Skip to Main Content
In this paper, we present a fully automatic algorithm for segmentation of the prostate from the lower abdomen of male patients' CT images. A statistical shape prior is adapted to the process of prostate segmentation. Shape variability of the prostate is derived from expert manually segmented images. Furthermore, we also propose to use genetic algorithm to perform the let set curve evolution. Each individual of the GA population represents a segmenting contour. The fitness of each individual is evaluated based on the texture of the region it encloses. Compared to the manual gold standard segmentations, the results of our automatic segmentation approach after the adaptation of the statistical shape model and GA indicate that our method meets promising results and clinical application.