Automatic detection of breast lesions in mammograms images with features extraction using Otsu's method


Abstract in English

A mammogram is the best option for early detection of breast cancer, Computer Aided Diagnostic systems(CADs) developed in order to improve the diagnosis of mammograms. This paper presents a proposed method to automatic images segmentation depending on the Otsu's method in order to detect microcalcifications and mass lesions in mammogram images. The proposed technique is based on three steps: (a) region of interest (ROI), (b) 2D wavelet transformation, and (c) OTSU thresholding application on ROI. The method tested on standard mini- MIAS database. It implemented within MATLAB software environment. Experimental results and performance evaluate results show that the proposed detection algorithm is a tool to help improve the diagnostic performance, and has the possibility and the ability to detect the breast lesions.

References used

SMITH R. A. 1993-Epidemiology of breast cancer in a categorical course in physics. Technical Aspects of Breast Imaging, 2nd ed. RSNA publication, Oak Book, II, pp.21
Peto.R, Boreham.J, Clarke.M, Davies.C, Beral.V, May 2000 -UK and USA Breast cancer deaths down 25% in year 2000 at ages 20-69 years. THE LANCET, Volume 355, Issue 9217 ،Page 1822, 20
Ghosh .R, Ghosh. M, Yearwood. J. April, 2004 -A Modular Framework for Multi category feature selection in Digital mammography. In Proceedings of the 12th European Symposium On Artificial Neural Networks ESANN’2004, Bruges (Belgium), pp. 175-180, 28-30

Download