SWARM Intelligence based Model for Content Based Mammogram Image Retrieval

In this papers, we describe a strategy to content-based restoration of medical care images from a given databases. This also provides a preliminary speech as used to the restoration of digital mammograms. The aim of the Content Based Image Retrieval (CBIR) in medical-imaging perspective is to offer a analytic aid by means of show of appropriate previous situations, to radiologists along with confirmed pathology and other appropriate information. Here for the content-based image retrieval, we introduce a new hybrid approach. The use of a neural network called Self Organizing Map (SOM) for clustering the images with respect to their basic characteristics is proposed in the first step. The Particle Swarm Optimization (PSO) based search will be made on a sub set of images, which were having some basic characteristics of the input query image is proposed in the second step. We used our approach to a data source of high quality mammogram images. The trial results show that the suggested technique is more efficient and effective than a genetic algorithm technique.. To conclude whether our CBIR system is helpful to physicians, we conducted a review trial with five radiologists. The results show that our system using PSO retrieval doubled the doctors’ diagnostic accuracy.