Fully automated breast boundary and pectoral muscle segmentation in mammograms

作者：

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.

摘要

•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.

论文关键词：Breast mammography,Breast segmentation,Pectoral segmentation,Computer aided diagnosis

论文评审过程：Received 16 March 2017, Revised 25 May 2017, Accepted 1 June 2017, Available online 9 June 2017, Version of Record 12 August 2017.

论文官网地址：https://doi.org/10.1016/j.artmed.2017.06.001