A hierarchical pipeline for breast boundary segmentation and calcification detection in mammograms

Peng Shi, Jing Zhong, Andrik Rampun, Hui Wang

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Breast cancer is one of the most common cancer risks to women in the world. Amongst multiple breast imaging modalities, mammography has been widely used in breast cancer diagnosis and screening. Quantitative analyses including breast boundary segmentation and calcification localization are essential steps in a Computer Aided Diagnosis system based on mammography analysis. Due to uneven signal spatial distributions of pectoral muscle and glandular tissue, plus various artifacts in imaging, it is still challenging to automatically analyze mammogram images with high precision. In this paper, a fully automated pipeline of mammogram image processing is proposed, which estimates skin-air boundary using gradient weight map, detects pectoral-breast boundary by unsupervised pixel-wise labeling with no pre-labeled areas needed, and finally detects calcifications inside the breast region with a novel texture filter. Experimental results on Mammogram Image Analysis Society database show that the proposed method performs breast boundary segmentation and calcification detection with high accuracy of 97.08% and 96.15% respectively, and slightly higher accuracies are achieved on Full-Field Digital Mammography image datasets. Calculation of Jaccard and Dice indexes between segmented breast regions and the ground truths are also included as comprehensive similarity evaluations, which could provide valuable support for mammogram analysis in clinic.
LanguageEnglish
Pages178-188
JournalComputers in Biology and Medicine
Volume96
Early online date16 Mar 2018
DOIs
Publication statusE-pub ahead of print - 16 Mar 2018

Fingerprint

Mammography
Breast
Pipelines
Imaging techniques
Computer aided diagnosis
Labeling
Image analysis
Spatial distribution
Muscle
Skin
Screening
Image processing
Textures
Pixels
Tissue
Breast Neoplasms
Pectoralis Muscles
Air
Early Detection of Cancer
Artifacts

Cite this

@article{77ad3e9f4b9c4affa96ec7e4f4a092b9,
title = "A hierarchical pipeline for breast boundary segmentation and calcification detection in mammograms",
abstract = "Breast cancer is one of the most common cancer risks to women in the world. Amongst multiple breast imaging modalities, mammography has been widely used in breast cancer diagnosis and screening. Quantitative analyses including breast boundary segmentation and calcification localization are essential steps in a Computer Aided Diagnosis system based on mammography analysis. Due to uneven signal spatial distributions of pectoral muscle and glandular tissue, plus various artifacts in imaging, it is still challenging to automatically analyze mammogram images with high precision. In this paper, a fully automated pipeline of mammogram image processing is proposed, which estimates skin-air boundary using gradient weight map, detects pectoral-breast boundary by unsupervised pixel-wise labeling with no pre-labeled areas needed, and finally detects calcifications inside the breast region with a novel texture filter. Experimental results on Mammogram Image Analysis Society database show that the proposed method performs breast boundary segmentation and calcification detection with high accuracy of 97.08{\%} and 96.15{\%} respectively, and slightly higher accuracies are achieved on Full-Field Digital Mammography image datasets. Calculation of Jaccard and Dice indexes between segmented breast regions and the ground truths are also included as comprehensive similarity evaluations, which could provide valuable support for mammogram analysis in clinic.",
author = "Peng Shi and Jing Zhong and Andrik Rampun and Hui Wang",
year = "2018",
month = "3",
day = "16",
doi = "doi.org/10.1016/j.compbiomed.2018.03.011",
language = "English",
volume = "96",
pages = "178--188",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier",

}

A hierarchical pipeline for breast boundary segmentation and calcification detection in mammograms. / Shi, Peng; Zhong, Jing; Rampun, Andrik; Wang, Hui.

In: Computers in Biology and Medicine, Vol. 96, 16.03.2018, p. 178-188.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A hierarchical pipeline for breast boundary segmentation and calcification detection in mammograms

AU - Shi, Peng

AU - Zhong, Jing

AU - Rampun, Andrik

AU - Wang, Hui

PY - 2018/3/16

Y1 - 2018/3/16

N2 - Breast cancer is one of the most common cancer risks to women in the world. Amongst multiple breast imaging modalities, mammography has been widely used in breast cancer diagnosis and screening. Quantitative analyses including breast boundary segmentation and calcification localization are essential steps in a Computer Aided Diagnosis system based on mammography analysis. Due to uneven signal spatial distributions of pectoral muscle and glandular tissue, plus various artifacts in imaging, it is still challenging to automatically analyze mammogram images with high precision. In this paper, a fully automated pipeline of mammogram image processing is proposed, which estimates skin-air boundary using gradient weight map, detects pectoral-breast boundary by unsupervised pixel-wise labeling with no pre-labeled areas needed, and finally detects calcifications inside the breast region with a novel texture filter. Experimental results on Mammogram Image Analysis Society database show that the proposed method performs breast boundary segmentation and calcification detection with high accuracy of 97.08% and 96.15% respectively, and slightly higher accuracies are achieved on Full-Field Digital Mammography image datasets. Calculation of Jaccard and Dice indexes between segmented breast regions and the ground truths are also included as comprehensive similarity evaluations, which could provide valuable support for mammogram analysis in clinic.

AB - Breast cancer is one of the most common cancer risks to women in the world. Amongst multiple breast imaging modalities, mammography has been widely used in breast cancer diagnosis and screening. Quantitative analyses including breast boundary segmentation and calcification localization are essential steps in a Computer Aided Diagnosis system based on mammography analysis. Due to uneven signal spatial distributions of pectoral muscle and glandular tissue, plus various artifacts in imaging, it is still challenging to automatically analyze mammogram images with high precision. In this paper, a fully automated pipeline of mammogram image processing is proposed, which estimates skin-air boundary using gradient weight map, detects pectoral-breast boundary by unsupervised pixel-wise labeling with no pre-labeled areas needed, and finally detects calcifications inside the breast region with a novel texture filter. Experimental results on Mammogram Image Analysis Society database show that the proposed method performs breast boundary segmentation and calcification detection with high accuracy of 97.08% and 96.15% respectively, and slightly higher accuracies are achieved on Full-Field Digital Mammography image datasets. Calculation of Jaccard and Dice indexes between segmented breast regions and the ground truths are also included as comprehensive similarity evaluations, which could provide valuable support for mammogram analysis in clinic.

U2 - doi.org/10.1016/j.compbiomed.2018.03.011

DO - doi.org/10.1016/j.compbiomed.2018.03.011

M3 - Article

VL - 96

SP - 178

EP - 188

JO - Computers in Biology and Medicine

T2 - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

ER -