earticle

영어

Prostate segmentation from MRI is a necessary first step and plays an important role in clinical decision making process. A MR T1 Image segmentation method of the prostate based on distance regularized level set evolution (DRLSE) is proposed. To smooth the prostate image to reduce the noise, a preprocessed prostate image with Gaussian kernel and get an edge indicator is convolved. We construct an energy function with a distance regularization term and an external energy term containing the edge indicator and minimize it by solving the gradient flow which can be implemented with a finite difference scheme. In segmentation experiments, the impact of parameters λ , μ , α and ε in DRLSE model on the image segmentation is analyzed, and an optimal value of these parameters is given. The experiment results confirm the effectiveness of the MRI segmentation method of prostate for different situation of different patients.