الفهرس 
General introductionOnly 14 pages are availabe for public view
 |  | from | 143 |  |  |
| | | from | 143 | | |
Abstract
”The integration of digital technology within each step of a dental workflow has transformed dentistry, as it can render the dental procedures in a more efficient way, saving time, increasing accuracy, facilitating the treatments, and improving the outcome to meet rising patient demands.
The first and most essential step in the majority of digital dental workflows is image segmentation in order to generate 3D models of the dentomaxillofacial structures, any flaw in this step would contribute towards accumulation of error in the later steps.
Considering the limitations of the conventional segmentation methods, recent application of deep convolutional neural networks (CNNs) has outperformed the previously available algorithms for modelling of the dentomaxillofacial region. These CNNs have been successfully applied with promising results for the CBCT-based automated segmentation of the teeth, pharyngeal airway space, inferior alveolar nerve canal, and mandible. However, a lack of evidence exists related to the CNN based automated segmentation of the midfacial structures.
Hence, the overall aim of the PhD project is twofold. Firstly, to develop a tool for automatic
segmentation of the midfacial structures (bone and air) on CBCT images. Secondly, to incorporate these automated virtual 3D models in clinical applications to assess its performance in the digital workflow. The hypothesis behind this work is that a deep CNN approach could offer a more accurate, consistent, and time-efficient segmentation compared to the present conventional approaches.
Besides, it could deliver accurate and ready-to-print 3D models that are essential to patient-specific digital treatment planning.