Open AccessA cad system for improving classification performance in breast cancer detection
Author(s) -
Bincy Babu,
A Josephin Arockia Dhivya,
R. Chandrasekaran,
T. R. Thamizhvani,
R. Hemalatha
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i2.25.16566
Subject(s) - computer science , artificial intelligence , mammography , cad , support vector machine , pattern recognition (psychology) , segmentation , breast cancer , classifier (uml) , feature extraction , digital mammography , cancer , medicine , engineering drawing , engineering
Early detection is a key factor in reducing breast cancer mortality rate. Research works in the area of mammography plays an important role in identification of calcification clusters and detection of breast cancer.The purpose of proposed research is to find the best combination of feature extraction algorithm to classify mammogram into benign and malignant. It includes Marker Controlled Watershed Segmentation Technique (MCWS), feature set extraction methods and SVM classifier algorithm. The GLCM, GLRLM and first order texture descriptors are used to describe the calcification clusters.The standard inputs such as normal and abnormal breast images for the proposed system are taken from Digital Database for Screening Mammography (DDSM). The computational study showed that combination of all the three features descriptors provide better classification result with 97% accuracy and it ensures improved the CAD system performance for small training data sets compared to existing techniques.