ADMID: An association rule discovery for mammogram image diagnosis

In this paper, we propose a new method called ADMID, which supports mammogram image diagnosis through association rules. Our method combines low-level features automatically extracted from images with high-level knowledge obtained from specialists to mine association rules, suggesting possible diagnoses. The suggestions of diagnosis are used to accelerate the image analysis performed by specialists as well as to provide them an alternative to work on. ADMID is optimized, in the sense that it combines, in a single step, feature selection and discretization, reducing the mining complexity. The proposed framework was applied to real datasets and the results show high sensitivity up to 98.97% and accuracy up to 98.63%. The results testify that association rules are well suited to support the diagnosing task.