Image Segmentation

A segmentation method comprises clustering spatial feature data, for instance intensity and volumetric shape index to automatically segment an image, e.g, of a medical lesion. A disclosed algorithm has the following steps: calculating volumetric shape index (SI) for each voxel in the image, combining the SI features with the intensity range and the spatial position (x, y, z) to form a 5-dimensional feature vector set, grouping the 5-dimensional feature vector set into clusters, employing a modified expectation-maximization algorithm (EM) considering not only spatial but also shape features on an intensity mode map from the clustering algorithm to merge the neighbouring regions or modes. The joint spatial intensity shape feature provides rich information for the segmentation of the anatomic structures of interest, such as lesions or tumors.