Mammographic mass eigendetection

Arnau Oliver; Jordi Freixenet; Robert Marti; Erika R. E. Denton; Reyer Zwiggelaar

Mammographic mass eigendetection

Arnau Oliver, Jordi Freixenet, Robert Marti, Erika R. E. Denton, Reyer Zwiggelaar

Adran Cyfrifiadureg

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

Crynodeb

A new algorithm for the detection of masses in mammographic images is presented. The algorithm has been designed in two steps. Firstly, the regions likely to be a mass are detected by using a deformable template matching approach, where the template is constructed using the eigenimages of a set of manually detected masses. Subsequently, an algorithm adapted from the eigenfaces approach is used to assure that the detected regions really depict true masses (false positive reduction). The evaluation uses a leave-one-out methodology and is based on a database of 120 mammograms, which include 40 masses and 80 normals. ROC and FROC analysis is used to demonstrate the potential of the developed approach.

Iaith wreiddiol	Saesneg
Tudalennau	71-75
Nifer y tudalennau	5
Statws	Cyhoeddwyd - 04 Gorff 2006
Digwyddiad	10th UK Conference on Medical Image Understanding and Analysis - MIUA: 4-5 th July 2006, University of Manchester - University of Manchester, Manchester, Teyrnas Unedig Prydain Fawr a Gogledd Iwerddon Hyd: 04 Gorff 2006 → 05 Gorff 2006

Cynhadledd

Cynhadledd	10th UK Conference on Medical Image Understanding and Analysis - MIUA
Teitl cryno	MIUA 2006
Gwlad/Tiriogaeth	Teyrnas Unedig Prydain Fawr a Gogledd Iwerddon
Dinas	Manchester
Cyfnod	04 Gorff 2006 → 05 Gorff 2006

Cysylltiad parhaol

Dolen barhaus

Dyfynnu hyn

@conference{5a4dba37f19c4978bf19a4824361fe8d,

title = "Mammographic mass eigendetection",

abstract = "A new algorithm for the detection of masses in mammographic images is presented. The algorithm has been designed in two steps. Firstly, the regions likely to be a mass are detected by using a deformable template matching approach, where the template is constructed using the eigenimages of a set of manually detected masses. Subsequently, an algorithm adapted from the eigenfaces approach is used to assure that the detected regions really depict true masses (false positive reduction). The evaluation uses a leave-one-out methodology and is based on a database of 120 mammograms, which include 40 masses and 80 normals. ROC and FROC analysis is used to demonstrate the potential of the developed approach.",

author = "Arnau Oliver and Jordi Freixenet and Robert Marti and Denton, \{Erika R. E.\} and Reyer Zwiggelaar",

year = "2006",

month = jul,

day = "4",

language = "English",

pages = "71--75",

note = "10th UK Conference on Medical Image Understanding and Analysis - MIUA : 4-5 th July 2006, University of Manchester, MIUA 2006 ; Conference date: 04-07-2006 Through 05-07-2006",

}

TY - CONF

T1 - Mammographic mass eigendetection

AU - Oliver, Arnau

AU - Freixenet, Jordi

AU - Marti, Robert

AU - Denton, Erika R. E.

AU - Zwiggelaar, Reyer

PY - 2006/7/4

Y1 - 2006/7/4

N2 - A new algorithm for the detection of masses in mammographic images is presented. The algorithm has been designed in two steps. Firstly, the regions likely to be a mass are detected by using a deformable template matching approach, where the template is constructed using the eigenimages of a set of manually detected masses. Subsequently, an algorithm adapted from the eigenfaces approach is used to assure that the detected regions really depict true masses (false positive reduction). The evaluation uses a leave-one-out methodology and is based on a database of 120 mammograms, which include 40 masses and 80 normals. ROC and FROC analysis is used to demonstrate the potential of the developed approach.

AB - A new algorithm for the detection of masses in mammographic images is presented. The algorithm has been designed in two steps. Firstly, the regions likely to be a mass are detected by using a deformable template matching approach, where the template is constructed using the eigenimages of a set of manually detected masses. Subsequently, an algorithm adapted from the eigenfaces approach is used to assure that the detected regions really depict true masses (false positive reduction). The evaluation uses a leave-one-out methodology and is based on a database of 120 mammograms, which include 40 masses and 80 normals. ROC and FROC analysis is used to demonstrate the potential of the developed approach.

M3 - Paper

SP - 71

EP - 75

T2 - 10th UK Conference on Medical Image Understanding and Analysis - MIUA

Y2 - 4 July 2006 through 5 July 2006

ER -

Mammographic mass eigendetection

Crynodeb

Cynhadledd

Cysylltiad parhaol

Ôl bys

Dyfynnu hyn