The immune system has been linked to periodontitis risk in oral inflammation and systemic consequences. Specifically, this study investigated whether hub genes were associated with immune cells via integrating single-cell RNA sequencing (scRNA-seq) and Mendelian randomization (MR). We analyzed scRNA-seq data to identify differentially expressed genes (DEGs) and immune cell subtypes in periodontitis. First, MR analysis was conducted using eQTL data to determine causal relationships between immune cell gene expression and periodontitis risk. Then, Gene ontology (GO) and pathway enrichment analyses were performed to understand functional implications. In addition, CellChat trajectory analysis explored intercellular communication. Finally, reverse transcription quantitative polymerase chain reaction (RT-qPCR) and immunohistochemistry (IHC) were used to validate hub genes. Comprehensive bioinformatics analysis delineated 23 immunologically distinct cell populations and identified 7 pivotal regulatory genes (ANXA1, ARL4C, CD79B, LRRC25, NKG7, SLC11A1, and VIM) demonstrating significant causal associations with periodontitis pathogenesis. Functional pathway analysis demonstrated these molecular markers participate in critical immunomodulatory pathways. RT-qPCR validation confirmed concordance between mRNA expression patterns of these DEGs and MR findings. Immunohistochemical analysis substantiated the causal relationships predicted by MR analysis, showing positive correlations for ANXA1 and SLC11A1 expression, while CD79B exhibited an inverse association. Advanced computational modeling of immune cell receptor-ligand interactions and cellular communication networks uncovered distinct functional roles during periodontitis development, providing novel insights into disease progression mechanisms. This study highlights the crucial role of immune cells and hub genes in periodontitis. These findings provide valuable insights into immune-related mechanisms and potential interventions for periodontitis.

Objective This study aimed to develop and validate a Mask RCNN–Self-Attention (Mask RCNN-SA) framework for automated 3D segmentation of maxillary structures and to investigate volumetric biomarkers of lateral incisor RR associated with impacted maxillary canines. Methods CBCT scans from 42 patients with impacted maxillary canines were randomly divided into training, validation, and test sets (7:2:1) and used to train a Mask RCNN-SA network. Segmentation performance was evaluated using the Dice similarity coefficient (DSC), sensitivity, specificity, and 95% Hausdorff distance. Volumetric measurements of the maxilla, lateral incisors, and first premolars were derived from the segmentation masks to quantify RR-related volume loss. Associations among canine impaction, sex, RR grade, and volumetric changes were analyzed using logistic regression, hierarchical regression, and support vector machine (SVM) classification. Statistical significance was set at P < 0.05. Results The Mask RCNN-SA achieved high segmentation accuracy across anatomical regions (DSC: 93.6% for maxilla; 92.5% for lateral incisor; sensitivity ≥ 94%; accuracy ≥ 97%). Automated segmentation required 0.08 min per scan, significantly faster than manual segmentation. Volumetric analysis revealed significantly reduced volumes on impacted sides for the maxilla (8.767 vs. 9.669 cm³, P = 0.0047) and lateral incisors (3.028 vs. 3.705 cm³, P = 0.0043). RR predominantly affected lateral incisors adjacent to impacted canines, with more pronounced root volume loss in females (21.1% smaller than males, P = 0.0202). SVM classification achieved an AUC of 0.956 for RR prediction. Hierarchical regression identified lateral incisor RR as the strongest determinant of volume reduction (β = 141.244, P < 0.001), whereas maxillary volume showed no added explanatory power. Conclusion The Mask RCNN-SA framework provides accurate, rapid, and clinically interpretable segmentation and volumetric assessment of maxillary structures in cases with impacted canines. This deep learning approach offers a clinical tool for early RR prediction and supports timely interceptive orthodontic interventions.

Background Periodontitis is a prevalent chronic inflammatory disease characterized by immune cell dysregulation and tissue destruction. This study integrates single-cell RNA sequencing (scRNA-seq), Mendelian randomization (MR), and expression quantitative trait loci (eQTL) analyses to uncover immune cell subtypes, causal genes, and develop a predictive nomogram model for periodontitis. Methods We analyzed scRNA-seq data to identify differentially expressed genes (DEGs) and immune cell subtypes in periodontitis. MR analysis was conducted to determine causal relationships between immune cell gene expression and periodontitis risk, utilizing eQTL data. Gene ontology (GO) and pathway enrichment analyses were performed to understand functional implications. Additionally, CellChat trajectory analysis explored intercellular communication. A nomogram model was constructed to predict periodontitis risk based on immune-related DEGs. Results The integrated analysis identified 23 distinct immune cell clusters and seven hub genes (ANXA1, ARL4C, CD79B, LRRC25, NKG7, SLC11A1, and VIM) that were causally linked to periodontitis. Pathway enrichment analysis revealed their involvement in key immune regulatory mechanisms. A robust nomogram model based on these DEGs was developed and validated, demonstrating high predictive accuracy for periodontitis risk. Immune subtypes were further characterized, revealing distinct roles in disease progression. Conclusion This study highlights the crucial role of immune cell subpopulations and hub genes in the pathophysiology of periodontitis. The nomogram model offers a novel tool for predicting periodontitis risk and identifying potential therapeutic targets. These findings provide valuable insights into immune-related mechanisms and potential interventions for periodontitis.

UNSTRUCTURED Root resorption (RR) of adjacent teeth secondary to impacted maxillary canines represents a significant orthodontic challenge, characterized by high morbidity and compromised treatment outcomes. This study introduced the Mask RCNN-SA network, which integrating volumetric features, to overcome traditional algorithmic limitations in anatomical modeling and establish an interpretable RR risk prediction model. Using 4200 CBCT slices augmented 42 CBCT patients, we trained the model for multiclass segmentation of the maxilla, lateral incisors, canines, first premolars, and background. The CBCT scans segmented by the Mask RCNN-SA network demonstrated a large overlap with the gold standard segmentations. The Mask RCNN-SA network–based 3D models of the maxilla and the teeth showed minor surface deviations when compared with the corresponding gold standard 3D models. The Mask RCNN-SA framework reduced segmentation time compared with manual segmentation, confirming volumetric parameters as key biomechanical RR indicators for quantitative preventive strategies.