Kidney Based Disease Identification Using Automatic D Segmentation

Abstract: Kidney is consisted of four different structures with different functions. That is renal cortex, renal column, renal medulla and renal pelvis. Different kidney diseases affect different part of kidney. For example, kidney tumor usually occurs in renal cortex, renal column hypertrophy may exist in renal column, medullar cystic kidney disease usually exists in renal medulla, and transitional cell cancer, renal pelvis and ureter cancer may attack renal pelvis. To proposed a fast fully automatic method for kidney components segmentation. The proposed method consists of two main parts: localization of renal cortex and segmentation of kidney components. In the localization phase, a fast localization method which effectively combines 3D GHT and 3D AAM is proposed, which utilizes the global shape and texture information. In the segmentation phase, a modified RF method and a cortex thickness model are proposed to efficiently accomplish the multi-structure segmentation task. Finally obtain the diseases in kidney.

Keywords: Renal Column, Renal Medulla, Renal Pelvis, Generalized Hough Transform, Kidney, Renal Cortex, Active Appearance Models, Random Forests..