Central odontogenic fibroma: report of 29 cases in a Korean population with tooth management.

This study presents the behavioural findings of central odontogenic fibroma (COF) in a specific ethnic group, analysing treatment methods and demonstrating how involved teeth should be managed in detail. Clinical, radiographic, and histological findings were gathered for 29 patients who visited our clinic, with all patients' data carefully examined by radiologists and reviewed microscopically. The cohort comprised 29 patients, with 16 females and 13 males, having a mean (SD) age of 33.1 (16.0) years. Among them, 19 patients were affected in the maxilla, with 15 showing anterior preference, and palatal depression was observed in six patients. Tooth resorption was evident in 15 patients, while 10 patients showed tooth displacement. Within the cohort, 13 patients underwent tooth extraction and resection, while the remaining 16 did not have teeth extracted. Notably, there was no significant difference in recurrence observed between these two groups. This study represents the largest study to date of COF within a single ethnic group and institution. A subset of cases exhibited noteworthy features of COF. However, intriguingly, despite these characteristics, the preservation of contiguous teeth did not demonstrate a significant impact on recurrence rates.

Automatic identification of posteroanterior cephalometric landmarks using a novel deep learning algorithm: a comparative study with human experts.

This study aimed to propose a fully automatic posteroanterior (PA) cephalometric landmark identification model using deep learning algorithms and compare its accuracy and reliability with those of expert human examiners. In total, 1032 PA cephalometric images were used for model training and validation. Two human expert examiners independently and manually identified 19 landmarks on 82 test set images. Similarly, the constructed artificial intelligence (AI) algorithm automatically identified the landmarks on the images. The mean radial error (MRE) and successful detection rate (SDR) were calculated to evaluate the performance of the model. The performance of the model was comparable with that of the examiners. The MRE of the model was 1.87 ± 1.53 mm, and the SDR was 34.7%, 67.5%, and 91.5% within error ranges of < 1.0, < 2.0, and < 4.0 mm, respectively. The sphenoid points and mastoid processes had the lowest MRE and highest SDR in auto-identification; the condyle points had the highest MRE and lowest SDR. Comparable with human examiners, the fully automatic PA cephalometric landmark identification model showed promising accuracy and reliability and can help clinicians perform cephalometric analysis more efficiently while saving time and effort. Future advancements in AI could further improve the model accuracy and efficiency.