Objective. Restoring the correct masticatory function of partially edentulous patient is a challenging task primarily due to the complex tooth morphology between individuals. Although some deep learning-based approaches have been proposed for dental restorations, most of them do not consider the influence of dental biological characteristics for the occlusal surface reconstruction. Description. In this article, we propose a novel dual discriminator adversarial learning network to address these challenges. In particular, this network architecture integrates two models: a dilated convolutional-based generative model and a dual global-local discriminative model. While the generative model adopts dilated convolution layers to generate a feature representation that preserves clear tissue structure, the dual discriminative model makes use of two discriminators to jointly distinguish whether the input is real or fake. While the global discriminator focuses on the missing teeth and adjacent teeth to assess whether it is coherent as a whole, the local discriminator aims only at the defective teeth to ensure the local consistency of the generated dental crown. Results. Experiments on 1000 real-world patient dental samples demonstrate the effectiveness of our method. For quantitative comparison, the image quality metrics are used to measure the similarity of the generated occlusal surface, and the root mean square between the generated result and the target crown calculated by our method is 0.114mm. In qualitative analysis, the proposed approach can generate more reasonable dental biological morphology. Conclusion. The results demonstrate that our method significantly outperforms the state-of-the-art methods in occlusal surface reconstruction. Importantly, the designed occlusal surface has enough anatomical morphology of natural teeth and superior clinical application value.

Surface finish, especially the surface finish of functional features, and build time are two important concerns in additive manufacturing. A suitable part deposition orientation can enhance the surface quality of functional features and reduce the build time. This article proposes a novel method to obtain an optimum part deposition orientation for industrial-grade 3D printing based on fused deposition modeling process by considering two objective functions at a time, namely adaptive feature roughness (the weighted sum of all feature roughnesses) and build time. First, mesh segmentation and level classification of features are carried out. Then, models for evaluation of adaptive feature roughness and build time are established. Finally, a non-dominated sorting genetic algorithm-II based on Compute Unified Device Architecture is used to obtain the Pareto-optimal set. The feasible of the algorithm is evaluated on several examples. Results demonstrate that the proposed parallel algorithm obtains a limiting solution that enhances the surface quality of functional features significantly and reduces average running time by 94.8% compared with the traditional genetic algorithm.

To address the insufficient matching between high strength and low elastic modulus in traditional metal bone scaffolds and the issue of secondary surgical removal, this study used degradable zinc magnesium alloy as the material to study the relationship between porosity gradient distribution and mechanical and biological properties of Gyroid porous bone scaffolds. We established three groups of scaffolds with different porosity gradient distribution, including uniform, axial gradient, and radial gradient. Numerical simulation experiments were conducted for axial compression. The simulation results show that compared to uniform and axial gradients, radial gradient scaffolds have the highest Young’s modulus and exhibit exceptional load-bearing capacity. The results of sample compression experiments show that under the same (average) porosity, the elastic modulus of uniform porous scaffolds and radial gradient porous scaffolds was not significantly different, but reverse radial gradient scaffolds exhibited superior yield strength relative to uniform porous scaffolds. Moreover, forward radial gradient scaffold extracts showed lower toxicity on the in vitro proliferation of mouse calvarial pre-osteoblast cells. By designing a forward radial gradient Gyroid porous bone scaffold, it is expected to obtain a biodegradable Zn-2Mg porous bone scaffold with excellent mechanical and biological properties.