EXPLORE PUBLICATIONS BY COUNTRIES

Anisotropic diffusion, Local features, Directional diffusion, Segmentation

Advances in digital imaging techniques have made possible the acquisition of large volumes of Transrectal Ultrasound (TRUS) prostate images so that there is considerable demand for automated segmentation. Prostate cancer diagnosis and treatment rely on segmentation of these Transrectal Ultrasound (TRUS) prostate images, a challenging and difficult task due to weak prostate boundaries, speckle noise and the narrow range of gray levels, leading most image segmentation methods to perform poorly. The enhancement of ultrasound images is challenging, however prostate segmentation can be effectively improved in contrast enhanced images. Anisotropic diffusion has been used for image analysis based on selective smoothness or enhancement of local features such as region boundaries. In its formal form, anisotropic diffusion tends to encourage within-region smoothness and avoid diffusion across different regions. In this paper we extend the anisotropic diffusion to multiple directions such that segmentation methods can effectively be applied based on rich extracted features. A preliminary segmentation method based on extended diffusion is proposed. Finally an adaptive anisotropic diffusion is introduced based on image statistics.