A New GLLD Operator for Mass Detection in Digital Mammograms

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.

Combination of Texture and Shape Features Using Machine and Deep Learning Algorithms for Breast Cancer Diagnosis

“…The main limitation of using the LBP code is that it may give the same results with two completely different gray levels when the differences with the neighbors are the same. In [20], we improved the LBP algorithm to allow the extraction of more relevant texture feature attributes from mammographic images to reduce the false positive and true negative rates based on the gray level and local difference information. In the following, we present details of the GLLD algorithm.…”

“…In the GLLD algorithm [20], we computed the average for each [3×3] neighborhood noted g cmean , then we attributed this value to the central pixel. The Fig.…”

A Survey of Computer-aided Detection of Breast Cancer with Mammography

“…Finally a twin support vector machine area under the receiver operating characteristics (ROC) curve is 0.988 for 512 ROIs. Gargouri et al [29] proposed a new local pattern model named gray level and local difference (GLLD) to represent a ROI. Using 1000 ROIs from Digital Database for Screening Mammography (DDSM) database, the author reported the area under the ROC curve is 0.95.…”

Anomaly classification in digital mammography based on multiple‐instance learning

“…First, all CADe models based on the segmentation of results. This is true for the detection [12][13][14][15][16][17][18][19][20][21][22], false positive reduction [23][24][25][26][27], and segmentation [28][29][30] of masses. In other words, CADx systems are focused on mass classification systems [13,22,[31][32][33][34][35][36][37][38], or malignant/no-malignant classification systems in general [39].…”