Background: Dental plaque causes many common oral diseases (e.g., caries, gingivitis, and periodontitis). Therefore, plaque detection and control are extremely important for children’s oral health. The objectives of this study were to design a deep learning-based artificial intelligence (AI) model to detect plaque on primary teeth and to evaluate the diagnostic accuracy of the model. Methods: A conventional neural network (CNN) framework was adopted, and 886 intraoral photos of primary teeth were used for training. To validate clinical feasibility, 98 intraoral photos of primary teeth were assessed by the AI model. Additionally, tooth photos were acquired using a digital camera. One experienced pediatric dentist examined the photos and marked the regions containing plaque. Then, a plaque-disclosing agent was applied, and the areas with plaque were identified. After 1 week, the dentist drew the plaque area on the 98 photos taken by the digital camera again to evaluate the consistency of manual diagnosis. Additionally, 102 intraoral photos of primary teeth were marked to denote the plaque areas obtained by the AI model and the dentist to evaluate the diagnostic capacity of each approach based on lower-resolution photos. The mean intersection-over-union (MIoU) metric was employed to indicate detection accuracy. Results: The MIoU for detecting plaque on the tested tooth photos was 0.726 ± 0.165. The dentist’s MIoU was 0.695 ± 0.269 when first diagnosing the 98 photos taken by the digital camera and 0.689 ± 0.253 after 1 week. Compared to the dentist, the AI model demonstrated a higher MIoU (0.736 ± 0.174), and the results did not change after 1 week. When the dentist and the AI model assessed the 102 intraoral photos, the MIoU was 0.652 ± 0.195 for the dentist and 0.724 ± 0.159 for the model. The results of a paired t-test found no significant difference between the AI model and human specialist (P > .05) in diagnosing dental plaque on primary teeth. Conclusions: The AI model showed clinically acceptable performance in detecting dental plaque on primary teeth compared with an experienced pediatric dentist. This finding illustrates the potential of such AI technology to help improve pediatric oral health.

Early transition from breastfeeding and non-nutritive sucking habits may be related to occlusofacial abnormalities as environmental factors. Previous studies have not taken into account the potential for interactions between feeding practice, non-nutritive sucking habits and occlusal traits. This study assessed the effects of breast-feeding duration, bottle-feeding duration and non-nutritive sucking habits on the occlusal characteristics of primary dentition in 3–6-year-old children in Peking city. This cross sectional study was conducted via an examination of the occlusal characteristics of 734 children combined with a questionnaire completed by their parents/guardians. The examination was performed by a single, previously calibrated examiner and the following variables were evaluated: presence or absence of deep overbite, open bite, anterior crossbite, posterior crossbite, deep overjet, terminal plane relationship of the second primary molar, primary canine relationship, crowding and spacing. Univariate analysis and multiple logistic regressions were applied to analyze the associations. It was found that a short duration of breast-feeding (never or ≤6 months) was directly associated with posterior cross bite (OR = 3.13; 95% CI = 1.11–8.82; P = 0.031) and no maxillary space (OR = 1.63; 95% CI = 1.23–2.98; P = 0.038). In children breast-fed for ≤6 months, the probability of developing pacifier-sucking habits was 4 times that for those breast-fed for >6 months (OR = 4.21; 95% CI = 1.85–9.60; P = 0.0002). Children who were bottle-fed for over 18 months had a 1.45-fold higher risk of nonmesial step occlusion and a 1.43-fold higher risk of a class II canine relationship compared with those who were bottle-fed for up to 18 months. Non-nutritive sucking habits were also found to affect occlusion: A prolonged digit-sucking habit increased the probability of an anterior open bite, while a pacifier-sucking habit associated with excessive overjet and absence of lower arch developmental space. Breastfeeding duration was shown to be associated with the prevalence of posterior crossbite, no maxillary space in the deciduous dentition and development of a pacifier-sucking habit. Children who had a digit-sucking habit were more likely to develop an open bite.

Streptococcus mutans (S. mutans) is a potential pathogenic bacteria of dental caries. However, the level of S. mutans is low in some children with severe early childhood caries (SECC)To evaluate th...

Cell membrane vesicles (CMVs) are composed of natural cell membranes which makes them effective drug delivery systems with low immunogenicity and prolonged circulation time. However, targeting delivery of CMVs in vivo for clinical applications is still a major challenge. In this study, CXCR4 recombinant lentivirus is transfected into MC‐3T3 cells and membrane CXCR4‐enriched MC‐3T3 cells are obtained. CMVs with enriched membrane CXCR4 display (CXCR4‐CMVs) are obtained from the transfected MC‐3T3 cells. Curcumin, an effective natural anti‐inflammatory compound, is encapsulated into CXCR4‐CMVs through physical entrapment (CXCR4/Cur‐CMVs), with the membrane integrity of CXCR4/Cur‐CMVs being well‐preserved. CXCR4/Cur‐CMVs induce enhanced M2 macrophage polarization, exhibit anti‐inflammatory effects, and significantly improve homing via the CXCR4/CXCL12 axis in vitro. Utilizing ulcerative colitis and apical periodontitis as inflammatory disease models, it is found that CXCR4/Cur‐CMVs are obviously aggregated within inflammatory areas after intravenous administration, which results in significant amelioration of ulcerative colitis and apical periodontitis. Therefore, this research may provide a feasible and innovative approach for fabricating an inflammatory site‐targeting delivery system, by engineering CMVs to increase membrane‐presenting CXCR4 receptor.