Segmentation of kidneys from computed tomography using 3D fast GrowCut algorithm

This paper proposes a fast GrowCut (FGC) algorithm and applies the new algorithm in three-dimensional (3D) kidney segmentation from computed tomography (CT) volume data. Users could mark the object of interest with different labels in CT slices. FGC propagates the labels using monotonically decreasing function and gray features to derive an optimal cut for a given data in space. The gray features play a great role in comparing with neighborhood cells. The experimental results clearly demonstrate nie superiority of FGC in accuracy and speed.