Segmentation of medical images using seeded region growing technique isincreasingly becoming a popular method because of its ability to involvehigh-level knowledge of anatomical structures in seed selection process. Regionbased segmentation of medical images are widely used in varied clinicalapplications like visualization, bone detection, tumor detection andunsupervised image retrieval in clinical databases. As medical images aremostly fuzzy in nature, segmenting regions based intensity is the mostchallenging task. In this paper, we discuss about popular seeded region growmethodology used for segmenting anatomical structures in CT Angiography images.We have proposed a gradient based homogeneity criteria to control the regiongrow process while segmenting CTA images.
展开▼