Classification ensemble for mammograms using Ant-Miner

This paper proposes a new classification method based on association rule mining. This association rule-based classifier is experimented on a real dataset; a database of medical images from MIAS database. The proposed system employs Ant-Miner metaheuristic algorithm for extracting knowledge in the form of decision rules using texture features extracted with the help of co-occurrence matrices. These rules are used to predict unseen mammogram. The experimental results show that the method performs with greater accuracy.