Computer-aided modelling of three-dimensional maxillofacial tissues through multi-modal imaging

Recent developments in digital imaging techniques have allowed a wide spread of three-dimensional methodologies based on capturing anatomical tissues by different approaches, such as cone-beam computed tomography, three-dimensional photography and surface scanning. In oral rehabilitation, an objective method to predict surgical and orthodontic outcomes should be based on anatomical data belonging to soft facial tissue, facial skeleton and dentition (maxillofacial triad). However, none of the available imaging techniques can accurately capture the complete triad. This article presents a multi-modal framework, which allows image fusion of different digital techniques to create a three-dimensional virtual maxillofacial model, which integrates photorealistic face, facial skeleton and dentition. The methodology is based on combining structured light surface scanning and cone-beam computed tomography data processing. The fusion procedure provides multi-modal representations by aligning different tissues on the basis of common anatomical constraints.