Image retrieval of calcification clusters in mammogram using feature fusion and relevance feedback

In order to assist doctors to diagnose mammogram. In connection with the similar lesions retrieval problem of microcalcification cluster in mammogram, we pursue a new algorithm with multi-feature fusion and relevance feedback. Multi-feature fusion of this method adopts multi-distance measure to calculate the similarity directing at different features. Experiment is based on mammogram image database which contain 250 mammogram images and each image contains calcification cluster, we verified the retrieval performance by the precision - recall ratio (PVR) of single feature, feature fusion and relevance feedback. Experimental results show that the method has a better retrieval result than these methods which based single feature and feature fusion which using single distance measurement.