Robust Automatic Pectoral Muscle Segmentation from Mammograms Using Texture Gradient and Euclidean Distance Regression

In computer-aided diagnosis (CAD) of mediolateral oblique (MLO) view of mammogram, the accuracy of tissue segmentation highly depends on the exclusion of pectoral muscle. Robust methods for such exclusions are essential as the normal presence of pectoral muscle can bias the decision of CAD. In this...

Full description

Saved in:
Bibliographic Details
Published in:Journal of digital imaging Vol. 29; no. 1; pp. 115 - 125
Main Authors: Bora, Vibha Bafna, Kothari, Ashwin G., Keskar, Avinash G.
Format: Journal Article
Language:English
Published: New York Springer US 01.02.2016
Springer Nature B.V
Subjects:
Algorithms
Automation
Breast Neoplasms - diagnostic imaging
Computer aided design
Databases, Factual
Female
Humans
Imaging
Mammography - methods
Medicine
Medicine & Public Health
Muscles
Pattern Recognition, Automated - methods
Pectoralis Muscles - diagnostic imaging
Radiographic Image Interpretation, Computer-Assisted - methods
Radiology
Regression
Reproducibility of Results
Segmentation
Surface layer
Texture
Pectoral muscle detection
Computer aided diagnosis
Hough transform
Euclidean distance regression
Mammograms
Texture gradient
ISSN:0897-1889, 1618-727X, 1618-727X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In computer-aided diagnosis (CAD) of mediolateral oblique (MLO) view of mammogram, the accuracy of tissue segmentation highly depends on the exclusion of pectoral muscle. Robust methods for such exclusions are essential as the normal presence of pectoral muscle can bias the decision of CAD. In this paper, a novel texture gradient-based approach for automatic segmentation of pectoral muscle is proposed. The pectoral edge is initially approximated to a straight line by applying Hough transform on Probable Texture Gradient (PTG) map of the mammogram followed by block averaging with the aid of approximated line. Furthermore, a smooth pectoral muscle curve is achieved with proposed Euclidean Distance Regression (EDR) technique and polynomial modeling. The algorithm is robust to texture and overlapping fibro glandular tissues. The method is validated with 340 MLO views from three databases—including 200 randomly selected scanned film images from miniMIAS, 100 computed radiography images and 40 full-field digital mammogram images. Qualitatively, 96.75 % of the pectoral muscles are segmented with an acceptable pectoral score index. The proposed method not only outperforms state-of-the-art approaches but also accurately quantifies the pectoral edge. Thus, its high accuracy and relatively quick processing time clearly justify its suitability for CAD.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0897-1889
1618-727X
1618-727X
DOI:10.1007/s10278-015-9813-5