Automatic Registration-Fusion Scheme Based on Similarity Measures: An Application to Dental Imaging.

摘要

A novel automatic registration-fusion scheme based on similarity measures is proposed in this paper. It utilizes the geometrical configuration between the X-ray source, the CCD sensor and the target tissue using the appropriate geometric transformations, as well as the calculation of similarity measures between two dental radiographic images to be registered. Moreover, a fusion process has been developed to combine information from registered dental images. Result on clinical data reveals the advantageous performance of the proposed automatic registration method compared to the manual one using an independent evaluation criterion such as the mutual information criterion. Furthermore, the automatic registration approach outperforms despite the fuzzy dental boundaries and the lack of characteristic edges of the radiographic images. These preliminary findings may be used in order to establish the use of the proposed automatic method relieving the expert from the tedious and time- consuming task of defining analogous markers between the two radiographic images.