Search

The developmental patterns of the pelvic epiphyses are one of the anatomical markers used in the assessment of skeletal age and the legally relevant age threshold. In this study, four regression models and five classification models were developed for forensic age estimation and the determination of the 18-year threshold, respectively. A total of 2137 conventional pelvic radiographs (1215 males and 922 females) aged 10.00-25.99 years were analyzed, and the ossification and fusion of the iliac crest and ischial tuberosity epiphyses were scored separately. The epiphyses on both sides were used as inputs for all models. The accuracy of the regression models was compared using the mean absolute error (MAE) and root mean square error. The percentages of correct classifications were evaluated for the determination of the 18-year threshold. Support vector regression (SVR) and gradient boosting regression (GBR) showed higher accuracy for age estimation in both sexes. The lowest MAE was 1.38 years in males when using SVR and 1.16 years in females when using GBR. In the demarcation of minors and adults, the percentage of correct classification was over 92%, and the area under the receiver operating characteristic curves was over 0.91 in all models, except the Bernoulli naive Bayes classifier. This study demonstrated that the present models may be helpful for age estimation and the determination of the 18-year threshold. However, owing to the high effective dose of ionizing radiation used during conventional radiography of the pelvis, it is expected that these models will be tested with pelvic MRI for age estimation., Competing Interests: Declaration of Competing Interest None., (Copyright © 2020 Elsevier B.V. All rights reserved.)

Purpose: To develop a deep learning bone age assessment model based on pelvic radiographs for forensic age estimation and compare its performance to that of the existing cubic regression model., Materials and Method: A retrospective collection data of 1875 clinical pelvic radiographs between 10 and 25 years of age was obtained to develop the model. Model performance was assessed by comparing the testing results to estimated ages calculated directly using the existing cubic regression model based on ossification staging methods. The mean absolute error (MAE) and root-mean-squared error (RMSE) between the estimated ages and chronological age were calculated for both models., Results: For all test samples (between 10 and 25 years old), the mean MAE and RMSE between the automatic estimates using the proposed deep learning model and the reference standard were 0.94 and 1.30 years, respectively. For the test samples comparable to those of the existing cubic regression model (between 14 and 22 years old), the mean MAE and RMSE for the deep learning model were 0.89 and 1.21 years, respectively. For the existing cubic regression model, the mean MAE and RMSE were 1.05 and 1.61 years, respectively., Conclusion: The deep learning convolutional neural network model achieves performance on par with the existing cubic regression model, demonstrating predictive ability capable of automated skeletal bone assessment based on pelvic radiographic images., Key Points: • The pelvis has considerable value in determining the bone age. • Deep learning can be used to create an automated bone age assessment model based on pelvic radiographs. • The deep learning convolutional neural network model achieves performance on par with the existing cubic regression model.