YOLO-V5 based deep learning approach for tooth detection and segmentation on pediatric panoramic radiographs in mixed dentition.

OBJECTIVES: In the interpretation of panoramic radiographs (PRs), the identification and numbering of teeth is an important part of the correct diagnosis. This study evaluates the effectiveness of YOLO-v5 in the automatic detection, segmentation, and numbering of deciduous and permanent teeth in mixed dentition pediatric patients based on PRs. METHODS: A total of 3854 mixed pediatric patients PRs were labelled for deciduous and permanent teeth using the CranioCatch labeling program. The dataset was divided into three subsets: training (n = 3093, 80% of the total), validation (n = 387, 10% of the total) and test (n = 385, 10% of the total). An artificial intelligence (AI) algorithm using YOLO-v5 models were developed. RESULTS: The sensitivity, precision, F-1 score, and mean average precision-0.5 (mAP-0.5) values were 0.99, 0.99, 0.99, and 0.98 respectively, to teeth detection. The sensitivity, precision, F-1 score, and mAP-0.5 values were 0.98, 0.98, 0.98, and 0.98, respectively, to teeth segmentation. CONCLUSIONS: YOLO-v5 based models can have the potential to detect and enable the accurate segmentation of deciduous and permanent teeth using PRs of pediatric patients with mixed dentition.

Detecting white spot lesions on post-orthodontic oral photographs using deep learning based on the YOLOv5x algorithm: a pilot study.

BACKGROUND: Deep learning model trained on a large image dataset, can be used to detect and discriminate targets with similar but not identical appearances. The aim of this study is to evaluate the post-training performance of the CNN-based YOLOv5x algorithm in the detection of white spot lesions in post-orthodontic oral photographs using the limited data available and to make a preliminary study for fully automated models that can be clinically integrated in the future. METHODS: A total of 435 images in JPG format were uploaded into the CranioCatch labeling software and labeled white spot lesions. The labeled images were resized to 640 × 320 while maintaining their aspect ratio before model training. The labeled images were randomly divided into three groups (Training:349 images (1589 labels), Validation:43 images (181 labels), Test:43 images (215 labels)). YOLOv5x algorithm was used to perform deep learning. The segmentation performance of the tested model was visualized and analyzed using ROC analysis and a confusion matrix. True Positive (TP), False Positive (FP), and False Negative (FN) values were determined. RESULTS: Among the test group images, there were 133 TPs, 36 FPs, and 82 FNs. The model's performance metrics include precision, recall, and F1 score values of detecting white spot lesions were 0.786, 0.618, and 0.692. The AUC value obtained from the ROC analysis was 0.712. The mAP value obtained from the Precision-Recall curve graph was 0.425. CONCLUSIONS: The model's accuracy and sensitivity in detecting white spot lesions remained lower than expected for practical application, but is a promising and acceptable detection rate compared to previous study. The current study provides a preliminary insight to further improved by increasing the dataset for training, and applying modifications to the deep learning algorithm. CLINICAL REVELANCE: Deep learning systems can help clinicians to distinguish white spot lesions that may be missed during visual inspection.

The caries impacts and experiences questionnaire for Turkish children by age groups'.

BACKGROUND: The Caries Impacts and Experiences Questionnaire for Children (CARIES-QC) assess children's effects of dental caries on their quality of life. This study aimed to determine the scale's Turkish version (CARIES-QC/T) validity and reliability according to age groups and to create the scale that is specific to selected age groups. METHODS: Children were divided up into 3 age groups (5-7, 8-10 and 11-14 ages). Explanatory factor analysis (EFA) was used in the concept validation process. Confirmatory factor analysis (CFA) was used for cross-cultural validity. For each group, test-retest analyses were performed on 20 children. Inter-question correlation and Cronbach's alpha were used to examine internal consistency. RESULTS: A total of 360 children (mean age; 9.04, 56.1% girls,) 120 children in each group, participated in the study. Questions 7 and 12 for the 5-7 age group, Questions 4 and 7 for the 8-10 and 11-14 age groups were excluded from the analysis (according to EFA results; factor loads < 0.30). Three modified CARIES-QC/T scales structures with a total of 10 questions were developed for the age groups of 5-7, 8-10, and 11-14. CONCLUSIONS: Some questions on the Caries-QC/T scale should be eliminated, it was found when it was evaluated for age specificity. Although the results of the Caries-QC scale studies to be carried out in different societies and age groups vary, the high sample size in this study and the statistically strong results showed that the Caries-QC/T scale forms that we adapted could be used by the specified age groups.

Supernumerary Teeth and Dental Development.

PURPOSE: The aims of this study were to compare the radiographic development of permanent teeth in a group of children with and without supernumerary teeth (ST), determine whether using cone-beam computed tomography or panoramic radiography improves the accuracy of dental age (DA) estimation and investigate the effects of factors including the numbers and positions of ST. METHODS: One hundred fifty dental radiographs of children with and without ST at the ages of 6.0 to 14.9 years were included in this study. The children in both groups were age and sex-matched. The lower left-side 7 permanent teeth were evaluated according to the Demirjian method, DA was determined. The difference between chronological age (CA) and DA (CA-DA) for the children with and without ST and further based on the number and localization of ST were calculated. RESULTS: For all groups, the mean DA values were higher than the mean CA values. The difference between the CA and DA values in the children with ST was higher than the difference in the children without ST. Supernumerary teeth in posterior localization, multiple ST and among boys were observed to increase the differences between the mean CA and DA values. The mean age difference between radiographies in the children with and without ST was similar. CONCLUSION: Panoramic radiography was found adequate in determination of dental development with the Demirjian method. Dental development was even more advanced in the children with ST in comparison to the control group. Clinicians should keep in mind that the dental developments of children with supernumerary teeth may be advanced.

Cone beam computed tomography imaging of superior semicircular canal morphology: a retrospective comparison of cleft lip/palate patients and normal controls.

OBJECTIVE: This study evaluated the prevalence and morphological characteristics of the superior semicircular canal (SSCC) in cleft lip and palate (CL/P) patients using cone beam computed tomography (CBCT). MATERIALS AND METHODS: CBCT images of 53 CL/P patients (28 males and 25 females) and a control group of 76 patients (42 males and 34 females) were evaluated. Retrospectively, 258 temporal bone images from 129 patients were evaluated in terms of SSCC morphology and divided into a normal pattern (0.6-1.7 mm in thickness), a papyraceous pattern (<0.5 mm), a thick pattern (>1.8 mm), a pneumatized pattern and dehiscent. The chi-squared test was used to compare differences among semicircular canal dehiscence (SSCD) patterns in the CL/P and control groups; p ≤ .05 was taken to reflect statistical significance. RESULTS: The characteristics of the SSCC were evaluated on CBCT images in patients with CL/P and controls. In total, 158 (61%) cases were normal (0.6-1.7 mm in thickness), 31 (12%) papyraceous (<0.5 mm), 8 (3%) thick, and 34 (13%) pneumatized. SSCD was observed in 27 (11%) cases. Statistically significant differences between the CL/P and control groups were evident in terms of SSCC morphology (p < .001). CONCLUSIONS: SSCD should be considered if a CL/P patient exhibits a vestibular system deficiency. Oral and maxillofacial radiologists should pay attention to SSCD when interpreting CBCT images. Future studies should use high-level spatial resolution CBCT to focus on cleft site and SSCC morphology in larger patient populations.

Detecting the presence of taurodont teeth on panoramic radiographs using a deep learning-based convolutional neural network algorithm.

OBJECTIVES: Artificial intelligence (AI) techniques like convolutional neural network (CNN) are a promising breakthrough that can help clinicians analyze medical imaging, diagnose taurodontism, and make therapeutic decisions. The purpose of the study is to develop and evaluate the function of CNN-based AI model to diagnose teeth with taurodontism in panoramic radiography. METHODS: 434 anonymized, mixed-sized panoramic radiography images over the age of 13 years were used to develop automatic taurodont tooth segmentation models using a Pytorch implemented U-Net model. Datasets were split into train, validation, and test groups of both normal and masked images. The data augmentation method was applied to images of trainings and validation groups with vertical flip images, horizontal flip images, and both flip images. The Confusion Matrix was used to determine the model performance. RESULTS: Among the 43 test group images with 126 labels, there were 109 true positives, 29 false positives, and 17 false negatives. The sensitivity, precision, and F1-score values of taurodont tooth segmentation were 0.8650, 0.7898, and 0.8257, respectively. CONCLUSIONS: CNN's ability to identify taurodontism produced almost identical results to the labeled training data, and the CNN system achieved close to the expert level results in its ability to detect the taurodontism of teeth.

Evaluation of the relationship between malocclusions and sleep-disordered breathing in children.

OBJECTIVE: To determine the relationship between dental/skeletal malocclusions and sleep-disordered breathing (SDB) in the early diagnosis and treatment of sleep disorders in children. METHODS: Patients were evaluated by pedodontists to identify dental, skeletal, and functional malocclusion (n = 240; <15 years). In order to determine the sleep and daytime behavior of the patients, pediatric sleep questionnaires (PSQ) were applied. Per results of the PSQ, patients with a mean of ≥ 0.33 were defined as the high-risk group. RESULTS: A total of 25.8% children were in the high-risk group, with the most convex profile, high-angle growth direction, and mandibular retrognathy. The prevalence of habitual snoring, mouth breathing, and dry mouth was 48.4%, 64.5%, and 87.2% among all high-risk children, respectively. CONCLUSION: Convex profile, high-angle growth direction, and retrognathic mandible were determined as risk factors for SDB. The prevalence of dry mouth, mouth breathing, and snoring was higher in the high-risk group.

Accuracy of age estimation with Demirjian and Nolla methods in Eastern Turkish children aged 3-17 years old.

Purpose: Dental age assessment is one of the most reliable methods of chronological age estimation used for criminal, forensic and anthropologic purposes. This study aimed to determine how accurate it was to estimate the chronological age by looking at the dental age measured with the Nolla and Demirjian methods in a Turkish sample, based on the variables of gender and age-group. Materials and methods: A retrospective study was performed on panoramic radiographs of 1587 subjects (774 females and 813 males), aged 3-17 years. The mean dental age according to the Demirjian and Nolla methods were compared to the mean chronological age (CA). Also, the percentage value of prediction of CA was determined by using the both methods. Results: An under-estimation of the chronological age was observed by using Nolla's method (males -0.003, females -0.32, both -0.16) and an over-estimation of the dental age was observed by using Demirjian's method (males 0.61, females 0.75,both 0.68). Conclusion: Nolla's method was more accurate in the CA estimation than Demirjian's method in Eastern Turkish population.

Evaluation of impacted canines' localization and adjacent lateral incisors' root resorption with orthopantomography and cone-beam computed tomography.

OBJECTIVES: In this retrospective study, the frequency and severity of ectopic eruption in the children's permanent canines, changes between the impacted canine parameters on orthopantomography (OPG) taken for routine follow-up were demonstrated. Also, it was aimed to reveal the differences between OPG and cone beam computed tomography (CBCT). METHODS: Ten thousand (5020 girls, 4980 boys) pediatric patient, were retrospectively investigated for the presence of impacted canine radiographically. OPG and CBCT images of 343 pediatric patients (207 girls, 136 boys) detected impacted canines (n = 432) were evaluated in four steps that the angular and linear measurement, position and status relationships with adjacent anatomical structures were investigated. RESULTS: The incidence of impacted canine in children was 3.43% (4.02% girls, 2.73% boys). The percentage of adjacent lateral incisor' resorption was 33%. Although the presence of resorption in lateral incisors in contact with a canine was found to be statistically significant (p = 0.02), there was no statistically significant relationship the follicle size and localization of canine in the transverse plane. When images were compared, it was found that there was a statistically significant difference between CBCT and OPG about the parameter of canine angulation to the midline and parameter of canine angulation to the lateral incisor. CONCLUSIONS: Pediatric dentists should prefer OPG as the first choice for radiographic imaging for the diagnosis of impacted canine at an early age. Follow-up OPGs should be carefully studied with advancing age. The CBCT should be preferred to prevent complications, to view its relationship with adjacent anatomical structures and canine localization in detail.

Evaluation of radix entomolaris in mandibular first and second molars using cone-beam computed tomography and review of the literature.

OBJECTIVES: The aim of the present study is to identify the prevalence of radix entomolaris in mandibular first and second molars and to determine morphological classifications and associations with other root and canals. METHODS: Mandibular first and second molar teeth of 850 Turkish patients were evaluated using cone-beam computed tomography. A total of 2800 mandibular first molars and second molars were screened. The CBCT examination was performed at five different axial levels. The prevalence of total radix entomolaris, unilateral-bilateral, right-left side and gender distributions, and the classification of radix entomolaris's canal configurations were measured. RESULTS: Radix entomolaris was found in 2.9% (n = 25) of the patients and 1.2% (n = 34) of the teeth. The prevalence of radix entomolaris in mandibular first molars was higher than in mandibular second molars (p < 0.01), in males than in females (p < 0.05) and in right side than left side. An additional tubercle was found in 23% of the teeth with radix entomolaris. For buccolingual orientation, Type A canal variation was the highest and Type C canal variation was the lowest. Regarding locations of cervical parts, Type III canal variation was the highest while Type I canal variation was the lowest. CONCLUSIONS: The prevalence of radix entomolaris was lower in the Turkish population than in other Asian populations but, in multiethnic societies, it needs attention. Before starting endodontic treatment, the clinician should examine the radiography thoroughly and apply advanced radiography methods when necessary. Cone-beam computed tomography is a valuable advanced radiography method for assessing such anatomical variations in vivo.