Cluster analysis boosted watershed segmentation of neurological image

Image segmentation plays a crucial role in medical imaging by facilitating the delineation of regions of interest. The ultimate aim of an automatic image segmentation system is to mimic the human visual system in order to provide a meaningful image subdivision. The watershed transform is a well established tool for the segmentation of images. We have considered Magnetic Resonance Images (MRI) of four Multiple Sclerosis (MS) patients provided by IRCCS Centro Neurolesi "Bonino-Pulejo" of Messina in their original format and tested on them the watershed algorithm implemented using MATLAB 7.6. In this paper we propose an algorithm that use Watershed variant encapsulating Cluster Analysis, then region merging and edge detection procedures were used. This method uses an analysis of variance approach to evaluate the distances between clusters to identify the lesion and to support clinicians in the diagnosis of MS. The algorithm is able to segment or extract desired parts of only gray-scale images and is applied the Cluster Analysis for solved the problem of undesirable oversegmentation results produced by the watershed technique. From our results, we have seen that several analyzed regions have similar characteristics to be grouped together in same class. In particular, we saw that at a distance equal to the level of 0.084, you can find the MS regions. Then the set of parameters considered provides a good description of the regions selected by watershed and then through the cluster analysis allows the distinction between normal and suspect regions.