Rough Sets and Gaussian Mixture Model in Medical Image Diagnosis

Abstract

This paper proposes methods for modeling the content of medical images to help physicians in diagnosing. The Gaussian mixture model is used for medical image segmentation, while the rough set theory is a powerful approach that permits the searching for patterns in medical images using the minimal length principles. Searching for models with small size is performed by means of many different kinds of reducts that generate the decision rules capable for identifying the medical diagnosis.