Detection of Secondary Structure in Medical Images using Wavelet and Watershed

Image segmentation is the most essential and crucial process in order to facilitate the delineation, characterization and visualization of structures of interests in medical images. In recent years, various methods of medical image segmentation have been employed depending on the type of tissues, anatomy of object of interest and imaging modality being used. In this paper, a novel problem specific segmentation method is proposed to detect secondary structures in medical images incorporating wavelet transform and watershed transformation. The proposed method consists of 5 stages: wavelet transformation, inter scale linking, feature calculation and clustering, morphological processing and watershed transformation. This paper presents the proposed method and preliminary results tested using computed tomography (CT) images of human anatomy. The preliminary experimental results of this research have shown encouraging results with elimination of over segmentation problem frequently faced in watershed transformation