Traditional orthodontic treatment relies on subjective estimations of orthodontists and iterative communication with technicians to achieve desired tooth alignments. This process is time-consuming, complex, and highly dependent on the orthodontist’s experience. With the development of artificial intelligence, there’s a growing interest in leveraging deep learning methods to achieve tooth alignment automatically. However, the absence of publicly available datasets containing pre/post-orthodontic 3D dental models has impeded the advancement of intelligent orthodontic solutions. To address this limitation, this paper proposes the first public 3D orthodontic dental dataset, comprising 1,060 pairs of pre/post-treatment dental models sourced from 435 patients. The proposed dataset encompasses 3D dental models with diverse malocclusion, e.g., tooth crowding, deep overbite, and deep overjet; and comprehensive professional annotations, including tooth segmentation labels, tooth position information, and crown landmarks. We also present technical validations for tooth alignment and orthodontic effect evaluation. The proposed dataset is expected to contribute to improving the efficiency and quality of target tooth position design in clinical orthodontic treatment utilizing deep learning methods.

(1) Background: Vascularization remains a critical challenge in bone tissue engineering. The objective of this study was to prevascularize calcium phosphate cement (CPC) scaffold by co-culturing human periodontal ligament stem cells (hPDLSCs) and human umbilical vein endothelial cells (hUVECs) for the first time; (2) Methods: hPDLSCs and/or hUVECs were seeded on CPC scaffolds. Three groups were tested: (i) hUVEC group (hUVECs on CPC); (ii) hPDLSC group (hPDLSCs on CPC); (iii) co-culture group (hPDLSCs + hUVECs on CPC). Osteogenic differentiation, bone mineral synthesis, and microcapillary-like structures were evaluated; (3) Results: Angiogenic gene expressions of co-culture group were 6–9 fold those of monoculture. vWF expression of co-culture group was 3 times lower than hUVEC-monoculture group. Osteogenic expressions of co-culture group were 2–3 folds those of the hPDLSC-monoculture group. ALP activity and bone mineral synthesis of co-culture were much higher than hPDLSC-monoculture group. Co-culture group formed capillary-like structures at 14–21 days. Vessel length and junction numbers increased with time; (4) Conclusions: The hUVECs + hPDLSCs co-culture on CPC scaffold achieved excellent osteogenic and angiogenic capability in vitro for the first time, generating prevascularized networks. The hPDLSCs + hUVECs co-culture had much better osteogenesis and angiogenesis than monoculture. CPC scaffolds prevacularized via hPDLSCs + hUVECs are promising for dental, craniofacial, and orthopedic applications.

Accurate tooth segmentation and numbering are the cornerstones of efficient automatic dental diagnosis and treatment. In this paper, a multitask learning architecture has been proposed for accurate tooth segmentation and numbering in panoramic X-ray images. A graph convolution network was applied for the automatic annotation of the target region, a modified convolutional neural network-based detection subnetwork (DSN) was used for tooth recognition and boundary regression, and an effective region segmentation subnetwork (RSSN) was used for region segmentation. The features extracted using RSSN and DSN were fused to optimize the quality of boundary regression, which provided impressive results for multiple evaluation metrics. Specifically, the proposed framework achieved a top F1 score of 0.9849, a top Dice metric score of 0.9629, and an mAP (IOU = 0.5) score of 0.9810. This framework holds great promise for enhancing the clinical efficiency of dentists in tooth segmentation and numbering tasks.

Generative artificial intelligence (GenAI) is rapidly advancing in healthcare and is poised to transform dentistry. Given its increasing adoption in clinical and educational contexts, a comprehensive review is needed to evaluate current progress and future directions. This narrative review investigates its applications, challenges, and prospects. 74 studies from 2020 to 2025 were analyzed, covering various branches of dental medicine. GenAI has shown promise in crown design, tooth alignment, radiographic diagnosis, and educational content generation, using generative adversarial networks, diffusion models, and large language models. However, limitations remain, including insufficient clinical validation, non-standardized datasets, fragmented workflows, and ethical concerns such as data privacy and transparency. Overall, GenAI represents a transformative technology with potential to enhance diagnosis, treatment planning, and education, but continued research and standardized protocols are essential for safe integration.