TRUS image segmentation with non-parametric kernel density estimation shape prior

Due to noises, speckles, etc., automatic prostate segmentation is rather challenging, and using only low-level information such as intensity gradient is insufficient and unable to tackle the problem. In this paper, we propose an automatic prostate segmentation method combining intrinsic properties of TRUS images with the high-level shape prior information. First, intrinsic properties of TRUS images, such as the intensity transition near the prostate boundary as well as the speckle induced texture features obtained by Gabor filter banks, are integrated to deform the model to the target contour. These properties make our method insensitive to high gradient regions introduced by noises and speckles. Then, the preliminary segmentation is fine-tuned by the non-parametric shape prior, which is optimally distilled by non-parametric kernel density estimation as it can approximate arbitrary distributions. The refinement is along the direction of mean shift vector, and considerably strengthens the robustness of the method. The performance of our method is validated by experimental results. Compared with the state of the art, the accuracy and robustness of the method is quite promising, and the mean absolute distance is only 1.21 ± 0.85 mm.