Int. J. of Applied Mathematics, Computational Science and Systems Engineering



A Mammographic Images Classification Technique via the Gaussian Radial Basis Kernel ELM and KPCA

Author(s): Bacha Sawssen, Taouali Okba, Liouane Noureeddine

Abstract: Computer Assisted Diagnosis (CAD) and Artificial Intelligence (AI) are hot topics in the field of medical imaging. Recently, many methods have been proposed. In this research work, a novel mammography image classifier based on Kernel Extreme Learning Machine (KELM) and Kernel Principal Component Analysis (KPCA) is presented. The proposed algorithm, called KELM-KPCA, aims to detect breast tumors by classifying mammographic images. The system first used discrete Tchebichef transform (DTT) to extract features from the images. After normalization of the feature vectors, the kernel principal component analysis (KPCA) is applied to reduce the dimensionality of the features. The reduced characteristics were then subjected to classification by KELM. The k-factor cross-validation strategy was used to improve the generalization of the proposed algorithm. The Mammographic Image Analysis Society (MIAS) dataset is used in this work. The simulation results were compared to the existing algorithms and it was observed that the proposed work outperforms other algorithms. Work on the same dataset in terms of accuracy, F-score, sensitivity and specificity.

Keywords: Mammography, CAD, classification, machine learning, KPCA

Pages: 92-98


Ιnt. J. of Applied Mathematics, Computational Science and Systems Engineering (published by International Academic Publications)


"International Academic Publications", 1666 Kennedy Causeway #412, North Bay Village, Miami, Florida, United States of America.



+1 914 2787705