Kidney Segmentation in Ultrasound Images Using Curvelet Transform and Shape Prior

Automatic tissue kidney segmentation is an important factor in evaluation and diagnosis of kidney's activities and diseases. In this paper, a novel kidney segmentation algorithm in ultrasound images based on Curve let Transform (CT) and Shape prior is proposed. In this algorithm, to segment the kidney's tissue, shape prior and signed distance functions are used to extract variable shape model, and to enhance image and noise removal, applying a nonlinear function on Curve let Transform coefficients. In this shape-based algorithm, segmentation is carried out using calculating the parameters of shape model to minimize the energy function. Using minimizing of energy function, image divides into two regions, textures with low and high variances, inside and outside of the border curve. The proposed algorithm is evaluated on a standard set of the kidney ultrasound images. Obtained segmentation results show that more than 92% of pixels inside of kidney's tissue are extracted correctly.