Oral Surgery Oral Medicine Oral Pathology Oral Radiology最新文献

Objective: Although mucoepidermoid carcinoma is one of the most common salivary gland malignancies, its involvement in the jaws is exceedingly rare. This report's purpose is to describe the histologic and demographic features of intraosseous mucoepidermoid carcinoma (IMEC) and to add evidence to support a potential relationship with glandular odontogenic cysts (GOCs).

Study design: Cases of patients diagnosed with IMEC were obtained from Oral Pathology Laboratory, Inc, at New York-Presbyterian Queens from 1985 to 2024. Slides and clinical information were reviewed.

Results: Fourteen patients with IMEC were identified who had an average age of 58.6 years and a slight female predilection. IMEC was equally present in both jaws. Twelve patients were classified as having low-grade tumors with cystic areas composed of an admixture of epidermoid and mucous cells, 6 cases of which had areas resembling GOCs. Two patients had high-grade tumors demonstrating anaplasia and perineural invasion. One high-grade tumor had areas that resembled a GOC. Four of the 7 presentations of IMEC (6 low-grade and 1 high-grade) with GOC features were from the mandible.

Conclusions: We describe the common and uncommon histopathologic features of IMEC while also demonstrating that GOC-type areas often are seen as a component of these tumors. Therefore, all lesions identified as GOCs should be carefully analyzed to rule out the early development of an IMEC.

Purpose: To evaluate the effects of Sticky Bone-a biomaterial composed of Solid-PRF (S-PRF), a variant of platelet-rich fibrin (PRF), and deproteinized bovine bone-on bone formation after tooth extraction performed prior to radiotherapy, with follow-up during both the pre- and postradiotherapy phases.

Methods: Fifteen patients were randomized to receive either a blood clot (control) or Sticky Bone (experimental) in each extraction socket. Six patients were followed for up to 60 days after radiotherapy. Clinical assessments included evaluation of the surgical site, whereas bone repair was qualitatively analyzed using radiographs reviewed by three blinded examiners. Data were analyzed using the Mann-Whitney U test, multilevel binary regression, and mixed-effects regression (α = 0.05).

Results: Sticky Bone showed no significant effect on the evaluated clinical outcomes, regardless of the assessment period. Improved clinical scores were observed 7 days postoperatively; however, no meaningful differences in soft tissue healing or bone repair were detected within 60 days after radiotherapy.

Conclusion: The null hypothesis was accepted: Sticky Bone had no significant effect on bone or soft tissue healing for up to 60 days after radiotherapy when applied to extraction sites prior to treatment.

Objective: This study aims to develop an AI-powered detection system for identifying dental anatomy-specifically tooth numbers and names-using YOLO (You Only Look Once) models to enhance diagnostic efficiency and automation in dentistry STUDY DESIGN: An annotated dataset of 724 high-resolution digital intraoral dental photographs (505 for training, 112 for validation, 107 for testing), obtained from Kaggle and Roboflow, was used. Multiple YOLO versions (YOLOv8l, YOLOv9c, YOLOv10l, YOLO11l) were implemented. Model performance was evaluated based on recall, precision, F1 score, and mean Average Precision (mAP@50).

Results: YOLOv8l achieved the highest F1 score (96.7%) and recall (97.8%). YOLO11l yielded the best precision (96.6%) and highest mAP@50 (98.4%). All models demonstrated strong potential in detecting teeth accurately from high-resolution images.

Conclusion: YOLO-based models offer an effective solution for automatic detection of dental anatomy. Their integration into telemedicine and digital dentistry platforms can streamline diagnostic workflows, reduce manual workload, and expand access to dental care, particularly in underserved regions.

Objective: The aim of this study was to evaluate the performance of a deep learning (DL) model in automatically identifying dental trauma types on selected periapical radiographs, classified according to the Andreasen system.

Methods and materials: Selected periapical radiographs were annotated based on the Andreasen classification. Using these annotations, a YOLOv8-based DL model was developed to classify trauma types. Because of the large number of trauma subtypes and the limited dataset size, labels were later consolidated into two main categories, and a second model was trained. The performance of both models was assessed using sensitivity, precision, and F1-score.

Results: The initial model showed low overall performance, with a sensitivity of 0.34, precision of 0.29, and F1-score of 0.31. Among the subtypes, avulsion achieved the best performance across all metrics (F1-score: 0.83). After regrouping labels into two main categories, the model's overall performance improved markedly (F1-score: 0.76). Performance was higher for detecting "injuries to hard dental tissues and the pulp" (F1-score: 0.82) than for "injuries to the periodontal tissues" (F1-score: 0.44).

Conclusion: The DL model demonstrated strong potential in identifying dental trauma on selected periapical radiographs, particularly in accurately localizing fracture lines.