Extraoral profile photographs are crucial for orthodontic diagnosis, documentation, and treatment planning. The purpose of this study was to evaluate classifications made on extraoral patient photographs by deep learning algorithms trained using grouped patient pictures based on cephalometric measurements. Cephalometric radiographs and profile photographs of 990 patients from the archives of Kocaeli University Faculty of Dentistry Department of Orthodontics were used for the study. FH-NA, FH-NPog, FMA and N-A-Pog measurements on patient cephalometric radiographs were carried out utilizing Webceph. 3 groups for every parameter were formed according to cephalometric values. Deep learning algorithms were trained using extraoral photographs of the patients which were grouped according to respective cephalometric measurements. 14 deep learning models were trained and tested for accuracy of prediction in classifying patient images. Accuracy rates of up to 96.67% for FH-NA groups, 97.33% for FH-NPog groups, 97.67% for FMA groups and 97.00% for N-A-Pog groups were obtained. This is a pioneering study where an attempt was made to classify clinical photographs using artificial intelligence architectures that were trained according to actual cephalometric values, thus eliminating or reducing the need for cephalometric X-rays in future applications for orthodontic diagnosis.
Objectives: The aim of this study was to assess the reliability of panoramic radiography (OPG) using age estimation method using cone beam computed tomography (CBCT) verification in the evaluation of radiographic visibility of root pulp (RPV) of mandibular third molars for age estimation.Methods: CBCT and OPG images of 429 mandibular third molars from 290 patients were evaluated. RPV of fully mineralized mandibular third molars was evaluated as stages 0, 1, 2, and 3 for both imaging methods. Descriptive statistics were performed separately for stages by age for both genders. The consistency of these scores with chronological age was evaluated for both imaging methods. The reliability of OPG evaluation was also analyzed with CBCT scores. Results Spearman’s rho correlation demonstrated a positive correlation between RPV and chronological age for both genders and for OPG and CBCT evaluation. Considering the minimum ages of both imaging methods, all stages were above the age of 18 except for the female group of Stage 2 and all Stage 0. For the comparison of OPG and CBCT RPV Staging scores, the κ score was found to be 0.312 (p < 0.001), indicating a fair agreement.Conclusion: In conclusion, the absence of Stage 3 at age of 18 and under might have a forensic value for RPV age estimation method. Considering the fair agreement in the verification of OPG scores, it is not possible to determine the exact age with the RPV detected in OPG images, the use of CBCT for the RPV evaluation is recommended to available cases.
30 June 2015 in Journal of Oral and Maxillofacial Research
Oral leukoplakia is a precancerous lesion of the oral mucosa. The upregulation of Ki67 and cyclooxygenase-2 has been reported in both dysplastic and non-dysplastic tissues. The aim of this clinicopathological study was to investigate the prognostic value of Ki67 and cyclooxygenase-2 expression for oral leukoplakia. A total of 50 samples were investigated and the study group consisted of 30 oral leukoplakia samples. Samples of 10 intact oral mucosa and 10 squamous cell carcinoma were included as negative and positive control groups, respectively. Epithelial dysplasia was defined as oral intraepithelial neoplasia (OIN) and classified into subgroups 1 - 3. Tissue samples were assessed immunohistochemically for Ki67 and cyclooxygenase-2 expression. Clinicopathological correlations of oral leukoplakia patients were also investigated. All OIN 3 patients were non-smokers (P < 0.05), and homogeneous oral leukoplakia lesions also presented OIN. Both cyclooxygenase-2 and Ki67 expression increased with the severity of lesions, which defined different subgroups (P < 0.05), except there was no significant difference between the hyperkeratosis and OIN groups for Ki67 expression. Cyclooxygenase-2 and Ki67 expression may have a prognostic value for the malignant transformation of oral leukoplakia.
1 April 2021 in Journal of Stomatology Oral and Maxillofacial Surgery