Statistical categorization of human histological images

Histology is the science of understanding the structure of animals and plants, and studying the functional implications of biological structures. In this paper, we propose a statistical modeling approach to human histological image categorization. Texture features of the images are characterized by localized Gabor filters. The probabilistic distribution of the texture patterns from each category is approximated by a finite Gaussian mixture model. Expectation maximization (EM) procedure and minimum message length (MML) principle are used to perform density estimation and model selection, respectively. Component-wise EM and weak component annihilation are applied to avoid the drawbacks of the standard EM. Experimental validation is provided based on images from different organs and parts of the body.