Curvelet Transform-Local Binary Pattern Feature Extraction Technique for Mass Detection and Classification in Digital Mammogram

Abstract

Aim: To develop a Curvelet Transform (CT)-Local Binary Pattern (LBP) feature extraction technique for mass detection and classification in digital mammograms. Study Design: A feature extraction technique. Place and Duration of Study: Sample: Department of Computer Science and Engineering LAUTECH, Ogbomoso, Nigeria 2016. Methodology: Three hundred (300) mammograms were acquired from the public available Mammographic Image Analysis Society (MIAS). One hundred and eighty images were used for training while the remaining 120 images out were used for testing purposes. The images were used pre-processed and segmented into Region of Interests (ROIs) using Histogram Normalization and Active Contour algorithms, respectively. CT algorithm was used to extract shape features from the ROIs while texture features were extracted using the LBP algorithm. K-Nearest Neighbor (KNN) algorithm was employed to classify the extracted features into normal and abnormal mammograms. The abnormal mammograms were further classified into benign (non-cancerous) and Malignant (cancerous) masses using KNN algorithm as well. The technique was implemented using Matrix Laboratory 8.2.0 (R2013b). The performance of the developed technique in classifying mammograms into normal/abnormal was investigated by comparing it with the existing CT-based and LBP-based techniques using sensitivity, specificity, and accuracy. Results: The results of the evaluation showed that the sensitivity, specificity and overall performance for CT-based and LBP-based technique techniques are 72.0, 73.7 and 75.83%; 84.0%, 83.2% and 80.83% while sensitivity, specificity and overall performance of the developed CT-LBP technique are 96.0%, 93.7 and 94.17% respectively. The developed system improved detection of abnormality and the classification rate of mammogram in term of sensitivity, specificity and overall performance, which could be adopted in clinical practices for better detection and classification of breast cancer.