Cluster, Fuzzy C-Means, Medical image Segmentation, Noise removal.
Accurate segmentation of medical images is a key step in contouring during radiotherapy planning. In this article we have presented modified Watershed Algorithm for medical image segmentation. Image segmentation is often described as partitioning an image into a finite number of semantically non-overlapping regions. The use of the conventional watershed algorithm for medical image analysis is widespread because of its advantages, such as always being able to produce a complete division of the image. In this techniques, Decision based median filter used for noise removal, is best for salt and pepper noise reduction. Secondly, Fuzzy C-Means used for cluster selection and for final segmentation modified watershed segmentation used is integrated with FCM. The aim of this method is reduce the number of segments after proposed method and to overcome problem faced by this method which is over-segmentation and noise sensitivity.