Description

The segmentation in medical images were more helpful for the identification the separate organs from the images if there are several organs in the scan like abdominal scan. The images were filtered using gaussian filter which removes the noises in the input images. Thresholding process is employed inorder to identify and eliminate portions other than liver in the abdominal scan image. Nonlinear diffusion is applied to the threshold applied image inorder to eliminate the other portions further. Improved region growing algorithm is applied for which the larger portion segmented in the nonlinear diffusion acts as the seed. The performance of the process is measured based on the performance metrics like volumetric overlap error (VOE), relative volume difference (RVD), average symmetric surface distance (ASD) and root mean square symmetric surface distance (RMD).