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.

Morphometric and morphological evaluation of mastoid emissary canal using cone-beam computed tomography.

OBJECTIVES: This study aimed to determine mastoid emissary canal's (MEC) and mastoid foramen (MF) prevalence and morphometric characteristics on cone-beam computed tomography (CBCT) images to underline its clinical significance and discuss its surgical consequences. METHODS: In the retrospective analysis, two oral and maxillofacial radiologists analyzed the CBCT images of 135 patients (270 sides). The biggest MF and MEC were measured in the images evaluated in MultiPlanar Reconstruction (MPR) views. The MF and MEC mean diameters were calculated. The mastoid foramina number was recorded. The prevalence of MF was studied according to gender and side of the patient. RESULTS: The overall prevalence of MEC and MF was 119 (88.1%). The prevalence of MEC and MF is 55.5% in females and 44.5% in males. MEC and MF were identified as bilateral in 80 patients (67.20%) and unilateral in 39 patients (32.80%). The mean diameter of MF was 2.4 ± 0.9 mm. The mean height of MF was 2.3 ± 0.9. The mean diameter of the MEC was 2.1 ± 0.8, and the mean height of the MEC was 2.1 ± 0.8. There is a statistical difference between the genders (p = 0.043) in foramen diameter. Males had a significantly larger mean diameter of MF in comparison to females. CONCLUSION: MEC and MF must be evaluated thoroughly if the surgery is contemplated. Radiologists and surgeons should be aware of mastoid emissary canal morphology, variations, clinical relevance, and surgical consequences while operating in the suboccipital and mastoid areas to avoid unexpected and catastrophic complications. CBCT may be a reliable imaging diagnostic technique.