Artificial Intelligence Shows Promise for Interpreting Dental X-Rays
According to research presented at EuroPerio10, the world’s premier congress in periodontology and implant dentistry organized by the European Federation of Periodontology (EFP), a deep learning algorithm (artificial intelligence) successfully detects periodontal disease from 2D bitewing radiographs.
Dr Burak Yavuz mentioned: “Our study shows the potential for artificial intelligence (AI) to automatically identify periodontal pathologies that might otherwise be missed. This could reduce radiation exposure by avoiding repeat assessments, prevent the silent progression of periodontal disease, and enable earlier treatment.”
The neural network discovered 108 furcation defects, 508 cases of dental calculus, 2,215 cases of horizontal bone loss, 340 cases of vertical bone loss, 859 cases of alveolar bone loss, and 2,215 cases of horizontal bone loss. Sensitivity, precision, and F1 score—the weighted average of sensitivity and precision—were used to compare the algorithm’s success in spotting defects to the physician’s evaluation. The best value for sensitivity, precision, and F1 score is 1, and the worst value is 0.
The author also stated: “This study provides a glimpse into the future of dentistry, where AI automatically evaluates images and assists dental professionals to diagnose and treat disease earlier.”