A new fuzzy Gaussian mixture model (FGMM) based algorithm for mammography tumor image classification

Abstract

Computer aided diagnosis systems are recently introduced to increase the accuracy of mammography interpretation. This paper introduces a new classification algorithm based on Fuzzy Gaussian Mixture Model (FGMM) by combining the power of Gaussian Mixture Model (GMM) and Fuzzy Logic System (FLS) for computer aided diagnosis system, to classify the detected regions in mammogram images into malignant or benign categories. The experimental results are obtained from a data set of 300 images taken from the Digital Database for Screening Mammography (DDSM, University of South Florida) for different classes. Confusion matrix analysis is used to measure the performance of the proposed FGMM system. The results show that the proposed FGMM classifier has achieved an overall Matthews Correlation Coefficient (MCC) classification quality of 86.16 %, with 93 % accuracy, 90 % sensitivity and 96 % specificity, and outperformed other classifiers in all aspects. The experimental results obtained from the developed classifier prove that the proposed technique will improve the diagnostic accuracy and reliability of radiologists' image interpretation in the diagnosis of breast cancer. The resulting breast cancer Computer Aided Diagnosis (CAD) detection system is a promising tool to provide preliminary decision support information to physicians for further diagnosis.