An Immune-Inspired Approach for Breast Cancer Classification
Abstract
Many pattern recognition and machine learning methods have been used in cancer diagnosis. The Artificial Immune System (AIS) is a novel computational intelligence technique. Designed by the principles of the natural immune system, it is able of learning, memorize and perform pattern recognition. The AIS's are used in various domains as intrusion detection, robotics, illnesses diagnostic, data mining, etc. This paper presents a new immune inspired idea based on median filtering for cloning, and applied for benign/malignant breast cancer classification. The classifier was tested on Wisconsin Diagnostic Breast Cancer Database using classification accuracy, sensitivity ans specificity, and was found to be very competitive when compared to other classifiers.