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.

Increasing the vertical dimesion affects not only functional problems but also the facial appearance. In particular, when restoring the reduced vertical dimension, it is important to evaluate facial appearance because the change affects the patient’s aesthetics. Cephalometric radiographs can predict changes in the facial appearance through skeletal and vertical classifications using anatomical indicators, and the changes before and after treatment can be easily observed, which could serve as good data in evaluating treatment success. In this study, comparative evaluation was performed through cephalometric radiography, and the aesthetic and functional improvement was confirmed.

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.

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.