AI detects pulpal calcifications on BW radiographs
1. Title:
Detection of pulpal calcifications on bite-wing radiographs using deep learning
2. Authors:
Fatma Yuce; Muhammet Üsame Öziç; Melek Tassoker
3. Summary:
This research article investigates the use of the YOLOv4 deep learning algorithm to automate the identification of pulpal calcifications within dental bite-wing radiographs. By training the model on 2,000 images labeled by expert radiologists, the study sought to create a reliable clinical decision support system for dentists. The results demonstrated that the artificial intelligence achieved high accuracy and precision in both locating pulp chambers and detecting the presence of calcified masses. This technology is particularly significant because pulp stones can complicate root canal treatments and lead to procedural errors if not identified beforehand. Ultimately, the authors conclude that deep learning can effectively assist practitioners by providing a diagnostic performance that rivals human expertise.
**4. Key Words:**Artificial intelligence; Bite-wing; Deep learning; Pulpal calcification; YOLOv4
5. Extracted data
5.1. Year: 2023
5.2. Modality: Bite-wing radiography (2D intraoral X-ray)
5.3. Dataset: 2,000 bite-wing radiographs
5.4. Dataset Split: Training: 80% (1,600 images); Validation: 10% (200 images); Testing: 10% (200 images).
5.5. Network Architecture: YOLOv4
5.6. Metrics: Recall, Precision, Specificity, F1-score, Accuracy, Intersection over Union (IoU), Mean Average Precision (mAP), Confidence score.
5.7. AP - Professional Qty: 2
5.8. AP - Supervisor Presence: No (consensus)
5.9. AP - Experience Level: 11 years; 3 years
5.10. AP - Expertise Area: OMFR (Oral and Maxillofacial Radiology)
5.11. AP - Tool or System: MakeSense
5.12. ML Task: Object Detection
5.13. Project Objective: To develop and validate a deep learning model capable of automatically detecting pulp chambers and identifying the presence of pulpal calcifications on bite-wing radiographs.
6. Clinical Relevance: Automatic detection of pulpal calcifications can support dentists and non-specialists by improving diagnostic accuracy, reducing procedural complications during endodontic treatments, and functioning as a decision support system in dental radiology.
