Automated breast profile segmentation for ROI detection using digital mammograms
Mammography is currently the most effective imaging modality used by radiologists for the screening of breast cancer. Finding an accurate, robust and efficient breast profile segmentation technique still remains a challenging problem in digital mammography. Extraction of the breast profile region an...
Saved in:
Main Authors: | , , , |
---|---|
Format: | Conference Paper |
Language: | English |
Published: |
2017
|
Online Access: | http://dspace.uniten.edu.my/jspui/handle/123456789/5832 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.uniten.dspace-5021 |
---|---|
record_format |
dspace |
spelling |
my.uniten.dspace-50212018-01-04T06:40:53Z Automated breast profile segmentation for ROI detection using digital mammograms Nagi, J. Abdul Kareem, S. Nagi, F. Khaleel Ahmed, S. Mammography is currently the most effective imaging modality used by radiologists for the screening of breast cancer. Finding an accurate, robust and efficient breast profile segmentation technique still remains a challenging problem in digital mammography. Extraction of the breast profile region and the pectoral muscle is an essential pre-processing step in the process of computer-aided detection. Primarily it allows the search for abnormalities to be limited to the region of the breast tissue without undue influence from the background of the mammogram. The presence of pectoral muscle in mammograms biases detection procedures, which recommends removing the pectoral muscle during mammogram pre-processing. In this paper we explore an automated technique for mammogram segmentation. The proposed algorithm uses morphological preprocessing and seeded region growing (SRG) algorithm in order to: (1) remove digitization noises, (2) suppress radiopaque artifacts, (3) separate background region from the breast profile region, and (4) remove the pectoral muscle, for accentuating the breast profile region. To demonstrate the capability of our proposed approach, digital mammograms from two separate sources are tested using Ground Truth (GT) images for evaluation of performance characteristics. Experimental results obtained indicate that the breast regions extracted accurately correspond to the respective GT images. © 2010 IEEE. 2017-11-14T03:21:23Z 2017-11-14T03:21:23Z 2010 Conference Paper http://dspace.uniten.edu.my/jspui/handle/123456789/5832 10.1109/IECBES.2010.5742205 en Proceedings of 2010 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2010 2010, Article number 5742205, Pages 87-92 |
institution |
Universiti Tenaga Nasional |
building |
UNITEN Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Tenaga Nasional |
content_source |
UNITEN Institutional Repository |
url_provider |
http://dspace.uniten.edu.my/ |
language |
English |
description |
Mammography is currently the most effective imaging modality used by radiologists for the screening of breast cancer. Finding an accurate, robust and efficient breast profile segmentation technique still remains a challenging problem in digital mammography. Extraction of the breast profile region and the pectoral muscle is an essential pre-processing step in the process of computer-aided detection. Primarily it allows the search for abnormalities to be limited to the region of the breast tissue without undue influence from the background of the mammogram. The presence of pectoral muscle in mammograms biases detection procedures, which recommends removing the pectoral muscle during mammogram pre-processing. In this paper we explore an automated technique for mammogram segmentation. The proposed algorithm uses morphological preprocessing and seeded region growing (SRG) algorithm in order to: (1) remove digitization noises, (2) suppress radiopaque artifacts, (3) separate background region from the breast profile region, and (4) remove the pectoral muscle, for accentuating the breast profile region. To demonstrate the capability of our proposed approach, digital mammograms from two separate sources are tested using Ground Truth (GT) images for evaluation of performance characteristics. Experimental results obtained indicate that the breast regions extracted accurately correspond to the respective GT images. © 2010 IEEE. |
format |
Conference Paper |
author |
Nagi, J. Abdul Kareem, S. Nagi, F. Khaleel Ahmed, S. |
spellingShingle |
Nagi, J. Abdul Kareem, S. Nagi, F. Khaleel Ahmed, S. Automated breast profile segmentation for ROI detection using digital mammograms |
author_facet |
Nagi, J. Abdul Kareem, S. Nagi, F. Khaleel Ahmed, S. |
author_sort |
Nagi, J. |
title |
Automated breast profile segmentation for ROI detection using digital mammograms |
title_short |
Automated breast profile segmentation for ROI detection using digital mammograms |
title_full |
Automated breast profile segmentation for ROI detection using digital mammograms |
title_fullStr |
Automated breast profile segmentation for ROI detection using digital mammograms |
title_full_unstemmed |
Automated breast profile segmentation for ROI detection using digital mammograms |
title_sort |
automated breast profile segmentation for roi detection using digital mammograms |
publishDate |
2017 |
url |
http://dspace.uniten.edu.my/jspui/handle/123456789/5832 |
_version_ |
1644493592595529728 |
score |
13.19449 |