A statistical approach for automatic kidneys detection

The problem we address in this paper is an automatic detection of kidneys with cysts in abdominal 2D computed tomography images. Identifying abdominal organs is a key step in medical image retrieval application. However, due to gray levels similarities of adjacent organs, contrast media effect, and relatively high variation of organ's positions and shapes, automatically identifying abdominal organs has always been a high challenging task. In this paper, we present an original method, in a statistical framework, for fully automatic kidneys detection. The method is tested on over 400 clinically acquired images and very promising results were obtained.