Detection and Segmentation of Kidney from Ultrasound Image Using GVF

Abstract

The ultrasound imaging technique is used to identify abnormalities of the kidney. The kidney may contain abnormalities, e.g. kidney swelling, change in its position and appearance. Kidney abnormality may also appear due to cysts, cancerous cells, congenital anomalies, blockage of urine, etc. To operate abnormal kidney, it is required to detect the exact and accurate place of cyst in the kidney. The ultrasound images have low contrast and mainly contain speckle noise which creates a challenging task in kidney abnormalities detection. Thus preprocessing of ultrasound images is an important task to remove speckle noise. In preprocessing, to reduce speckle noise Gaussian filter is applied the resultant image is enhanced using histogram equalization. The preprocessed ultrasound image is segmented using Gradient Vector Flow (GVF) segmentation. This external force (i.e., GVF) was calculated gradient vectors of gray level and binary edge map.