"

Cookies ussage consent

I agree.

Our site saves small pieces of text information (cookies) on your device in order to deliver better content and for statistical purposes. You can disable the usage of cookies by changing the settings of your browser. By browsing our site without changing the browser settings you grant us permission to store that information on your device.

Computer aided detection of microcalcification clusters in mammogram images with machine learning approach

İSMAIL İŞERI1,* , CEMIL ÖZ1

Affiliation

  1. Sakarya University, Faculty of Computer and Information Sciences, Department of Computer Engineering, Esentepe Campus, Sakarya, Turkey

Abstract

Breast cancer is one of the most deadly disease for women health. One of the most used method is digital mammography in medical diagnosis for breast cancer. Mammogram images are important for detecting breast cancer in early stages. Scientiests works on computer aided detection systems for developing second reader systems for radiologists and for reducing detection and diagnose error rates. The complexity and difficulty of microcalcification detection is one of the initial problem in mamogram analysis. In this paper, it is proposed a new feature extraction method called multi-window based statiscal analysis (MWBSA) for detection of microcilcification clusters which are early signs of breast cancer and two stage software framework as a computer aided detection and diagnosis system is proposed. The artifical neural network (ANN) is used as a classifier. Results show that multi window based approach is as applicable as other well known methos (GLCM and Wavelet) and also the computer detection system is applicable as a second reader. As a result of the ROC analysis high sensitivity values 1,00 by using MIAS database is obtained..

Keywords

Microcalcification, Neural Networks, Classification, Detection of Breast Cancer, Mammograms, Machine Learning.

Citation

İSMAIL İŞERI, CEMIL ÖZ, Computer aided detection of microcalcification clusters in mammogram images with machine learning approach, Optoelectronics and Advanced Materials - Rapid Communications, 8, 7-8, July-August 2014, pp.689-695 (2014).

Submitted at: June 11, 2014

Accepted at: July 10, 2014