Joining associative classifier for medical images
Jiang Yun, Zhanhuai Li, Yong Wang, Zhang Longbo · 2005
One of the best prevention measures against breast cancer is the early tumor detection in digital mammography. Detecting tumor in mammography is a difficult task because of their size and the high content of similar patterns in the image. This brings the necessity of creating automatic tools to find whether a mammography present tumor or not. In this paper we join association rule classifier with rough set theory which we call the joining associative classifier (JAC) to mining digital mammography. The experimental results shows that this joining associative classifier performance at 77.48% of classifying accuracy which is higher than 69.11% using associative classifier only. At the same time, the number of rules decreased distinctively. Moreover, the experiments we conducted demonstrate the use and effectiveness of association rule mining in image categorization.