AI Pilot Study Revolutionizes Pulp Stone Detection in Panoramic Radiographies

The study showed the potential of using artificial intelligence (AI)-supported clinical decision-support system software to increase the efficiency and effectiveness of dentists.

"In the near future, the integration of AI-supported clinical decision support systems may augment the capabilities of clinicians in detecting pulp stones and other anomalies on panoramic radiographs, leading to improved treatment outcomes and patient care," the researchers wrote.

Pulp stones, or denticles, are mineralized masses that develop within the pulp chamber or root canals of teeth. While often asymptomatic, pulp stones can pose challenges for dentists during diagnosis and treatment planning, particularly when obscured by surrounding tissues or overlapping structures in traditional radiographic images.

Kaan Orhan, Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Ankara University, Ankara, Turkey, and colleagues aimed to evaluate the effectiveness of employing a deep learning approach for the automated detection of pulp stones in panoramic imaging.

For this purpose, a comprehensive dataset incusing 2409 panoramic radiography images (7564 labels) underwent labeling using the CranioCatch labeling program, developed in Eskişehir, Turkey. The dataset was stratified into three distinct subsets: training (n = 1929, 80% of the total), validation (n = 240, 10% of the total), and test (n = 240, 10% of the total) sets.

A 3 × 3 clash operation was applied to the images to optimize the visual clarity of labeled regions. The YOLOv5 architecture was employed for artificial intelligence modeling, yielding F1, sensitivity, and precision metrics of 0.7892, 0.8026, and 0.7762, respectively, during the evaluation of the test dataset.

Among deep learning-based AI algorithms applied to panoramic radiographs, using numerical identification for detecting pulp stones has achieved remarkable success. The success rates of training models are expected to increase using datasets consisting of larger images.

"The successful application of deep learning algorithms for detecting pulp stone on panoramic radiographs holds significant clinical implications," the researchers wrote.

"Further research optimizing these AI-based tools with larger datasets holds the potential to enhance diagnostic efficiency and accuracy in dental practice."

In conclusion, successful pulp stone detection with automatic deep learning in panoramic radiography represents a significant leap forward in dental imaging technology. This AI pilot study is promising for enhanced diagnostic accuracy, efficiency, and improved patient care in dentistry.

Reference:

Altındağ, A., Bahrilli, S., Çelik, Ö., Bayrakdar, İ. Ş., & Orhan, K. (2023). The Detection of Pulp Stones with Automatic Deep Learning in Panoramic Radiographies: An AI Pilot Study. Diagnostics, 14(9), 890. https://doi.org/10.3390/diagnostics14090890