Can Artificial Intelligence (AI) Design Natural Tooth Morphology?

Objectives: Dental crown design is one of the most important aspects in restorative dentistry. It is not only the requirements for functional purposes such as mastication and phonetics, but also for the aesthetic and the confidence of the patient. The design must be personalised to fit individual conditions and requirements. Computer-aided design and computer-aided manufacturing (CAD/CAM) has been advocated to improve the traditional workflow. However, it encounters problems such as lack of accuracy, expensive, and still need experienced practitioners to operate. A fully automatic algorithm for dental crown design by utilising AI technology was presented in this study with the potential of improving current workflow.
Methods: 500 sets of mandibular second premolars, adjacent teeth and their antagonist teeth were collected digitally, and machine learned with Generative Adversarial Network (GAN) approach. Twelve sets of data without the mandibular second premolars were used as test group. The twelve AI generated crowns were compared with their original natural mandibular second premolars in parameters of cusp angles, 3D similarity measurements, occlusal contact point numbers and area (measured by 100 μm and 200 μm virtual articulating paper) using Geomagic software.
Results: No significant difference at α=0.05 level was observed regarding cusp angles, occlusal contact points and contact areas between AI designed crowns and nature teeth. Among twelve validation cases, the maximum Root Mean Square (RMS) value was calculated to be 0.6176 mm and the minimum RMS value was 0.2662 mm.
Conclusions: Dental crown shape designed by the GAN method in this study showed no statistical difference among morphological and occlusal parameters, i.e., AI designed crowns is comparable with those of natural teeth. This is anticipated a new tool to design a personalised dental crown with high accuracy.