Segmentation of ultrasound images by using quantizer neural network

Zümray Dokur; Mehmet Nadir Kurnaz; Tamer Ölmez

Segmentation of ultrasound images by using quantizer neural network

Zümray Dokur^*
, Mehmet Nadir Kurnaz
, Tamer Ölmez

^*Corresponding author for this work

Department of Electronics and Communication Engineering

Istanbul Technical University

Research output: Contribution to journal › Conference article › peer-review

3 Citations (Scopus)

Abstract

Quantizer neural network (QNN) is proposed for the segmentation of ultrasound images. The elements of the feature vectors are formed by the image intensities within one neighborhood of the pixel of interest. QNN is a hybrid neural network structure, which is trained by genetic algorithms. Genetic algorithms are used to find optimum values for the weights of the nodes The hybrid neural network is comparatively examined with multilayer perceptron (MLP) for the segmentation of ultrasound images.

Original language	English
Pages (from-to)	257-261
Number of pages	5
Journal	Proceedings of the IEEE Symposium on Computer-Based Medical Systems
Publication status	Published - 2002
Event	fifteenth IEEE Symposium on Computer-Based Medical Systems - Maribor, Slovenia Duration: 4 Jun 2002 → 7 Jun 2002

Cite this

@article{acd745279c3841a88c37d2ea27841cda,

title = "Segmentation of ultrasound images by using quantizer neural network",

abstract = "Quantizer neural network (QNN) is proposed for the segmentation of ultrasound images. The elements of the feature vectors are formed by the image intensities within one neighborhood of the pixel of interest. QNN is a hybrid neural network structure, which is trained by genetic algorithms. Genetic algorithms are used to find optimum values for the weights of the nodes The hybrid neural network is comparatively examined with multilayer perceptron (MLP) for the segmentation of ultrasound images.",

author = "Z{\"u}mray Dokur and Kurnaz, \{Mehmet Nadir\} and Tamer {\"O}lmez",

year = "2002",

language = "English",

pages = "257--261",

journal = "Proceedings of the IEEE Symposium on Computer-Based Medical Systems",

issn = "1063-7125",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "fifteenth IEEE Symposium on Computer-Based Medical Systems ; Conference date: 04-06-2002 Through 07-06-2002",

}

TY - JOUR

T1 - Segmentation of ultrasound images by using quantizer neural network

AU - Dokur, Zümray

AU - Kurnaz, Mehmet Nadir

AU - Ölmez, Tamer

PY - 2002

Y1 - 2002

N2 - Quantizer neural network (QNN) is proposed for the segmentation of ultrasound images. The elements of the feature vectors are formed by the image intensities within one neighborhood of the pixel of interest. QNN is a hybrid neural network structure, which is trained by genetic algorithms. Genetic algorithms are used to find optimum values for the weights of the nodes The hybrid neural network is comparatively examined with multilayer perceptron (MLP) for the segmentation of ultrasound images.

AB - Quantizer neural network (QNN) is proposed for the segmentation of ultrasound images. The elements of the feature vectors are formed by the image intensities within one neighborhood of the pixel of interest. QNN is a hybrid neural network structure, which is trained by genetic algorithms. Genetic algorithms are used to find optimum values for the weights of the nodes The hybrid neural network is comparatively examined with multilayer perceptron (MLP) for the segmentation of ultrasound images.

UR - https://www.scopus.com/pages/publications/0036068794

M3 - Conference article

AN - SCOPUS:0036068794

SN - 1063-7125

SP - 257

EP - 261

JO - Proceedings of the IEEE Symposium on Computer-Based Medical Systems

JF - Proceedings of the IEEE Symposium on Computer-Based Medical Systems

T2 - fifteenth IEEE Symposium on Computer-Based Medical Systems

Y2 - 4 June 2002 through 7 June 2002

ER -

Segmentation of ultrasound images by using quantizer neural network

Abstract

Other files and links

Fingerprint

Cite this