Computer-aided design and 3-dimensional artificial/convolutional neural network for digital partial dental crown synthesis and validation

Abstract

Abstract The current multiphase, invitro study developed and validated a 3-dimensional convolutional neural network (3D-CNN) to generate partial dental crowns (PDC) for use in restorative dentistry. The effectiveness of desktop laser and intraoral scanners in generating data for the purpose of 3D-CNN was first evaluated (phase 1). There were no significant differences in surface area [t-stat(df) = − 0.01 (10), mean difference = − 0.058, P > 0.99] and volume [t-stat(df) = 0.357(10)]. However, the intraoral scans were chosen for phase 2 as they produced a greater level of volumetric details (343.83 ± 43.52 mm 3 ) compared to desktop laser scanning (322.70 ± 40.15 mm 3 ). In phase 2, 120 tooth preparations were digitally synthesized from intraoral scans, and two clinicians designed the respective PDCs using computer-aided design (CAD) workflows on a personal computer setup. Statistical comparison by 3-factor ANOVA demonstrated significant differences in surface area ( P < 0.001), volume ( P < 0.001), and spatial overlap ( P < 0.001), and therefore only the most accurate PDCs (n = 30) were picked to train the neural network (Phase 3). The current 3D-CNN produced a validation accuracy of 60%, validation loss of 0.68–0.87, sensitivity of 1.00, precision of 0.50–0.83, and serves as a proof-of-concept that 3D-CNN can predict and generate PDC prostheses in CAD for restorative dentistry.