Segmentation based on Textons and Mammographic Building Blocks

Izzati Muhimmah; Wenda He; Erika R. E. Denton; Reyer Zwiggelaar

Segmentation based on Textons and Mammographic Building Blocks

Izzati Muhimmah
, Wenda He
, Erika R. E. Denton
, Reyer Zwiggelaar

Adran Cyfrifiadureg

Norfolk and Norwich University Hospitals NHS Foundation Trust

Allbwn ymchwil: Cyfraniad at gynhadledd › Papur › adolygiad gan gymheiriaid

582 Wedi eu Llwytho i Lawr (Pure)

Crynodeb

The objective of this paper is to investigate a potential approach of mammographic image segmentation based on textons and mammographic building blocks (i.e. nodular, linear, homogeneous, and radiolucent) as described in Tabar’ ´ s tissue model. The texton approach is based on clustering filter responses in a high dimension for a
particular building block. The texton selection process is based on a combination of visual assessment (probability maps) and minimum spanning tree topological information. The initial segmentation results are promising, which may lead us to an automatic Tabar’ ´ s mammographic risk assessment

Iaith wreiddiol	Saesneg
Tudalennau	228-232
Nifer y tudalennau	5
Statws	Cyhoeddwyd - 17 Gorff 2007
Digwyddiad	Medical Image Understanding and Analysis 2007: University of Wales Aberystwyth, 17-18 th July - University of Wales, Aberystwyth, Aberystwyth, Teyrnas Unedig Prydain Fawr a Gogledd Iwerddon Hyd: 17 Gorff 2007 → 18 Gorff 2007

Cynhadledd

Cynhadledd	Medical Image Understanding and Analysis 2007
Teitl cryno	MIUA 2007
Gwlad/Tiriogaeth	Teyrnas Unedig Prydain Fawr a Gogledd Iwerddon
Dinas	Aberystwyth
Cyfnod	17 Gorff 2007 → 18 Gorff 2007

Mynediad at Ddogfen

Medical Image Understanding and Analysis 2007 proceedingsFersiwn derfynol wedi’i chyhoeddi, 29.1 MB

Cysylltiad parhaol

Dolen barhaus

Dyfynnu hyn

@conference{4c0c07e699a741428f82532f263f6a69,

title = "Segmentation based on Textons and Mammographic Building Blocks",

abstract = "The objective of this paper is to investigate a potential approach of mammographic image segmentation based on textons and mammographic building blocks (i.e. nodular, linear, homogeneous, and radiolucent) as described in Tabar{\textquoteright} ´ s tissue model. The texton approach is based on clustering filter responses in a high dimension for a particular building block. The texton selection process is based on a combination of visual assessment (probability maps) and minimum spanning tree topological information. The initial segmentation results are promising, which may lead us to an automatic Tabar{\textquoteright} ´ s mammographic risk assessment",

author = "Izzati Muhimmah and Wenda He and Denton, \{Erika R. E.\} and Reyer Zwiggelaar",

year = "2007",

month = jul,

day = "17",

language = "English",

pages = "228--232",

note = "Medical Image Understanding and<br/>Analysis 2007 : University of Wales Aberystwyth, 17-18 th July, MIUA 2007 ; Conference date: 17-07-2007 Through 18-07-2007",

}

TY - CONF

T1 - Segmentation based on Textons and Mammographic Building Blocks

AU - Muhimmah, Izzati

AU - He, Wenda

AU - Denton, Erika R. E.

AU - Zwiggelaar, Reyer

PY - 2007/7/17

Y1 - 2007/7/17

N2 - The objective of this paper is to investigate a potential approach of mammographic image segmentation based on textons and mammographic building blocks (i.e. nodular, linear, homogeneous, and radiolucent) as described in Tabar’ ´ s tissue model. The texton approach is based on clustering filter responses in a high dimension for a particular building block. The texton selection process is based on a combination of visual assessment (probability maps) and minimum spanning tree topological information. The initial segmentation results are promising, which may lead us to an automatic Tabar’ ´ s mammographic risk assessment

AB - The objective of this paper is to investigate a potential approach of mammographic image segmentation based on textons and mammographic building blocks (i.e. nodular, linear, homogeneous, and radiolucent) as described in Tabar’ ´ s tissue model. The texton approach is based on clustering filter responses in a high dimension for a particular building block. The texton selection process is based on a combination of visual assessment (probability maps) and minimum spanning tree topological information. The initial segmentation results are promising, which may lead us to an automatic Tabar’ ´ s mammographic risk assessment

M3 - Paper

SP - 228

EP - 232

T2 - Medical Image Understanding and<br/>Analysis 2007

Y2 - 17 July 2007 through 18 July 2007

ER -

Segmentation based on Textons and Mammographic Building Blocks

Crynodeb

Cynhadledd

Mynediad at Ddogfen

Cysylltiad parhaol

Ôl bys

Dyfynnu hyn