Segmentation of ventricles in Alzheimer MR images using Tukey's biweight edge indicator and level set method

Alzheimer's disease is a complex neurological disorder that leads to ventricle enlargement and whole brain shrinkage. In this work, an attempt has been made to segment ventricles in both normal and Alzheimer MR images using Tukey's biweight anisotropic diffusion filtering and modified distance regularized level set method. Geometric features are extracted from the segmented ventricles and analyzed statistically. Results show that the proposed level set method is able to segment ventricles in both normal and Alzheimer conditions. Tukey's biweight anisotropic diffusion filtering is able to provide strong and continuous edges for the levelset to segment. Geometric features such as area and Euler number are found to be statistically highly significant (p<0.0001). Thus this study seems to be clinically useful.