Improved watershed transform for tumor segmentation: Application to mammogram image compression

Wei Yen Hsu

Research output: Contribution to journalArticle

35 Citations (Scopus)

Abstract

In this study, an automatic image segmentation method is proposed for the tumor segmentation from mammogram images by means of improved watershed transform using prior information. The segmented results of individual regions are then applied to perform a loss and lossless compression for the storage efficiency according to the importance of region data. These are mainly performed in two procedures, including region segmentation and region compression. In the first procedure, the canny edge detector is used to detect the edge between the background and breast. An improved watershed transform based on intrinsic prior information is then adopted to extract tumor boundary. Finally, the mammograms are segmented into tumor, breast without tumor and background. In the second procedure, vector quantization (VQ) with competitive Hopfield neural network (CHNN) is applied on the three regions with different compression rates according to the importance of region data so as to simultaneously reserve important tumor features and reduce the size of mammograms for storage efficiency. Experimental results show that the proposed method gives promising results in the compression applications.

Original languageEnglish
Pages (from-to)3950-3955
Number of pages6
JournalExpert Systems with Applications
Volume39
Issue number4
DOIs
Publication statusPublished - Mar 2012
Externally publishedYes

Fingerprint

Image compression
Watersheds
Tumors
Hopfield neural networks
Vector quantization
Image segmentation
Detectors

Keywords

  • Competitive Hopfield neural network (CHNN)
  • Image segmentation
  • Improved watershed transform
  • Mammogram
  • Tumor
  • Vector quantization

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Engineering(all)

Cite this

Improved watershed transform for tumor segmentation : Application to mammogram image compression. / Hsu, Wei Yen.

In: Expert Systems with Applications, Vol. 39, No. 4, 03.2012, p. 3950-3955.

Research output: Contribution to journalArticle

@article{d8bf200a0f424b019582af6de7828598,
title = "Improved watershed transform for tumor segmentation: Application to mammogram image compression",
abstract = "In this study, an automatic image segmentation method is proposed for the tumor segmentation from mammogram images by means of improved watershed transform using prior information. The segmented results of individual regions are then applied to perform a loss and lossless compression for the storage efficiency according to the importance of region data. These are mainly performed in two procedures, including region segmentation and region compression. In the first procedure, the canny edge detector is used to detect the edge between the background and breast. An improved watershed transform based on intrinsic prior information is then adopted to extract tumor boundary. Finally, the mammograms are segmented into tumor, breast without tumor and background. In the second procedure, vector quantization (VQ) with competitive Hopfield neural network (CHNN) is applied on the three regions with different compression rates according to the importance of region data so as to simultaneously reserve important tumor features and reduce the size of mammograms for storage efficiency. Experimental results show that the proposed method gives promising results in the compression applications.",
keywords = "Competitive Hopfield neural network (CHNN), Image segmentation, Improved watershed transform, Mammogram, Tumor, Vector quantization",
author = "Hsu, {Wei Yen}",
year = "2012",
month = "3",
doi = "10.1016/j.eswa.2011.08.148",
language = "English",
volume = "39",
pages = "3950--3955",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "4",

}

TY - JOUR

T1 - Improved watershed transform for tumor segmentation

T2 - Application to mammogram image compression

AU - Hsu, Wei Yen

PY - 2012/3

Y1 - 2012/3

N2 - In this study, an automatic image segmentation method is proposed for the tumor segmentation from mammogram images by means of improved watershed transform using prior information. The segmented results of individual regions are then applied to perform a loss and lossless compression for the storage efficiency according to the importance of region data. These are mainly performed in two procedures, including region segmentation and region compression. In the first procedure, the canny edge detector is used to detect the edge between the background and breast. An improved watershed transform based on intrinsic prior information is then adopted to extract tumor boundary. Finally, the mammograms are segmented into tumor, breast without tumor and background. In the second procedure, vector quantization (VQ) with competitive Hopfield neural network (CHNN) is applied on the three regions with different compression rates according to the importance of region data so as to simultaneously reserve important tumor features and reduce the size of mammograms for storage efficiency. Experimental results show that the proposed method gives promising results in the compression applications.

AB - In this study, an automatic image segmentation method is proposed for the tumor segmentation from mammogram images by means of improved watershed transform using prior information. The segmented results of individual regions are then applied to perform a loss and lossless compression for the storage efficiency according to the importance of region data. These are mainly performed in two procedures, including region segmentation and region compression. In the first procedure, the canny edge detector is used to detect the edge between the background and breast. An improved watershed transform based on intrinsic prior information is then adopted to extract tumor boundary. Finally, the mammograms are segmented into tumor, breast without tumor and background. In the second procedure, vector quantization (VQ) with competitive Hopfield neural network (CHNN) is applied on the three regions with different compression rates according to the importance of region data so as to simultaneously reserve important tumor features and reduce the size of mammograms for storage efficiency. Experimental results show that the proposed method gives promising results in the compression applications.

KW - Competitive Hopfield neural network (CHNN)

KW - Image segmentation

KW - Improved watershed transform

KW - Mammogram

KW - Tumor

KW - Vector quantization

UR - http://www.scopus.com/inward/record.url?scp=82255162537&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=82255162537&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2011.08.148

DO - 10.1016/j.eswa.2011.08.148

M3 - Article

AN - SCOPUS:82255162537

VL - 39

SP - 3950

EP - 3955

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 4

ER -