New Embedded Denotes Fuzzy C-Mean Application for Breast Cancer Density Segmentation in Digital Mammograms

International Engineering Research and Innovation Symposium

Othman, Khairulnizam^1 ; Ahmad, Afandi^1

Embedded Computing Research Cluster, Microelectronics and Nanotechnology-Shamsuddin Research Centre (MiNT-SRC), Universiti Tun Hussein Onn Malaysia, Johor, Malaysia^1

关键词: Different densities;    Digital mammograms;    Fuzzy C-mean algorithm;    Hard constraints;    Mammographic density;    Mammography images;    Quantitative evaluation;    Segmentation algorithms;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/160/1/012105/pdf
DOI  :  10.1088/1757-899X/160/1/012105

来源: IOP

【 摘 要 】

In this research we explore the application of normalize denoted new techniques in advance fast c-mean in to the problem of finding the segment of different breast tissue regions in mammograms. The goal of the segmentation algorithm is to see if new denotes fuzzy c- mean algorithm could separate different densities for the different breast patterns. The new density segmentation is applied with multi-selection of seeds label to provide the hard constraint, whereas the seeds labels are selected based on user defined. New denotes fuzzy c- mean have been explored on images of various imaging modalities but not on huge format digital mammograms just yet. Therefore, this project is mainly focused on using normalize denoted new techniques employed in fuzzy c-mean to perform segmentation to increase visibility of different breast densities in mammography images. Segmentation of the mammogram into different mammographic densities is useful for risk assessment and quantitative evaluation of density changes. Our proposed methodology for the segmentation of mammograms on the basis of their region into different densities based categories has been tested on MIAS database and Trueta Database.