A simulation-based study of 3D printing angle optimization by integrating deep learning and NSGA-III for prosthesis and retainer manufacturing

Clinical Snapshot

Key Findings

• P Value: Angular resolution significantly affected PH and SA under most conditions (P<.001); SA in PH-optimised group P=.004; post hoc analysis confirmed greatest accuracy degradation between 1° and 10° resolutions

• Effect Size: Not reported; magnitude of SA and PH differences across angular resolutions not quantified in the abstract

• Primary Outcome: Dual-objective optimisation of support area (SA) and printing height (PH) for dental crowns and retainers across 24 dental casts at three angular resolutions (1°, 5°, 10°)

• Nnt Or Sensitivity: Computational efficiency: mesh simplification reduced processing time by 87.0% without altering optimal orientation distributions. Framework qualitatively outperformed commercial software in avoiding support placement on critical clinical surfaces (no quantified sensitivity/specificity reported)

• Confidence Interval: Not reported

Clinical Application

The framework requires integration of three distinct deep learning and optimisation components (PointNet++, MeshSegNet, NSGA-III), which presents a non-trivial implementation barrier for standard dental laboratories. The 87% reduction in computation time improves practical feasibility, but software integration into existing CAD/CAM workflows (e.g., exocad, 3Shape) has not been demonstrated. Clinical adoption would require regulatory-grade validation studies. In Australia, dental 3D printing systems and materials require TGA registration as medical devices (Class IIa or higher depending on application). The RACGP and Australian Dental Association (ADA) do not currently provide specific guidelines on automated build orientation optimisation. PBS does not fund dental prosthetic fabrication workflows directly. Before this framework could be considered for Australian clinical or laboratory adoption, it would require: (1) validation against TGA-registered printing platforms and materials; (2) demonstration of dimensional accuracy meeting ISO 12836 and relevant Australian Standards; (3) prospective clinical studies assessing marginal fit and patient outcomes. The framework may be of interest to Australian university dental schools and specialist prosthodontic practices as a research tool. Potentially applicable to dental laboratories and prosthodontic practices utilising photopolymer or resin-based 3D printing for crown and retainer fabrication. At present, applicability is limited to computational workflow optimisation and does not extend to direct clinical use.

Abstract

STATEMENT OF PROBLEM: Current dental 3-dimensional (3D) printing workflows lack automated tools for optimizing build orientations that preserve critical clinical surfaces. Existing slicing software programs often require manual adjustment and may place supports in functional areas. PURPOSE: The purpose of this simulation-based study was to develop and evaluate a computational framework by integrating deep learning and Non-dominated Sorting Genetic Algorithm III (NSGA-III) to optimize build orientations for dental crowns and retainers by minimizing the support area (SA) and printing height (PH). A secondary objective was to assess the effects of angular resolution and mesh simplification on optimization outcomes. MATERIAL AND METHODS: A 3-stage framework was developed using PointNet++ for cast classification, MeshSegNet for feature recognition, and NSGA-III for dual-objective optimization. Mesh simplification was applied to enhance computational efficiency. Twenty-four dental casts were tested in a repeated-measures design at 1, 5, and 10 degrees angular resolutions. Nonparametric statistical analyses were performed using the Friedman test (α=.05) with post hoc Wilcoxon signed-rank tests and Bonferroni correction. RESULTS: Mesh simplified reduced computation time by 87.0% without altering optimal orientation distributions. Reduced angular resolution significantly affected PH and SA outcomes under most conditions (P<.001), except for SA in the PH-optimized group (P=.004). Post hoc analysis confirmed the largest degradation in accuracy between 1 and 10 degrees. Compared with commercially available software programs, the proposed framework consistently avoided the placement of supports on critical surfaces. CONCLUSIONS: The proposed framework provides an automated and efficient approach to optimizing build orientations in dental 3D printing. Although simulation results demonstrated improved optimization performance, further experimental validation is required before clinical application.

References

1. 1.Hu, Y.-D., Lin, Y.-K., & Chen, J.-H. (2026). A simulation-based study of 3D printing angle optimization by integrating deep learning and NSGA-III for prosthesis and retainer manufacturing. The Journal of Prosthetic Dentistry. https://doi.org/10.1016/j.prosdent.2026.03.015