Segmentation of Breast Masses in Digital Mammograms using Adaptive Median Filtering and Texture Analysis
Nasseer M. Basheer1, Mustafa H. Mohammed2

1Dr. Naseer M. Basheer, Department of Computer Engineering, Technical College, Mosul Iraq.
2Mr. Mustafa H. Mohammed, M. Tech Student, Department of Computer Engineering, Technical College, Mosul Iraq.

Manuscript received on 21 March 2013 | Revised Manuscript received on 28 March 2013 | Manuscript published on 30 March 2013 | PP: 39-43 | Volume-2 Issue-1, March 2013 | Retrieval Number: A0474032113/2013©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Breast cancer continues to be one of the major causes of death among women. Early detection is a key factor to the success of treatment process. X-ray mammography is one of the most common procedures for diagnosing breast cancer due to its simplicity, portability and cost effectiveness. Mass detection using Computer Aided Diagnosis (CAD) schemes was an active field of research in the past few years, and some of these studies showed a promising future. T`hese CAD systems serve as a second decision tool to radiologists for discovering masses in the mammograms. In this paper, a breast mass segmentation method is presented based on adaptive median filtering and texture analysis. The algorithm is implemented using MATLAB environment. The program accepts a digital mammographic image (images taken from the Mammographic Image Analysis Society (MIAS) database). Adaptive median filtering is applied for contouring the image, then the best contour is chosen based on the texture properties of the resulting Region-of-Interest (ROI). The proposed CAD system produces (92.307%) mass sensitivity at 2.75 False Positive per Image (FPI) which is considered as a proper result in this field of research.
Keywords: Adaptive Median Filtering, Digital Mammograms, Mass Detection, Texture Analysis.

Scope of the Article: Predictive Analysis