Fully automated breast boundary and pectoral muscle segmentation in mammograms

Highlights • Edge’s information eccentricity and extent are important for pectoral detection. • Characteristics of edge’s noise: ‘half bull nose’, ‘full bull nose’ and ‘horizontal’. • A completed 2D breast model for breast boundary and pectoral muscle segmentation. • We showed the use of ACWE model...

Full description

Saved in:
Bibliographic Details
Published in:Artificial intelligence in medicine 2017-06, Vol.79, p.28-41
Main Authors: Rampun, Andrik, Morrow, Philip J, Scotney, Bryan W, Winder, John
Format: Article
Language:English
Subjects:
Algorithms
Breast mammography
Breast Neoplasms
Breast segmentation
Computer aided diagnosis
Humans
Internal Medicine
Mammography
Other
Pattern Recognition, Automated
Pectoral segmentation
Pectoralis Muscles
Radiographic Image Interpretation, Computer-Assisted
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Highlights • Edge’s information eccentricity and extent are important for pectoral detection. • Characteristics of edge’s noise: ‘half bull nose’, ‘full bull nose’ and ‘horizontal’. • A completed 2D breast model for breast boundary and pectoral muscle segmentation. • We showed the use of ACWE model is more accurate compared to ACE. • Entropy information to enhance the visibility along the skin line boundary.
ISSN:0933-3657
1873-2860
DOI:10.1016/j.artmed.2017.06.001