Descripció del projecte
This industrial PhD project is led by the NeuroADaS Lab research group, affiliated with the eHealth Center of the Open University of Catalonia (UOC), in collaboration with the technology company MOVUMTECH SL. The main objective of the project is to develop an innovative proof of concept to improve the surgical planning of dental implants, by applying solutions based on artificial intelligence (AI) to medical image processing, specifically maxillofacial images in CBCT (Cone Beam Computed Tomography) format, also known as 3D X-rays of the mouth.
The project aims to address in a detailed and automatic way the segmentation of CBCT images, focusing on the most relevant anatomical structures of the maxillofacial region, such as bone, teeth, dental nerve and maxillary sinuses. In addition, the aim is to develop a system capable of automatically classifying and labeling all dental areas, following the standard notation established by the FDI World Dental Federation, thus facilitating the understanding and clinical use of the processed data.
Another key objective of the project is to automatically identify the state of each tooth, detecting which ones are absent, which have been replaced by implants, which have some type of pathology and which ones are missing to be placed. This information will allow to optimize and streamline decision-making by dental professionals, improving the planning and execution of surgical interventions.
In parallel, the project also aims to develop efficient multimodal medical image registration methods, which allow combining information from different sources, such as CBCT, STL files (intraoral 3D scans) and other medical image formats. This integration will facilitate a more complete and precise view of the patient’s anatomy, significantly contributing to improving diagnosis and the development of more accurate and personalized surgical plans.
Finally, the development of a longitudinal registration technique is proposed, which allows comparing images acquired at different points in time of the same patient. This temporal tracking capacity may be key for the early detection of pathological changes, offering a powerful tool for the monitoring and prevention of oral health problems.
