Breast cancer diagnosis using a hybrid evolutionary neural network classifier

Abstract

The important role that mammography is playing in breast cancer detection can be attributed largely to the technical improvements and dedication of radiologists to breast imaging. A lot of work is being done to ensure that these diagnosing steps are becoming smoother, faster and more accurate in classifying whether the abnormalities seen in mammogram images are benign or malignant. This paper takes a step in that direction by introducing a hybrid evolutionary neural network classifier (HENC) combining the evolutionary algorithm, which has a powerful global exploration capability, with gradient-based local search method, which can exploit the optimum offspring to develop a diagnostic aid that accurately differentiates malignant from benign pattern. The computational experiments show that the presented HENC approach can obtain better generalization and much lower computational cost than the existing methods reported recently in the literature using the widely accepted Wisconsin breast cancer diagnosis (WBCD) database with some improvements.