Hybridized Algorithms for Medical Image Segmentation

Clustering analysisis a unsupervised patternrecognition and groups similar data items into same clusterwhile dissimilar data item will be moved into differentclusters.The purpose of data clustering is to reveal the datapatterns and gain some initial insights regarding datadistribution.Similarly Image segmentation groups pixels of animage into multiple segments with respect to intensities. This inturn helps to segment objects of interest from the images. In thispaper we discuss various segmentation algorithms such asFuzzyc-means, Maximum Entropy optimized with Particle swarmOptimization to detect abnormalities present in the image. Weapply these algorithms on MRI image and Ultra sound images.In order to improve the visibility of ultra sound images, we applymorphological filtering before segmentation. The results sectionof this paper show the outcome of the algorithms.