Intensity independent texture analysis in screening mammograms

Xizhao Li; Simon Williams; Murk Bottema

doi:10.1007/978-3-642-31271-7_61

Intensity independent texture analysis in screening mammograms

Xizhao Li
, Simon Williams
, Murk Bottema

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

5 Citations (Scopus)

Abstract

Image texture features for detecting malignant masses in screening mammograms are proposed that are independent of background intensity mean and variation. Subtracting local means and dividing by local standard deviation reveals linear structures of approximately 0.7 mm width in screening mammograms. A simple texture feature calculated from on this derived image is used to demonstrate that texture information associated with the location of cancer is retained in the mean and standard deviation normalized image. Such texture features have the potential to provide evidence of malignancy that better complements intensity based features for detecting breast cancer in screening mammograms.

Original language	English
Pages	474-481
Number of pages	8
DOIs	https://doi.org/10.1007/978-3-642-31271-7_61
Publication status	Published - 15 Aug 2012
Event	IWDM 2012 - Duration: 8 Jul 2012 → …

Conference

Conference	IWDM 2012
Period	8/07/12 → …

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

breast cancer
computer-aided mammography
mass detection
texture

Access to Document

10.1007/978-3-642-31271-7_61

Cite this

@conference{1ce585130c5b4c6d97f137a4c43f8da4,

title = "Intensity independent texture analysis in screening mammograms",

abstract = "Image texture features for detecting malignant masses in screening mammograms are proposed that are independent of background intensity mean and variation. Subtracting local means and dividing by local standard deviation reveals linear structures of approximately 0.7 mm width in screening mammograms. A simple texture feature calculated from on this derived image is used to demonstrate that texture information associated with the location of cancer is retained in the mean and standard deviation normalized image. Such texture features have the potential to provide evidence of malignancy that better complements intensity based features for detecting breast cancer in screening mammograms.",

keywords = "breast cancer, computer-aided mammography, mass detection, texture",

author = "Xizhao Li and Simon Williams and Murk Bottema",

year = "2012",

month = aug,

day = "15",

doi = "10.1007/978-3-642-31271-7\_61",

language = "English",

pages = "474--481",

note = "IWDM 2012 ; Conference date: 08-07-2012",

}

TY - CONF

T1 - Intensity independent texture analysis in screening mammograms

AU - Li, Xizhao

AU - Williams, Simon

AU - Bottema, Murk

PY - 2012/8/15

Y1 - 2012/8/15

N2 - Image texture features for detecting malignant masses in screening mammograms are proposed that are independent of background intensity mean and variation. Subtracting local means and dividing by local standard deviation reveals linear structures of approximately 0.7 mm width in screening mammograms. A simple texture feature calculated from on this derived image is used to demonstrate that texture information associated with the location of cancer is retained in the mean and standard deviation normalized image. Such texture features have the potential to provide evidence of malignancy that better complements intensity based features for detecting breast cancer in screening mammograms.

AB - Image texture features for detecting malignant masses in screening mammograms are proposed that are independent of background intensity mean and variation. Subtracting local means and dividing by local standard deviation reveals linear structures of approximately 0.7 mm width in screening mammograms. A simple texture feature calculated from on this derived image is used to demonstrate that texture information associated with the location of cancer is retained in the mean and standard deviation normalized image. Such texture features have the potential to provide evidence of malignancy that better complements intensity based features for detecting breast cancer in screening mammograms.

KW - breast cancer

KW - computer-aided mammography

KW - mass detection

KW - texture

UR - https://www.scopus.com/pages/publications/84864863833

U2 - 10.1007/978-3-642-31271-7_61

DO - 10.1007/978-3-642-31271-7_61

M3 - Paper

SP - 474

EP - 481

T2 - IWDM 2012

Y2 - 8 July 2012

ER -

Intensity independent texture analysis in screening mammograms

Abstract

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this