The MOGN Distribution Applied to Medical Imagery Processing

The generalized normal (GN) distribution is one of the most used models for imagery feature processing. Alternatives more flexible than the GN are sought in some real phenomena. We propose a new four-parameter distribution for modeling medical imagery called the Marshall–Olkin generalized normal (MOGN). Some of its properties are derived, including quantile function, expansions for the density and cumulative functions and ordinary and incomplete moments. We estimate the model parameters using maximum likelihood and provide a stochastic expectation– maximization (SEM)-based segmentation algorithm for features in medical images. The performance of our proposals is quantified in an application to real data in contrast to those furnished by the well-known segmentation methods: k -means and other based on the generalized normal SEM. Results indicate that the segmenter which is induced from the MOGN distribution may be an efficient tool for processing medical images.