Enhancing Caries Detection in Bitewing Radiographs Using YOLOv7.

The study aimed to evaluate the impact of image size, area of detection (IoU) thresholds and confidence thresholds on the performance of the YOLO models in the detection of dental caries in bitewing radiographs. A total of 2575 bitewing radiographs were annotated with seven classes according to the ICCMS™ radiographic scoring system. YOLOv3 and YOLOv7 models were employed with different configurations, and their performances were evaluated based on precision, recall, F1-score and mean average precision (mAP). Results showed that YOLOv7 with 640 × 640 pixel images exhibited significantly superior performance compared to YOLOv3 in terms of precision (0.557 vs. 0.268), F1-score (0.555 vs. 0.375) and mAP (0.562 vs. 0.458), while the recall was significantly lower (0.552 vs. 0.697). The following experiment found that the overall mAPs did not significantly differ between 640 × 640 pixel and 1280 × 1280 pixel images, for YOLOv7 with an IoU of 50% and a confidence threshold of 0.001 (p = 0.866). The last experiment revealed that the precision significantly increased from 0.570 to 0.593 for YOLOv7 with an IoU of 75% and a confidence threshold of 0.5, but the mean-recall significantly decreased and led to lower mAPs in both IoUs. In conclusion, YOLOv7 outperformed YOLOv3 in caries detection and increasing the image size did not enhance the model's performance. Elevating the IoU from 50% to 75% and confidence threshold from 0.001 to 0.5 led to a reduction of the model's performance, while simultaneously improving precision and reducing recall (minimizing false positives and negatives) for carious lesion detection in bitewing radiographs.

Feasibility of deep learning for dental caries classification in bitewing radiographs based on the ICCMS™ radiographic scoring system.

OBJECTIVE: To evaluate the potential of deep learning models for categorization of dental caries in bitewing radiographs based on the International Caries Classification and Management System (ICCMS™) radiographic scoring system (RSS). STUDY DESIGN: In total, 2758 annotated bitewing radiographs were randomly divided into 3 experiments to assess the ResNet-18, -50, -101, and -152. Experiment A tested 4-class ICCMS™-RSS training and validation using Carestream (CS) radiographs; experiment B tested training and validation using CS and VistaScan radiographs; experiment C tested 7-class ICCMS™-RSS training and validation using CS and VistaScan radiographs. The performance matrices and the areas under the receiver operating characteristic curves were analyzed to assess all procedures. RESULTS: In experiment A, ResNet-50 and ResNet-152 were equally accurate (71.11%) and approximately 78% sensitive. The latter presented the highest specificity (56.90%). In experiment B, ResNet-50 presented the highest sensitivity (79.51%) but ResNet-152 had the highest specificity (60.71%). In experiment C, all models markedly underperformed in distinguishing the 7-class ICCMS™-RSS with specificities of 16.46% to 22.41%. They had fewer classification errors in the 4-class classification (28.89%-35.56%) than in the 7-class classification (42.34%-53.06%). The areas under the receiver operating characteristic curves of all models were unanimously comparable. CONCLUSIONS: The ResNet models were able to classify dental caries according to the ICCMS™-RSS with average performances. The models underperformed in complicated classification tasks.

Assessment of YOLOv3 for caries detection in bitewing radiographs based on the ICCMS™ radiographic scoring system.

OBJECTIVES: To assess the feasibility of the YOLOv3 model under the intersection over union (IoU) thresholds of 0.5 (IoU50) and 0.75 (IoU75) for caries detection in bitewing radiographs based on the International Caries Classification and Management System (ICCMS™). MATERIALS AND METHODS: We trained the YOLOv3 model by feeding 994 annotated radiographs with the IoU50 and IoU75 thresholds. The testing procedure (n = 175) was subsequently conducted to evaluate the model's prediction metrics on caries classification based on the ICCMS™ radiographic scoring system. RESULTS: Regarding the 4-class classification representing caries severity, YOLOv3 could accurately detect and classify enamel caries and initial dentin caries (class RA) (IoU50 vs IoU75: precision, 0.75 vs 0.71; recall, 0.67 vs 0.64). Concerning the 7-class classification signifying specific caries depth (class 0, healthy tooth; classes RA1-3, initial caries affecting outer half, inner half of enamel, and the outer 1/3 of dentin; class RB4, caries extending to the middle 1/3 of dentin; classes RC5-6, extensively cavitated caries affecting the inner 1/3 of dentin and involving the pulp chamber), YOLOv3 could accurately detect and classify caries with pulpal exposure (class RC6) (IoU50 vs IoU75: precision, 0.77 vs 0.73; recall, 0.61 vs 0.57) but it failed to predict the outer half of enamel caries (class RA1) (IoU50 vs IoU75: precision, 0.35 vs 0.32; recall, 0.23 vs 0.21). CONCLUSIONS: YOLOv3 yielded acceptable performances in both IoU50 and IoU75. Although the performance metrics decreased in the 7-class detection, the two thresholds revealed comparable results. However, the model could not consistently detect initial-stage caries affecting the outermost surface of the enamel. CLINICAL RELEVANCE: YOLOv3 could be implemented to detect and classify dental caries according to the ICCMS™ classification with acceptable performances to assist dentists in making treatment decisions.