Estimation of Human Age using Machine Learning on Panoramic Radiographs: A Pilot Study for Brazilian Patients

Abstract This paper addresses a relevant problem in Forensic Sciences by integrating radiological techniques with cutting-edge machine learning methodologies to create a non-invasive, efficient, and less examiner-dependent approach for age estimation. We also present a new dataset composed of 12,827 dental panoramic X-ray images that reflect the specific demographic characteristics of the Brazilian population. The proposed approach achieved robust and reliable results, achieving a Test Mean Absolute Error of 3.1 years and an R-squared value of 95.5%. Professional radiologists have validated that our model focuses on critical features for age assessment used in odontology, including pulp chamber dimensions and stages of permanent teeth calcification, even in edentulous cases. The model also relies on information from the mandible, maxillary sinus, and vertebrae, indicating a wide range of anatomical features for decision-making. This study demonstrates the significant potential of AI to revolutionize age estimation in Forensic Science, offering a more accurate, efficient, and universally applicable solution.