OBJECTIVES: We propose a YOLOv11-TDSP model for improving the accuracy of dental abnormality detection on panoramic oral X-ray images. METHODS: The SHSA single-head attention mechanism was integrated with C2PSA in the backbone layer to construct a new C2PSA_SHSA attention mechanism. The computational redundancy was reduced by applying single-head attention to some input channels to enhance the efficiency and detection accuracy of the model. A small object detection layer was then introduced into the head layer to correct the easily missed and false detections of small objects. Two rounds of structured pruning were implemented to reduce the number of model parameters, avoid overfitting, and improve the average precision. Before training, data augmentation techniques such as brightness enhancement and gamma contrast adjustment were employed to enhance the generalization ability of the model. RESULTS: The experiment results showed that the optimized YOLOv11-TDSP model achieved an accuracy of 94.5%, a recall rate of 92.3%, and an average precision of 95.8% for detecting dental abnormalities. Compared with the baseline model YOLOv11n, these metrics were improved by 6.9%, 7.4%, and 5.6%, respectively. The number of parameters and computational cost of the YOLOv11-TDSP model were only 12% and 13% of those of the high-precision YOLOv11x model, respectively. CONCLUSIONS The lightweight YOLOv11-TDSP model is capable of highly accurate identification of various dental diseases on panoramic oral X-ray images.
Radiography, Panoramic/methods* ; Humans ; Algorithms ; Tooth Abnormalities/diagnostic imaging*

OBJECTIVES: This study aimed to investigate the clinical characteristics of deciduous fused teeth and their inherited permanent-tooth performance type by using panoramic radiographs. METHODS: A total of 14 404 panoramic radiographs of 3- to 6-year-old children with deciduous dentition were collected from January 2023 to July 2024. The incidence of deciduous fused teeth was observed, and the abnormality of permanent teeth was recorded. SPSS 24.0 software was used for statistical analysis. RESULTS: The incidence of deciduous fused teeth was 3.06% (441/14 404). The order of dental position was as follows: mandibular deciduous incisors and cusp teeth fused (58.18%) > mandibular deciduous central and lateral incisors fused (30.91%) > maxillary deciduous central and lateral incisors fused (8.89%) > deciduous incisors and supernumerary teeth fused (2.02%). Deciduous fused teeth were found in 226 boys and 215 girls, with no significant difference between the sexes (P>0.05). We observed one pair (87.76%, 387/441) and two pairs (12.24%, 54/441) of fused teeth (54/441), respectively. A total of 287 pairs of fusion teeth on the right side more than 208 pairs on the left side, and the difference between them was statistically significant (P<0.01). More fusion teeth existed in mandibular deciduous teeth (443 pairs) than in maxillary ones (54 pairs), and the difference between them was statistically significant (P<0.01). More unilateral deciduous teeth (387 subjects) were found than bilateral ones (54 subjects), and the difference between them was statistically significant (P<0.01). Three types of deciduous fused teeth with inherited permanent teeth were observed as follows: 1) 49.49% (245/495) of inherited permanent teeth was absent, 2) 46.67% (231/495) of inherited permanent teeth was not absent, and 3) the number of fused permanent teeth accounted for 3.84% (19/495). CONCLUSIONS The incidence of deciduous fused teeth was 3.06%, mostly occurring in the lower anterior teeth region, with no gender difference. One pair of fused teeth is commonly observed, more often on the right than the left. These fusions occur more frequently in the mandible than the maxillary, and unilateral cases are more common than bilateral ones. Deciduous fused teeth had a certain impact on inherited permanent teeth. Pediatric dentists should pay attention to and closely observe whether any abnormality exists in the permanent dentition for early detection to prevent the harm caused by deciduous fused teeth.
Humans ; Tooth, Deciduous/abnormalities* ; Male ; Child ; Female ; Child, Preschool ; Dentition, Permanent ; Radiography, Panoramic ; Fused Teeth/diagnostic imaging* ; Incisor/diagnostic imaging* ; Tooth, Supernumerary/diagnostic imaging* ; Incidence ; Mandible

OBJECTIVES: This study aimed to investigate the incidence, imaging characteristics, and clinical manifestations of the eruption failure of deciduous molars using panoramic radiographs to provide a foundation for diagnosis and treatment in this population. METHODS: This study retrospectively reviewed panoramic radiographs of children aged 4-8 years obtained from Stomatology Hospital, Zhejiang University School of Medicine between January 2021 and December 2023. A total of 31 331 subjects were included for the radiographic assessment of the tooth eruption failure of deciduous molars. Incidence, radiographic characteristics, and associated complications were documented. Statistical analysis was performed using SPSS 26.0. RESULTS: The incidence of the eruption failure of deciduous molars among children aged 4-8 years was 0.94% (296/31 331). The rate was 1.55 times higher in females than in males, demonstrating a significant gender difference (P<0.001). Among the affected deciduous molars, mandibular first deciduous molars accounted for 76.4%, followed by the mandibular second deciduous molars (13.8%), and the maxillary deciduous molars collectively comprised 9.8%. The severity of eruption disorders was significantly associated with the mesial and distal tilting of adjacent teeth and elongation of the antagonist (P<0.001). CONCLUSIONS The incidence of the eruption failure of deciduous molars in children aged 4-8 years was 0.94%, with a high prevalence in females and a predilection for the mandible, particularly the mandibular first deciduous molar. For deciduous molars with severe eruption failure, early intervention is crucial to mitigate complications such as malocclusion and space loss.
Humans ; Child ; Child, Preschool ; Tooth, Deciduous/diagnostic imaging* ; Female ; Molar/physiopathology* ; Male ; Retrospective Studies ; Tooth Eruption ; Radiography, Panoramic ; Incidence

OBJECTIVES: This study aims to evaluate the short- to medium-term clinical efficacy of demineralized dentin matrix (DDM) particles applied during the immediate implantation of alveolar bone defects in the posterior region. METHODS: A total of 76 patients with 110 simple taper retentive implants were included in the conducted study and divided into Groups A and B in accordance with the bone grafting materials. Cone beam computed tomography and panoramic radiographs were taken immediately after implant surgery, immediate crown repair, and final follow-up time. The average follow-up time for Groups A and B was recorded. The primary observed clinical indicators were overall survival rate of the implant, bone resorption of the mesial and distal margins of the implant, buccal bone width resorption at the platform level and 1 mm below the platform, and bone height of the implant. Implant complication was a secondary observed clinical indicator. RESULTS: During the 1-to-5-year follow-up observation period, the mean follow-up of Group A was 38.2 months while that of Group B was 39.9 months. In Group A, two implants failed, one of which fractured, and implant overall survival rate was 96.4%. Four implants failed in Group B due to peri-implantitis, and implant overall survival rate was 92.6%. No statistically significant difference in implant overall survival rate was found between the two groups (P>0.05). In Group A, the average bone resorption in the mesial and distal margins of the implants was (1.011±2.047) mm and (0.841±2.183) mm, respectively. In Group B, the average bone resorption of the mesial and distal margins of the implants was (1.546±1.778) mm and (1.431±1.909) mm, respectively. No statistically significant difference was noted between the two groups (P>0.05). In Group A, buccal bone width resorption at the platform level and 1 mm below the platform of the implant was (0.782±2.084) mm and (0.681±2.307) mm, respectively. In Group B, buccal bone width resorption at the platform level and 1 mm below the platform of implant was (1.071±1.474) mm and (0.949±1.909) mm, respectively. No statistically significant difference was found between the two groups (P>0.05). In Group A, the buccal bone height of resorption of the implant was (1.044±2.214) mm. In Group B, the buccal bone height of resorption of the implant was (1.075±1.456) mm. No statistically significant difference in bone height was observed between the two groups (P>0.05). CONCLUSIONS During the 1-to-5-year follow-up observation period, DDM particles can effectively increase the height and width of alveolar bone, and they can achieve the same effect of maintaining alveolar bone contour and bone augmentation compared with deproteinized inorganic calf bone. DDM particles can be used as a potential new bone grafting material for the treatment of bone defects in clinical practice.
Humans ; Follow-Up Studies ; Dentin ; Cone-Beam Computed Tomography ; Dental Implants ; Male ; Female ; Adult ; Alveolar Bone Loss/surgery* ; Middle Aged ; Bone Transplantation ; Radiography, Panoramic ; Dental Implantation, Endosseous/methods* ; Immediate Dental Implant Loading

For patients with partial jaw defects, cysts and dental implants, doctors need to take panoramic X-ray films or manually draw dental arch lines to generate Panorama images in order to observe their complete dentition information during oral diagnosis. In order to solve the problems of additional burden for patients to take panoramic X-ray films and time-consuming issue for doctors to manually segment dental arch lines, this paper proposes an automatic panorama reconstruction method based on cone beam computerized tomography (CBCT). The V-network (VNet) is used to pre-segment the teeth and the background to generate the corresponding binary image, and then the Bezier curve is used to define the best dental arch curve to generate the oral panorama. In addition, this research also addressed the issues of mistakenly recognizing the teeth and jaws as dental arches, incomplete coverage of the dental arch area by the generated dental arch lines, and low robustness, providing intelligent methods for dental diagnosis and improve the work efficiency of doctors.
Humans ; Radiography, Panoramic/methods* ; Cone-Beam Computed Tomography/methods* ; Head ; Image Processing, Computer-Assisted/methods*

Objective To evaluate the accuracy of different convolutional neural networks (CNN),representative deep learning models,in the differential diagnosis of ameloblastoma and odontogenic keratocyst,and subsequently compare the diagnosis results between models and oral radiologists. Methods A total of 1000 digital panoramic radiographs were retrospectively collected from the patients with ameloblastoma (500 radiographs) or odontogenic keratocyst (500 radiographs) in the Department of Oral and Maxillofacial Radiology,Peking University School of Stomatology.Eight CNN including ResNet (18,50,101),VGG (16,19),and EfficientNet (b1,b3,b5) were selected to distinguish ameloblastoma from odontogenic keratocyst.Transfer learning was employed to train 800 panoramic radiographs in the training set through 5-fold cross validation,and 200 panoramic radiographs in the test set were used for differential diagnosis.Chi square test was performed for comparing the performance among different CNN.Furthermore,7 oral radiologists (including 2 seniors and 5 juniors) made a diagnosis on the 200 panoramic radiographs in the test set,and the diagnosis results were compared between CNN and oral radiologists. Results The eight neural network models showed the diagnostic accuracy ranging from 82.50% to 87.50%,of which EfficientNet b1 had the highest accuracy of 87.50%.There was no significant difference in the diagnostic accuracy among the CNN models (P=0.998,P=0.905).The average diagnostic accuracy of oral radiologists was (70.30±5.48)%,and there was no statistical difference in the accuracy between senior and junior oral radiologists (P=0.883).The diagnostic accuracy of CNN models was higher than that of oral radiologists (P<0.001). Conclusion Deep learning CNN can realize accurate differential diagnosis between ameloblastoma and odontogenic keratocyst with panoramic radiographs,with higher diagnostic accuracy than oral radiologists.
Humans ; Ameloblastoma/diagnostic imaging* ; Deep Learning ; Diagnosis, Differential ; Radiography, Panoramic ; Retrospective Studies ; Odontogenic Cysts/diagnostic imaging* ; Odontogenic Tumors

During the automatic reconstruction of panoramic images, the effect of dental arch curve fitting will affect the integrity of the content of the panoramic image. Metal implants in the patient's mouth usually lead to a decrease in the contrast of the panoramic image, which affects the doctor's diagnosis. In this paper, an automatic oral panoramic image reconstruction method was proposed. By calculating key image areas and image extraction fusion algorithms, the dental arch curve could be automatically detected and adjusted on a small number of images, and the intensity distribution of teeth, bone tissue and metal implants on the image could be adjusted to reduce the impact of metal on other tissues, to generate high-quality panoramic images. The method was tested on 50 cases of cone beam computed tomography (CBCT) data with good results, which can effectively improve the quality of panoramic images.
Humans ; Radiography, Panoramic/methods* ; Cone-Beam Computed Tomography/methods* ; Tooth ; Algorithms ; Image Processing, Computer-Assisted/methods*

ABSTRACT Panoramic X-ray is well known to cause DNA damage and induces cellular death. The aim of the present study was to evaluate the cytotoxicity of radiation exposure from panoramic radiography on human buccal mucosa cells by assessing the cell viability using the simple-trypan blue exclusion test. The genotoxicity effect was evaluated by assessing comet assay score. This research included a total of 20 healthy patients who had panoramic radiography for a routine dental examination. Buccal mucosa cells were collected from all participants before X-ray exposure and at 30 min or 24 h after exposure in Groups 1 and 2, respectively, and subjected to a comet assay and trypan blue exclusion test to assess cell viability and DNA damage. Cell viability was calculated as the ratio of live (translucent) to total counted cells. Comet assay output images were analysed using OpenComet software and a visual score by measuring the percentages of tail DNA and summing the visual score, respectively. A statistically significant (p < 0.05) reduce in cell viability was observed at 30 min after exposure, furthermore there is no more reduction after 24 h. Both comet assay measurements showed a significant (p < 0.05) increase in the percentage of tail DNA and visual score at 30 min after exposure, then tend to decrease after 24 h of exposure, although it was not significant (p > 0.05). The results showed that panoramic radiography interfered cell viability and induced DNA damage in buccal mucosa cells within 30 min after exposure, but these effects were ceased after 24 h.
Mouth Mucosa--cytology ; Radiography, Panoramic

Objective To study the accuracy of Nolla method for age estimation of Northern Chinese Han children aged between 5.00 and 14.99 years based on original transformation tables and multiple regression model. Methods A total of 2 000 orthopantomographs （OPGs） were collected from the Hospital of Stomatology, Xi'an Jiaotong University, including 1 000 males and 1 000 females. Development stage of 7 left mandibular permanent teeth （except third molars） was assessed based on Nolla method, then age estimation was conducted through transformation tables and multiple regression model, respectively. Firstly, the development stage results of 7 permanent teeth were added up and the estimated age was obtained through the original transformation tables. Secondly, 80% of the samples （80 males and 80 females in each age group） were randomly selected from 2 000 OPGs as the train set. The chronological age of the selected patients was taken as the dependent variable, while gender and the development stage results of 7 permanent teeth were taken as the independent variable to establish multiple regression model. The remaining 20% of the samples were substituted into the model as the test set, to verify the accuracy of age estimation by multiple regression model. Results Mean chronological ages of males and females were 10.03±0.09 years and 10.01±0.09 years, respectively. The age estimated by original transformation tables showed an overestimation for males （0.18 years on average） and an underestimation for females （0.02 years on average）, with mean absolute error （MAE） of 0.94 years and 0.97 years, respectively. While the results by multiple regression model showed that males were overestimated by 0.06 years on average and females were underestimated by 0.02 years on average. The MAE was 0.66 years and 0.77 years, respectively. Conclusion The Nolla method is suitable for age estimation of Northern Chinese Han children. Compared with the original transformation tables method, the multiple regression model is more accurate for age estimation.
Adolescent ; Age Determination by Teeth ; Asian People ; Child ; Child, Preschool ; China ; Female ; Humans ; Male ; Molar, Third ; Radiography, Panoramic

Objective To discuss a new coding method for individual identification based on oral panoramic tomography, analyze the diversity of different coding modules in nonhomologous images and the consistency and the matching rate of the coding indexes of different coding modules in homologous images, and evaluate the application value of the different modules and the new coding method in individual identification. Methods The oral panoramic tomography images of 1 000 patients with permanent teeth were collected retrospectively. Each patient had two images taken at different times （called the Early database and the Late database according to the chronological order）. Each image was coded according to the designed coding method. A computer program was designed to compare the diversity of different modules, and calculate the diversity and consistency of different coding modules as well as the matching rate of the coding indexes. Results The diversity of the 4 modules that reflected teeth characteristics was much higher than that of other modules in the same database. The highest diversity was noticed in the module of right mandibular teeth in samples of both databases. The coding consistencies of the 4 modules were all above 50%. Besides, 90.2% of the matching rates of indexes of homologous images were over 80%. Conclusion The 4 modules have higher application value in individual identification, especially the right mandibular teeth. The coding method has a certain value in forensic individual identification.
Forensic Dentistry ; Forensic Medicine ; Humans ; Radiography, Panoramic ; Retrospective Studies ; Tooth/diagnostic imaging*