erika R. E.\}",

year = "2003",

month = jul,

day = "10",

language = "English",

pages = "137--140",

note = "Medical Image Understanding and Analysis 2003, MIUA 2003 ; Conference date: 10-07-2003 Through 11-07-2003",

}

TY - CONF

T1 - Texture Segmentation in Mammograms

AU - Zwiggelaar, Reyer

AU - Blot, Lilian

AU - Raba, David

AU - Denton, Erika R. E.

PY - 2003/7/10

Y1 - 2003/7/10

N2 - We have investigated a combination of statistical modelling and expectation maximisation for a texture based approach to the segmentation of mammographic images. Texture modelling is based on the implicit incorporation of spatial information through the introduction of a set-permutation-occurrence matrix. Statistical modelling is used for dimensionality reduction, data generalisation and noise removal purposes. Expectation maximisation modelling of the resulting feature vector provides the basis for image segmentation. The developed segmentation results are used for automatic mammographic risk assessment

AB - We have investigated a combination of statistical modelling and expectation maximisation for a texture based approach to the segmentation of mammographic images. Texture modelling is based on the implicit incorporation of spatial information through the introduction of a set-permutation-occurrence matrix. Statistical modelling is used for dimensionality reduction, data generalisation and noise removal purposes. Expectation maximisation modelling of the resulting feature vector provides the basis for image segmentation. The developed segmentation results are used for automatic mammographic risk assessment

M3 - Paper

SP - 137

EP - 140

T2 - Medical Image Understanding and Analysis 2003

Y2 - 10 July 2003 through 11 July 2003

ER -

Texture Segmentation in Mammograms

Abstract

Conference

Permanent link

Fingerprint

Cite this