Image Segmentation And Visualization Based On Visible Human Being Dataset

This paper is focused on the all related image processing techniques of Visible Women Dataset, including medical image segmentation and 3D visualization. A hybrid segmentation method which is based on the Level Set framework is proposed. Marching cube and other rendering methods are used to do visualization. A digital 3D model of uterus is precisely constructed.Based on the properties of color tomography images, we choose the Level Set framework to segment the interested organs out The coarse contour generated by some basic volume-based methods are used as the input of Level Set filter. The experiment indicates that this method can effectively locate the contour of volume of interest, coming with the smooth edges. Such a result gives a good foundation for the further visualization.As to the Visualization, We individually use three mature methods, such as Ray Casting, Texture Mapping and Marching Cube. Among them, Texture Mapping and Marching Cube provide comparatively satisfied result.Developing the whole system, we use some popular toolkits in the medical imaging field: Insight Segmentation and Registration Toolkit (ITK) and Visualization Toolkit (VTK). Code is highly organized and is extendable.