Forensic age estimation based on three-dimensional computed tomography of the chest

In this study, we propose an age prediction model based on chest computed tomography (CT) imaging. The study sample comprised 175 chest CT images from male and female individuals with an age range of 18 to 79 years. The areas assessed included the degree of fusion of the manubriosternal, xiphosternal, and costosternal joints. Differentiation of the fusion stages was performed using a unique scoring scale we developed, supported by reference images illustrating the stages of ossification in sternal synostoses. Based on the results of the regression analysis, a mathematical model for age prediction was developed, yielding a mean absolute error of 7.28 years for both sexes.