DIMAR - Discovering interesting medical association rules form MRI scans

Data mining is an expanding research frontier that provides numerous efficient and scalable methods to extract patterns of interest in datasets. In this paper , Computer Aided Diagnosis ( CAD ) is applied to brain MRI image processing. Four features based on texture as proposed by Harlick are extracted and stored in a transactional database. The system is then trained with the proposed efficient associative classifier. The existing CBA algorithm was extended to select only essential rules which help diagnosis of abnormal MRI of the brain. Our work is optimized in the sense it combines feature selection and discretization thereby reducing the mining complexity. The results showed higher sensitivity ( upto 98% ) and accuracy ( upto 97% ) allowing us to claim that association rules can effectively aid in the diagnosing task.