The accreditors of this session require that you periodically check in to verify that you are still attentive.
Please click the button below to indicate that you are.
Next-generation CBCT-based 3D Maxillofacial Analysis System
Date
May 6, 2024
Conventional orthodontic diagnosis has mainly used 2D cephalometric images, but there is a limit to the morphological information that can be extracted by 2D cephalometric methods to understand craniofacial structures with complex 3D morphology. A new 3D cephalogram was developed by fitting a wire mesh template consisting of 10.000 points to the craniofacial bone surface as a reference point and converting the 3D phase information to normalized information. This method allows complex 3D information to be vectorized so that maxillofacial morphology can be evaluated in a comprehensive analysis using machine learning and AI. We will illustrate how this 3D cephalometric can be applied by using examples of how differences in gender and food hardness can affect maxillofacial morphology. In addition, we have now successfully used AI to automatically detect landmarks on CBCT images for 3D cephalograms, which will also be discussed.
Learning Objectives
Evaluate the advantages and disadvantages of traditional 2D and 3D analysis of maxillofacial morphology.
Review how 3D image information is comprehensively analyzed by machine learning and other methods, and how the results are represented.
Outline the development status and future further development of automatic landmark detection by AI in 3D cephalograms.
Privacy Policy Update: We value your privacy and want you to understand how your information is being used. To make sure you have current and accurate information about this sites privacy practices please visit the privacy center by clicking here.