Home // SIGNAL 2018, The Third International Conference on Advances in Signal, Image and Video Processing // View article

Mass Segmentation in Mammograms Using Texture Features and Fuzzy C-means Algorithm

Authors:
Moustapha Mohamed Saleck
Abdelmajide El Moutaouakkil

Keywords: Mammograms; Mass; Fuzzy C-Means; Segmentation; Texture features.

Abstract:
The Fuzzy C-means (FCM) is one of the most efficient algorithms used in various studies, which aims at segmenting the masses in mammogram images, thus to build a Computer Aided Diagnosis (CAD) system capable of helping the physicians for an early diagnosis of the breast cancer. In this paper, we will introduce a new approach using FCM algorithm, in order to extract the mass from Region-of-Interested (ROI). The proposed method aims at avoiding the limitations of cluster number estimation in FCM by selecting as input data, the set of pixels, which are able to provide us the information required to perform the mass segmentation by fixing two clusters only. The Gray Level Occurrence Matrix (GLCM) is used to extract the texture features for getting the optimal threshold, which separate between selected set and the other sets of the pixels that influence on the mass boundary accuracy. The performance of the proposed method is evaluated by specificity, sensitivity, accuracy and overlap. The results obtained from experiments show a good efficiency at the different measures used in this study.

Pages: 25 to 27

Copyright: Copyright (c) IARIA, 2018

Publication date: May 20, 2018

Published in: conference

ISSN: 2519-8432

ISBN: 978-1-61208-638-5

Location: Nice, France

Dates: from May 20, 2018 to May 24, 2018