A Bayes-Based Region-Growing Algorithm for Medical Image Segmentation

This paper discusses a new Bayesian-analysis-based region-growing algorithm for medical image segmentation that can robustly and effectively segment medical images. Specifically the approach studies homogeneity criterion parameters in a local neighbor region. Using the multislices Gaussian and anisotropic filters as a preprocess helps reduce an image´s noise. The algorithm framework is tested on CT and MRI image segmentation, and experimental results show that the approach is reliable and efficient.