Image Mining for Mammogram Classification by Associative Classifier with Negative Rules Using Texture Features

Image mining is concerned with knowledge discovery in image databases. Image mining deals with the extraction of implicit knowledge, image data relationship, or other patterns not explicitly stored in the image databases. The focus of image mining is in extraction of patterns from large collection of images. Breast cancer is the leading cause of cancer death among women. Screening mammography is the only method currently available for the reliable detection of early and potentially curable breast cancer. Research indicates that the mortality rate could decrease by 30% if women age 50 and older have regular mammograms. The detection rate can be increased 5-15% by providing the radiologist with results from a computer-aided diagnosis (CAD) system acting as a second opinion. It would be beneficial if an accurate CAD system existed to identify normal mammograms and thus allowing the radiologist to focus on suspicious cases. This strategy could reduce the radiologists workload and improve screening performance. The texture statistical second considered is spatial gray level dependence method, gray level run length method and gray level difference method. Features are extracted from the first-order statistical method and second-order statistical method and are combined. It is observed that the result of these combined features provides higher accuracy when compared with the features from the first-order statistical method and second-order statistical method alone. Since mammography is considered as the most effective means for breast cancer diagnosis, this paper introduces multi dimensional genetic association rule mining for classification of mammograms. The purpose of our experiments is to explore the feasibility of image mining approach to extract patterns and whether that pattern will be helpful to diagnose breast cancer and tissue as well as increase the diagnostic accuracy of image processing and data mining techniques for optimum classification between normal and abnormalities in digital mammograms. Results shows very promising and the accuracy level is very high in compared to other techniques in case of image mining based on negative association rule mining. It is well known that data mining techniques are more suitable to larger databases than the one used for these preliminary tests. Computer-aided method using association rule could assist medical staff and improve the accuracy of mammogram detection. In particular, a Computer aided method based on association rules becomes more accurate with a larger dataset .Experimental results show that this new method can quickly and effectively mine potential association rules.