Andere Kunden interessierten sich auch für
![Segmentation of Medical MR Images Using Skew Gaussian Distribution]( "Segmentation of Medical MR Images Using Skew Gaussian Distribution")
Segmentation of Medical MR Images Using Skew Gaussian Distribution39,99 €![Statistical Shape Models for 3D Medical Image Segmentation]( "Statistical Shape Models for 3D Medical Image Segmentation")
Statistical Shape Models for 3D Medical Image Segmentation44,99 €![A generic architecture for e Government and e Democracy]( "A generic architecture for e Government and e Democracy")
A generic architecture for e Government and e Democracy51,99 €![Heuristics & Phylogenies]( "Heuristics & Phylogenies")
Heuristics & Phylogenies20,99 €![A Generic Natural Language Processing Tool for Odiya]( "A Generic Natural Language Processing Tool for Odiya")
A Generic Natural Language Processing Tool for Odiya36,99 €![Generic Context-Aware Middleware for Pervasive Smart Environment]( "Generic Context-Aware Middleware for Pervasive Smart Environment")
Generic Context-Aware Middleware for Pervasive Smart Environment53,99 €![Generic Monitoring and Reconfiguration]( "Generic Monitoring and Reconfiguration")
Generic Monitoring and Reconfiguration40,99 €
Medical image segmentation is challenging and requires more sophisticated algorithms. Medical images are obtained by several different modalities and each of them has certain characteristics. For this reason, there is a need for developing a method which works for any kind of medical images. Deformable model is one of the most popular method in medical segmentation that requires some features (such as an edge) to be present along the boundary of the object, and pull the deformable curve toward that feature. This methods may be sensitive to the starting position and may leak through the boundary of the object if the edge feature is not salient enough in certain regions in the image. On the other hand, level set method evolves a contour implicitly by manipulating a level set function .In this book, we implemented level set region-based method to segment several images from different modalities. Its performance is tested by comparing the segmented results with those obtained by manual segmentation.The method reached a good performance with an average accuracy 94%.