The determination of individuals' dental ages through panoramic radiographs using artificial intelligence algorithms

Objective: In our study, we aimed to perfom automatic estimation of dental age through panoramic radiographs using artificial intelligence algorithms in an attempt to overcome the such disadvantages as observer subjectivity affecting classical age estimation methods, the methods relying on time-consuming and labor-intensive manual measurements, and the challenges seen in routine clinical application due to sample sizes. Method: In our study, all patients between the ages of 6 and 15 who had panoramic radiographs between March 1, 2020 and March 1, 2022 in the archive of Pamukkale University Faculty of Dentistry, Department of Oral, Dental and Maxillofacial Radiology were included. Feature extraction was performed based on the data consisting of panoramic radiographs and patient records of the 622 individuals in our dataset using Two-Dimensional Deep Convolutional Neural Network (2D-DCNN) and One-Dimensional Deep Convolutional Neural Network (1D-DCNN) techniques. For age estimation using the extracted features, Genetic Algorithm and Random Forest Algorithm were modified, combined, and referred to as Modified Genetic-Random Forest Algorithm (MG-RF). The performance of the system was analyzed based on the calculated MSE, MAE, RMSE, and R2 values during the implementation of the code. Results: While MSE value was found to be 0,00027, MAE value was 0,0079, RMSE was 0,0888 and R2 was 0,999. Conclusion: It can be concluded that our study has demonstrated an effective performance in age determination given the acceptable difference of ± 1.00 year between estimated dental age and chronological age from birth to adolescence in forensic sciences. Therefore, we believe that the system employed in our study may have the potential to be used in the future within the scope of forensic sciences.