A New GLLD Operator for Mass Detection in Digital Mammograms.

N Gargouri,D Sellami Masmoudi,A Dammak Masmoudi,R Abid

doi:10.1155/2012/765649

Abstract

During the last decade, several works have dealt with computer automatic diagnosis (CAD) of masses in digital mammograms. Generally, the main difficulty remains the detection of masses. This work proposes an efficient methodology for mass detection based on a new local feature extraction. Local binary pattern (LBP) operator and its variants proposed by Ojala are a powerful tool for textures classification. However, it has been proved that such operators are not able to model at their own texture masses. We propose in this paper a new local pattern model named gray level and local difference (GLLD) where we take into consideration absolute gray level values as well as local difference as local binary features. Artificial neural networks (ANNs), support vector machine (SVM), and k-nearest neighbors (kNNs) are, then, used for classifying masses from nonmasses, illustrating better performance of ANN classifier. We have used 1000 regions of interest (ROIs) obtained from the Digital Database for Screening Mammography (DDSM). The area under the curve of the corresponding approach has been found to be A z = 0.95 for the mass detection step. A comparative study with previous approaches proves that our approach offers the best performances.

Highlights

Breast cancer is the major public health problem in the world
We propose in this paper a new local pattern model named gray level and local difference (GLLD) where we take into consideration absolute gray level values as well as local difference as local binary features
Az = 0.83 Az = 0.81 gray level and texture, in order to train the Artificial neural networks (ANNs) as a classifier. They have applied the principal component analysis (PCA) for the preprocessing step to overcome the problem of complexity and of increasing dimensionality

Summary

Introduction

Breast cancer is the major public health problem in the world. It constitutes the most common cancer among the female population [1]. The European community estimates that breast cancer corresponds to 19% of cancer death. It represents 24% of cancer cases [3]. 25% of all cases of breast cancer deaths occur if women were diagnosed between the age of 40 and 49. Thereafter, once the given system has been trained, a new ROI can be rightly classified Among all these detection algorithms, we can differentiate between two strategies. The first one includes the algorithms which extract features usually related to their texture from the ROI and trains a classifier.

Objectives

Methods

Results

Conclusion