Texture Segmentation of Endometrial Images for Aiding Diagnosis of Hyperplasia

The process of discriminating among benign and malignant hyperplasia begun with subjective methods using light microscopy and now is continuing with computerized morphometrical analysis that needs some features. One of the main features called volume percentage of stroma (VPS) is gained by calculating the percentage of stroma texture. Currently, this feature is calculated by pathologists on a manual basis. The algorithm here can automatically calculate VPS with a good precision. In this paper we proposed a method for segmentation of this texture based on Gabor wavelets and mathematical morphology. Gabor wavelets attain maximum joint space-frequency resolution which is highly significant in the process of texture segmentation. The ability of Gabor filters in discrimination of texture bands at different scales and orientations has been used to segment stroma texture which is mainly located in middle frequency bands from glandular elements. The proposed procedure could be the first and essential step of diagnosing endometrial hyperplasia in pathology