This study aimed to investigate which areas AI is sensitive when inputting panoramic radiographs with dental area masked and when inputting unmasked ones. Therefore, the null hypothesis of this study was that masking dental area would not make a difference in the sensitive areas of osteoporosis determination of AI. For this study 1165 female(average age 48.4 ± 23.9 years) from whom panoramic radiographs were taken were selected. Either osteoporosis or normal should be clearly defined by oral and maxillofacial radiologists. The panoramic radiographs from the female were classified as either osteoporosis or normal according to the mandibular inferior cortex shape. VGG-16 model was used to get training, validating, and testing to determine between osteoporosis or normal. Two experiments were performed; one using unmasked images of panoramic radiographs, and the other using panoramic radiographs with dental region masked. In two experiments, accuracy of VGG-16 was 97.9% with unmasked images and 98.6% with dental-region-masked images. In the osteoporosis group, the sensitive areas identified with unmasked images included cervical vertebrae, maxillary and mandibular cancellous bone, dental area, zygomatic bone, mandibular inferior cortex, and cranial base. The osteoporosis group shows sensitivity on mandibular cancellous bone, cervical vertebrae, and mandibular inferior cortex with masked images. In the normal group, when unmasked images were input, only dental region was sensitive, while with masked images, only mandibular cancellous bone was sensitive. It is suggestive that when dental influence of panoramic radiographs was excluded, AI determined osteoporosis on the mandibular cancellous bone more sensitively.

The purpose of this study was to verify the sensitive areas when the AI determines osteoporosis for the entire area of the panoramic radiograph. Panoramic radiographs of a total of 1,156 female patients(average age of 49.0±24.0 years) were used for this study. The panoramic radiographs were diagnosed as osteoporosis and the normal by Oral and Maxillofacial Radiology specialists. The VGG16 deep learning convolutional neural network(CNN) model was used to determine osteoporosis and the normal from testing 72 osteoporosis(average age of 73.7±8.0 years) and 93 normal(average age of 26.4±5.1 years). VGG16 conducted a gradient-weighted class activation mapping(Grad-CAM) visualization to indicate sensitive areas when determining osteoporosis. The accuracy of CNN in determining osteoporosis was 100%. Heatmap image from 72 panoamic radiographs of osteoporosis revealed that CNN was sensitive to the cervical vertebral in 70.8%(51/72), the cortical bone of the lower mandible in 72.2%(52/72), the cranial base area in 30.6%(22/72), the cancellous bone of the mandible in 33.3%(24/72), the cancellous bone of the maxilla in 20.8%(15/72), the zygoma in 8.3%(6/72), and the dental area in 5.6%(4/72). Consideration: it was found that the cervical vertebral area and the cortical bone of the lower mandible were sensitive areas when CNN determines osteoporosis in the entire area of panoramic radiographs.

The aim of this study was to investigate radiographic features of osteosclerosis on digital panoramic radiographs. Osteoscleosis was diagnosed with its radiographic features of amorphous non- expansible radiopacity with unknown etiology. In diagosing osteosclerosis, differential diagnosis is needed from periapical cemental dysplasia, osteoma, benign cementoblastoma, and anatomic structures. Fifty-eight osteosclerosis on digital panoramic radiopgraphs from 46 patients with osteoscleosis were selected for this study. All of the osteosclerosis were found in the mandible. Among them, 53(91.4%) occurred on the posterior region. The mean diameter was 9.1㎜. The internal structure was radiopaque in 39(67.2%) and mixed radiolucent and radiopaque in 19(35.3%). There was no specific effect on the surrounding structures. In 16(27.6%), partial or complete radiolucent margin was noted which might be digital image artifact by enhancement.

This study was performed as a part of serial experiments of applying convolutional neural network(CNN) in determining osteoporosis on panoramic radiograph. The purpose of this study was to investigate how sensitively CNN determine osteoporosis on cropped panoramic radiograph. Panoramic radiographs from 1268 female patients(mean age 45.2 ± 21.1 yrs) were selected for this study. For the osteoporosis group, 633(mean age 72.2 ± 8.5 yrs) were selected, while for the normal group 635(mean age 28.3 ± 7.0 yrs). AlexNet was utilized as CNN in this study. A multiple-column CNN was designed with two rectangular regions of interest on the mandible inferior area. An occluding method was used to analyze the sensitive area in determining osteoporosis on AlexNet. Testing of AlexNet showed accuracy of 99% in determining osteoporosis on panoramic radiographs. AlexNet was sensitive at the area of cortical and cancellous bone of the mandible inferior area including adjacent soft tissue.

To investigate the perceptions and attitudes of dental hygienists toward radiation safety management in Korea. A total of 800 dental hygienists were randomly selected for an anonymous survey, and 203 of them participated. The questionnaire items included the following: sex, career period, type of installed radiographic equipment, recognition of the diagnostic reference level (DRL), participation in radiation safety education, and attitudes toward radiation protection for both patients and dental hygienists. The participants were divided into two groups according to their years of experience (< 10 years versus ≥ 10 years). The difference between the groups was investigated according to frequency distribution. Fisher’s exact test or Pearson’s chi-square (χ2) test was used as appropriate. A regression analysis was performed to investigate the impact of wearing a thyroid collar for personnel protection during patient radiation exposure. The types of installed radiographic equipment included panoramic radiography (96.1%), cephalometric radiography (76.9%), intraoral radiography (72.9%), and cone-beam computed tomography (69.5%). Significant differences were observed in the learning pathway for the DRL (Fisher’s exact test, p < 0.05), satisfaction with radiation safety education (Pearson’s χ2 test = 5.3975, Pr = 0.02), and use of personnel radiation monitoring systems (Pearson’s χ2 test = 18.1233, Pr = 0.000) between the groups. Significant differences were also observed in personnel protection using a thyroid collar and patient protection during panoramic radiography (odds ratio = 14.2). Dental hygienists with more than 10 years of experience were more satisfied with radiation safety education and more interested in radiation monitoring. Considering career experience, customized, continuous, and effective radiation safety management education should be provided.

Deep convolutional network is a deep learning approach to optimize image recognition. This study aimed to apply DCNN to the reading of mandibular cortical thinning in digital panoramic radiographs. Digital panoramic radiographs of 1,268 female dental patients (age 45.2 ± 21.1yrs) were used in the reading of the mandibular cortical bone by two maxillofacial radiologists. Among the subjects, 535 normal subject’s panoramic radiographs (age 28.6 ±7.4 yrs) and 533 those of osteoporosis pationts (age 72.1 ± 8.7 yrs) with mandibular cortical thinning were used for training DCNN. In the testing of mandibular cortical thinning, 100 panoramic radiographs of normal subjects (age 26.6 ± 4.5 yrs) and 100 mandibular cortical thinning (age 72.5 ± 7.2 yrs) were used. The sensitive area of DCNN to mandibular cortical thinning was investigated by occluding analysis. The readings of DCNN were compared by two maxillofacial radiologists. DCNN showed 97.5% accuracy, 96% sensitivity, and 99% specificity in reading mandibular cortical thinning. DCNN was sensitively responded on the cancellous and cortical bone of the mandibular inferior area. DCNN was effective in diagnosing mandibular cortical thinning.

Artificial intelligence, has been applied in interpreting osteoporosis on dental panoramic radiograph with high accuracy. The purpose of this study was to investigate the sensitive area of convolutional neural network(CNN), one of artificial intelligence, in interpreting osteoporosis on dental panoramic radiograph. Dental panoramic radiographs taken from 1,170 female (49.19 ±21.91 average age, 21 minimum age, and 84 maximum age) were selected for this study. Two oral maxillofacial radiologists agreed upon interpreting osteoporosis by interpreting mandibular inferior cortical changes. The region of interest included upper and lower jaws for training and testing CNN in interpreting osteoporosis. A filter which was set to look for image characteristics moved through the entire panoramic radiography to identify sensitive areas that distinguish normal groups and osteoporosis patients. In interpreting osteoporosis on panoramic radiograph, CNN responded sensitively at the cancellous bone of the upper and lower jaws while oral maxillofacial radiologists interpreted mandibular inferior cortical change.

Menton (Me) deviation is commonly used for diagnosing facial asymmetry. This study compared angle and distance measurement in determining the severity of Me deviation for facial asymmetry diagnosis. Three-Dimensional Computed Tomographic(3D CT) images of 32 patients (mean age 22.5yrs, SD 3.4yrs; 16 male, 16 female) with facial asymmetry were selected for this study. Angle and distance of Me deviation in each patient were obtained and the severity of Me deviation was determined according to the angle and the distance measurement. The severity of Me deviation by angle and distance measurement was compared and statistical analysis was performed. Eight (25%) showed disagreement in severity of Me deviation between the two measurements. The kappa coefficient on the two measurements was 0.67, showing substantial agreement. It is suggested that both angle and distance measurement be performed in determining severity of Me deivation.

This study aimed to measure ramal lengths and angles on panoramic radiography applying a polar coordinate system for analyzing facial asymmetry within normal range. Panoramic radiographs taken from 15 males and 15 females (mean age 31.33±3.7 yrs in males and 28.87±2.72 yrs in females) with symmetric-looking faces were selected. The polar coordinate system, length of condylar and ramal height and angles between the ramus tangent and the connecting line of the most inferior point of bilateral orbital rim were measured from panoramic radiographic images. Bilateral differences in the ramal and condylar heights and angles were determined by asymmetric index. The polar coordinate applied for analyzing facial asymmetry uses length and angle measure. The normal range of facial asymmetry was measured using mean and standard deviation of asymmetry index of length and angle measure. A new analysis method using polar coordinate system on panoramic radiograph may provide more accurate analysis for facial asymmetry.

This study was conducted as part of a series of studies to introduce the Convolutional Neural Network(CNN) into the diagnostic field of osteoporosis. The purpose of this study was to compare the results when testing Digital Radiography(DR) and Computed Radiography(CR) panoramic radiographs by CNN that were trained by DR panoramic radiographs. The digital panoramic radiographs of females who visited for the purpose of diagnosis and treatment at Chonnam National University Dental Hospital were taken. Two Oral and Maxillofacial Radiologists were selected for the study to compare the panoramic radiographs with normal and osteoporosis images. Among them, 1068 panoramic radiographs of females{Mean [± standard deviation] age: 49.19 ± 21.91 years} obtained by DR method were used for training of CNN. 200 panoramic radiographs of females{Mean [± standard deviation] age: 63.95 ± 6.45 years} obtained by DR method and 202 panoramic radiographs of females{Mean [± standard deviation] age: 62.00 ± 6.86 years} obtained by CR method were used for testing of CNN. When the DR panoramic radiographs were tested, the Accuracy was 92.5%. When the CR panoramic radiographs were tested, the Accuracy was 76.2%. It can be seen that the CNN trained by DR panoramic radiographs is suitable to be tested with the same DR panoramic radiographs.

This study aimed to test a convolutional neural network (CNN) in two different settings of training and testing data. Panoramic radiographs were selected from 1170 female dental patients (mean age 49.19 ± 21.91 yr). The cortical bone of the mandible inferior border was evaluated for osteoporosis or normal condition on the panoramic radiographs. Among them, 586 patients (mean age 27.46 ± 6.73 yr) had normal condition, and osteoporosis was interpreted on 584 patients (mean age 71.00 ± 7.64 yr). Among them, one data set of 569 normal patients (mean age 26.61 ± 4.60 yr) and 502 osteoporosis patients (mean age 72.37 ± 7.10 yr) was used for training CNN, and the other data set of 17 normal patients (mean age 55.94 ± 4.0 yr) and 82 osteoporosis patients (mean age 62.60 ± 5.00 yr) for testing CNN in the first experiment, while the latter was used for training CNN and the former for testing CNN in the second experiment. The error rate was 15.15% in the first experiment and 5.14% in the second experiment. This study suggests that age-matched training data make more accurate testing results.

This study aimed to compare chin deviation in angle measurement on posteroanterior(PA) cephalogram and computed tomography (CT). Chin deviation was assessed as menton(Me) deviation in angle measurement on PA cephalogram and CT images of 35 patients who had orthognathic surgery (19 male and 16 female with average age of 22.1±3.33yr). The difference between the Me deviation was calculated and statistical analysis was performed to compare the deviation direction and asymmetry severity on the two imaging modalities. There was statistically significant difference in the difference of Me deviation between PA cephalogram and CT by one-simple t-test (p<.05). The mean difference of Me deviation was 2.21°± 1.84°. The maximum difference of Me deviation was 8.64°. There were statistical agreements in the deviation direction (k =0.82, p<.05) and in the severity of facial asymmetry (k =0.37, p<.05). The difference of the deviation direction was detected in 2 patients (5.71 %). The difference of the severity of facial asymmetry was in 15 patients (42.86%). The chin deviation in angle measurement might be different between PA cephalogram and CT in some patients.

This study aimed to compare the mandible inferior cortical bone thickness before and after orthognathic surgery on panoramic radiographs. Among 1092 orthognathic surgery patients, 37(12male, 25 female, average age 23.8 yrs± 4.4) were selected who underwent mandible inferior cortex contouring. The total mandible sides which underwent inferior cortex contouring were 62. The mandible inferior cortical bone thickness was measured below the mesial root of the first molar tooth. The mandible inferior cortical bone thickness was 3.49mm± 0.6mm before orthognathis surgery and 1.92 mm± 0.88 mm after surgery, with statistically significant difference between the two(p<.05). The mean contouring amount was 1.57 mm± 0.8 mm. Mandible inferior cortex contouring are often included in orthognathic surgery.

The purpose of this study is to evaluate the clinical and radiographic features of Bisphosphonate-related osteonecrosis of the jaws(BRONJ). The clinical and radiographic features of 27 patients diagnosed with BRONJ from 2008 to 2012 were evaluated on the basis of the charts and panoramic radiographs and cone beam computed tomographs. As for clinical features, the following contents were evaluated; type of dental treatments before occurrence of BRONJ, the cause of taking bisphosphonate medicine, undergoing dental treatment, interval between dental treatments and symptom expression. As for radiological features, location of BRONJ, size of bone destructions and sclerosing of the surrounding bone, locational relationship between mandibular canal and inferior border of bone destruction, and effect on the maxillary sinus. In clinical features, extraction was done in 18 patients(66.7%), as the most common dental treatment before occurrence of BRONJ. The most common cause of taking bisphosphonate medicine was osteoporosis(20 pateints, 70.4%). The patients treated during bisphosphonate administration was 17(63.0%). The interval between dental treatments and symptom in the most patients(14 patients, 51.8%) was within 1 month. In radiological features, sequestrum was seen in 11 patients(40.7%) and bony sclerosing in 15(55.6%). The mean width of sclerosing was 32.9±12.4mm and mean height 17.5±4.4mm. Bone destruction invaded to inferior border of mandibular canal in 88.2%(15 among 17 mandibles),. Maxillary sinusitis was diagnosed in 57.1% among the evaluated maxillae(4 among 11 maxillae). In diagnosing BRONJ, clinicians should be cautious about medical history of patients and have well-knowledge of radiographic features.

The maxillofacial region is susceptible to damage because facial bone is prominent. The aim of this study is to evaluate the incidence, etiology, seasonal distribution, and patterns of maxillofacial injuries and investigate the percentage of bone fractures on CT scans by patient’s gender and age. Electronic medical records of 1,483 patients who had maxillofacial injuries and visited the Emergency Medical Center of Chonnam National Hospital were evaluated. Age, gender, etiology, seasonal occurrence, frequency of fracture, and the pattern of bone fracture were analyzed by using IBM SPSS Statistics 21 (SPSS Inc., Chicago, IL, USA). Male to female ratio was 2.82:1. The most common causes of injury were falls or collisions (male 40.09%, female 48.2%), followed by traffic accidents and violence. The number of injuries related to sporting accidents, assult, and industrial accidents was higher in male patients than that of female patients. With regard to the seasonal occurrence, 434 cases (29.26%) occurred in the summer, while 306 cases (20.63%) occurred in the winter. In this study, 946 patients (63.79%) were identified to have facture and 537 patients (36.21%) were found to be without fracture on CT scans. The orbital bone (41.38%) was the most commonly fractured in the mid facial structures. The most common fracture site in the mandible was the body of the mandible (23.13%). The patterns of maxillofacial injuries were various based on gender, age, cause of injury, and season.

Objective: The aim of this study was to analyze factors indicating preventive removal of mandibular third molars by determining associated symptoms, pathologies, eruption state, position and angulation types of mandibular third molars. Study design: A retrospective study was made of 436 patients(200 females, 236 males), aged between 12 and 81 years (mean: 29.93 years) undergoing panoramic radiographic examinations. Total 700 mandibular third molars were analyzed. They were divided by age, sex, position and angulation of mandibular third molars, bony coverage, and associated pathologies- caries, pericoronitis, periodontitis, cyst, root resorption of adjacent teeth. Results: Among 409 pathologies associated with mandibular third molars, pericoronitis accounted for 34.2%(140 cases), which was the most common lesion, caries in the second and third molars for 28.9%, caries in the second molars for 11%(45 cases). Periodontitis showed in 7%(29 cases). In 4 cases, root resorption of adjecent tooth showed. The position which showed predominant pathologic lesion according to the Pell and Gregory classification was ⅡA(86.5%), followed by ⅡB(71.6%). Mandibular third molars without bony coverage(64.8%) showed pathologies frequently. Conclusions: The removal of mandibular third molars must be determined by the perceived risk if the teeth are not removed. The position and inclination of the third molars, bony coverage, age and sex of patients can be the important evidence in the decision making process.