Detection of periodontal bone loss patterns and furcation defects from panoramic radiographs using deep learning algorithm: a retrospective study.

BACKGROUND: This retrospective study aimed to develop a deep learning algorithm for the interpretation of panoramic radiographs and to examine the performance of this algorithm in the detection of periodontal bone losses and bone loss patterns. METHODS: A total of 1121 panoramic radiographs were used in this study. Bone losses in the maxilla and mandibula (total alveolar bone loss) (n = 2251), interdental bone losses (n = 25303), and furcation defects (n = 2815) were labeled using the segmentation method. In addition, interdental bone losses were divided into horizontal (n = 21839) and vertical (n = 3464) bone losses according to the defect patterns. A Convolutional Neural Network (CNN)-based artificial intelligence (AI) system was developed using U-Net architecture. The performance of the deep learning algorithm was statistically evaluated by the confusion matrix and ROC curve analysis. RESULTS: The system showed the highest diagnostic performance in the detection of total alveolar bone losses (AUC = 0.951) and the lowest in the detection of vertical bone losses (AUC = 0.733). The sensitivity, precision, F1 score, accuracy, and AUC values were found as 1, 0.995, 0.997, 0.994, 0.951 for total alveolar bone loss; found as 0.947, 0.939, 0.943, 0.892, 0.910 for horizontal bone losses; found as 0.558, 0.846, 0.673, 0.506, 0.733 for vertical bone losses and found as 0.892, 0.933, 0.912, 0.837, 0.868 for furcation defects (respectively). CONCLUSIONS: AI systems offer promising results in determining periodontal bone loss patterns and furcation defects from dental radiographs. This suggests that CNN algorithms can also be used to provide more detailed information such as automatic determination of periodontal disease severity and treatment planning in various dental radiographs.

The effect of mentoplate application on the condyle.

BACKGROUND: The aim of the study was to investigate the changes occurring in the mandibular condyle by using mentoplate together with rapid maxillary expansion (MP-RME) treatment in the correction of skeletal class III relationship, using fractal analysis (FA). METHODS: The sample consisted of 30 individuals (8-11 years) diagnosed with skeletal Class III malocclusion who underwent MP-RME treatment. Archival records provided cone-beam computed tomography (CBCT) images taken at two intervals: before MP-RME treatment (T0) and after treatment (T1). The CBCT images were obtained using standardized settings to ensure consistency in image quality and resolution. The trabecular structures in the bilateral condyles at both T0 and T1 were analyzed using FA. The FA was performed on these condylar images using the Image J software. The region of interest (ROI) was carefully selected in the condyle to avoid overlapping with cortical bone, and the box-counting method was employed to calculate the fractal dimension (FD). Statistical analysis was conducted to compare the FD values between T0 and T1 and to evaluate gender differences. The statistical significance was determined using paired t-tests for intra-group comparisons and independent t-tests for inter-group comparisons, with a significance level set at p < 0.05. RESULTS: The analysis revealed no statistically significant differences in the trabecular structures of the condyles between T0 and T1 (p > 0.05). However, a significant gender difference was observed in FA values, with males exhibiting higher FA values in the left condyle compared to females at both T0 and T1 (p < 0.05). Specifically, the FA values in the left condyle increased from a mean of 1.09 ± 0.09 at T0 to 1.13 ± 0.08 at T1 in males, whereas in females, the FA values remained relatively stable with a mean of 1 ± 0.09 at T0 and 1.03 ± 0.11 at T1. CONCLUSION: The findings indicate that MP-RME therapy does not induce significant alterations in the trabecular structure of the mandibular condyle. These results suggest the treatment's safety concerning the structural integrity of the condyle, although the observed gender differences in FA values warrant further investigation.

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.