There is high demand on supporting diagnostic work in medical practice, especially when using medical imaging processes. It requires high expertise to gain information from these images, because they are often very noisy. Cone-beam CT is one of the most recent technology in conservative dentistry.
In my thesis I analyze CBCT images, and I examine several image processing techniques, which are suitable to segment teeth located in the maxillofacial region. One of the most important aim of my thesis is to support medical diagnostic decisions by reconstructing the root canals of the segmented and separated teeth. In the thesis I propose a novel region growing segmentation method, and a method to detect root canals. The algorithms are developed in Matlab environment. In the second part of my thesis I present a visualization technique to display the separated and segmented teeth, and the root canals they contain.