Feature extraction based on empirical mode decomposition for automatic mass classification of mammogram images

Abstract

Breast cancer is one of the major health problems that leads to early mortality in women. To aid the radiologists, computer aided diagnosis provides a second opinion for the detection and classification of breast cancer. In this paper, two texture feature extraction methods using Empirical Mode Decomposition (EMD) have been proposed to classify the masses in mammogram images into benign or malignant. The first feature extraction method is based on Bi-dimensional Empirical Mode Decomposition (BEMD). On performing BEMD on Region of Interest (ROI) of mammogram image, the ROI is decomposed into a set of different frequency components called Bi-dimensional Intrinsic Mode Functions (BIMFs). Gray Level Co-occurrence Matrix (GLCM) and Gray Level Run Length Matrix (GLRM) features are extracted from these BIMFs and are given as input to the classifier for classification into benign or malignant. Due to the mode mixing problem that exists in BEMD, BIMFs obtained from BEMD are less orthogonal to each other. To overcome this drawback, the second feature extraction method called Modified Bi-dimensional Empirical Mode Decomposition (MBEMD) is proposed. The BIMFs are extracted by employing the proposed MBEMD on mammogram ROI. Features are extracted in a similar way as BEMD method. Support Vector Machine (SVM) and Linear Discriminant Analysis (LDA) classifiers are used for the classification of mammogram mass. The classification accuracy of 88.8%, 96.2% and Area Under the Curve (AUC) of Receiver Operating Characteristics (ROC) of 0.9, 0.96 are obtained with SVM classifier for BEMD, proposed MBEMD based features respectively. The results show that the proposed method yields consistent performance when applied across different databases.