Morphology and mechanical performance of dental crown designed by 3D-DCGAN

This study utilised an Artificial Intelligence (AI) method, namely 3D-Deep Convolutional Generative Adversarial Network (3D-DCGAN), which is one of the true 3D machine learning methods, as an automatic algorithm to design a dental crown.

Six hundred sets of digital casts containing mandibular second premolars and their adjacent and antagonist teeth obtained from healthy personnel were machine-learned using 3D-DCGAN. Additional 12 sets of data were used as the test dataset, whereas the natural second premolars in the test dataset were compared with the designs in (1) 3D-DCGAN, (2) CEREC Biogeneric, and (3) CAD for morphological parameters of 3D similarity, cusp angle, occlusal contact point number and area, and in silico fatigue simulations with finite element (FE) using lithium disilicate material.

The 3D-DCGAN design and natural teeth had the lowest discrepancy in morphology compared with the other groups (root mean square value = 0.3611). The Biogeneric design showed a significantly (p < 0.05) higher cusp angle (67.11°) than that of the 3D-DCGAN design (49.43°) and natural tooth (54.05°). No significant difference was observed in the number and area of occlusal contact points among the four groups. FE analysis showed that the 3D-DCGAN design had the best match to the natural tooth regarding the stress distribution in the crown. The 3D-DCGAN design was subjected to 26.73 MPa and the natural tooth was subjected to 23.97 MPa stress at the central fossa area under physiological occlusal force (300 N); the two groups showed similar fatigue lifetimes (F-N curve) under simulated cyclic loading of 100-400 N. Designs with Biogeneric or technician would yield respectively higher or lower fatigue lifetime than natural teeth.

This study demonstrated that 3D-DCGAN could be utilised to design personalised dental crowns with high accuracy that can mimic both the morphology and biomechanics of natural teeth.