Forensic Dental Age Estimation Using Modified Deep Learning Neural Network

Abstract

Dental age is one of the most reliable methods to identify an individual’s age. By using dental panoramic radiography (DPR) images, physicians and pathologists in forensic sciences try to establish the chronological age of individuals with no valid legal records or registered patients. The current methods in practice demand intensive labor, time, and qualified experts. The development of deep learning algorithms in the field of medical image processing has improved the sensitivity of predicting truth values while reducing the processing speed of imaging time. This study proposed an automated approach to estimate the forensic ages of individuals ranging in age from 8 to 68 using 1332 DPR images. Initially, experimental analyses were performed with the transfer learning-based models, including InceptionV3, DenseNet201, EfficientNetB4, MobileNetV2, VGG16, and ResNet50V2; and accordingly, the best-performing model, InceptionV3, was modified, and a new neural network model was developed. Reducing the number of the parameters already available in the developed model architecture resulted in a faster and more accurate dental age estimation. The performance metrics of the results attained were as follows: mean absolute error (MAE) was 3.13, root mean square error (RMSE) was 4.77, and correlation coefficient R2 was 87%. It is conceivable to propose the new model as potentially dependable and practical ancillary equipment in forensic sciences and dental medicine.

Keywords

• Dental age
• Deep learning
• Dental panoramic radiograph
• Forensic odontology
• InceptionV3
• Regression.

References

1. [1] E. Sironi et al. ‘Age estimation by assessment of pulp chamber volume: a bayesian network for the evaluation of dental evidence’, International Journal of Legal Medicine, 2018, vol. 132, no. 4, pp. 1125–1138.
2. [2] J. Lu, V. E. Liong, and J. Zhou, ‘Cost-sensitive local binary feature learning for facial age estimation’, IEEE Transactions on Image Processing, 2015, vol. 24, no. 12, pp. 5356–5368.
3. [3] A. Schmeling, and S. Black, ‘An introduction to the history of age estimation in the living. Age Estimation in the Living’, Chichester, UK. John Wiley & Sons Ltd, 2010, pp. 1–18.
4. [4] A. Olze et al. ‘Assessment of the radiographic visibility of the periodontal ligament in the lower third molars for the purpose of forensic age estimation in living individuals’, International journal of legal medicine, 2010, vol. 124, no. 5, pp. 445–448.
5. [5] R.B. Bassed, C. Briggs, and O.H. Drummer ‘Age estimation and the developing third molar tooth: an analysis of an australian population using computed tomography’, Journal of forensic sciences, 2011, vol. 56, no. 5, pp. 1185–1191.
6. [6] K.A. Kasper et al. ‘Reliability of third molar development for age estimation in a texas hispanic population: a comparison study’, Journal of forensic sciences, 2009, vol. 54, no. 3, pp. 651–657.
7. [7] L. Cular et al. ‘Dental age estimation from panoramic x-ray images using statistical models’, In: Proceedings of the 10th International Symposium on Image and Signal Processing and Analysis IEEE, 2017, pp. 25–30.
8. [8] D. Tabakcilar, R. Bundak, and K. Gencay, ‘Dental age in precocious and delayed puberty periods’, European Journal of Dentistry, 2021, vol. 15, no. 3, pp. 539–545.

9. [9] A. Demirjian, H. Goldstein, and J.M. Tanner, ‘A new system of dental age assessment’, Human biology, 1973, pp. 211–227.
10. [10] Y.C. Guo et al. ‘Accurate age classification using manual method and deep convolutional neural network based on orthopantomogram images’, International Journal of Legal Medicine, 2021, vol. 135, no. 4, pp. 1589–1597.
11. [11] M.I. Razzak, and S. Naz, ‘Microscopic blood smear segmentation and classification using deep contour aware cnn and extreme machine learning’ In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2017, pp. 49–55.
12. [12] İ. Ataş, ‘Performance Evaluation of Jaccard-Dice Coefficient on Building Segmentation from High Resolution Satellite Images’ Balkan Journal of Electrical and Computer Engineering, 2023, vol. 11, no. 1, pp. 100-106. https://doi.org/10.17694/bajece.1212563
13. [13] C. Özdemir, ‘Classification of Brain Tumors from MR Images Using a New CNN Architecture’, Traitement du Signal, 2023, vo. 40, no. 2, pp. 611-618. https://doi.org/10.18280/ts.400219
14. [14] M. Ataş, M.İ. Yeşilnacar, and A. Demir Yetiş, ‘Novel machine learning techniques based hybrid models (LR-KNN-ANN and SVM) in prediction of dental fluorosis in groundwater’, Environmental Geochemistry and Health, 2022, vol. 44, no. 11, pp. 3891-3905.
15. [15] C. Özdemi̇r, M. Ataş, and A.B. Özer, ‘Classification of Turkish spam e-mails with artificial immune system’, 21st Signal Processing and Communications Applications Conference (SIU), 2013, pp. 1-4.
16. [16] Y. Doğan, ‘A new global pooling method for deep neural networks: Global average of top-k max-pooling’, Traitement du Signal, 2023, vo. 40, no. 2, pp. 577-587. https://doi.org/10.18280/ts.400216
17. [17] M. Castelluccio et al. ‘Land use classification in remote sensing images by convolutional neural networks’, 2015, arXiv preprint arXiv:1508.00092.
18. [18] M. Stepanovsk`y et al. ‘Novel age estimation model based on development of permanent teeth compared with classical approach and other modern data mining methods’, Forensic science international, 2017, vol. 279, pp. 72–82.
19. [19] B. Hemalatha, and N. Rajkumar, ‘A versatile approach for dental age estimation using fuzzy neural network with teaching learning-based optimization classification’, Multimedia Tools and Applications, 2020, vol. 79, no. (5-6), pp. 3645–3665.
20. [20] J. Tao et al. ‘Dental age estimation: a machine learning perspective’, In: International Conference on Advanced Machine Learning Technologies and Applications, 2019, pp. 722–733.
21. [21] D. Back et al. ‘Forensic age estimation with bayesian convolutional neural networks based on panoramic dental x-ray imaging’ Proceedings of Machine Learning Research, 2019, pp. 1-4.
22. [22] J. Kim et al. ‘Development and validation of deep learning-based algorithms for the estimation of chronological age using panoramic dental x-ray images’, Proc. Mach. Learn. Res., 2019.
23. [23] M.K. Asif et al. ‘Dental age estimation in malaysian adults based on volumetric analysis of pulp/tooth ratio using cbct data’ Legal Medicine, 2019, vol. 36, pp. 50–58.
24. [24] M. Farhadian, F. Salemi, S. Saati, and N. Nafisi, ‘Dental age estimation using the pulp-to-tooth ratio in canines by neural networks’, Imaging science in dentistry, 2019, vol. 49, no. 1, pp. 19–26.
25. [25] E.H. Houssein, N. Mualla, and M. Hassan, ‘Dental age estimation based on x-ray images’ Computers, Materials & Continua, 2020, vol. 62, no. 2, pp. 591–605.
26. [26] W. Yu et al. ‘Automatic classification of leukocytes using deep neural network’, In: 2017 IEEE 12th International Conference on ASIC (ASICON), 2017, pp. 1041–1044.
27. [27] C. Szegedy et al. ‘Rethinking the inception architecture for computer vision’, In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 2818–2826.
28. [28] M. Sandler et al. ‘Mobilenetv2: Inverted residuals and linear bottlenecks’, In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 4510–4520.
29. [29] I. Bello et al. ‘Revisiting resnets: Improved training and scaling strategies’, Advances in Neural Information Processing Systems, 2021, vol. 34, pp. 22614–22627.
30. [30] M. Tan, and Q. Le, ‘Efficientnet: Rethinking model scaling for convolutional neural networks’, In: International Conference on Machine Learning, 2019, pp. 6105–6114.
31. [31] K. Simonyan, and A. Zisserman, ‘Very deep convolutional networks for largescale image recognition’ arXiv preprint arXiv:1409.1556, 2014.
32. [32] G. Huang et al. ‘Densely connected convolutional networks’ In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 4700–4708.
33. [33] O.J. Babajan, R. Bagherpour, ‘Estimating the wear rate of diamond cutting wire bead in building stone cutting using svr and ga mlp system’, Springer, 2022, pp. 1–13.
34. [34] R.R. Selvaraju et al. ‘Grad-cam: Visual explanations from deep networks via gradient-based localization’ In: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 618–626.
35. [35] M. Zaborowicz et al. ‘Deep learning neural modelling as a precise method in the assessment of the chronological age of children and adolescents using tooth and bone parameters’ Sensors, 2022, vol. 22, no.2, p. 637.
36. [36] N. Vila-Blanco, M.J. Carreira, P. Varas-Quintana, C. Balsa-Castro, I. Tomas, ‘Deep neural networks for chronological age estimation from opg. images‘, IEEE transactions on medical imaging, 2020, vol. 39, no. 7, p. 2374–2384.
37. [37] J.L. Prieto, E. Barberia, R. Ortega, C. Magana, ‘Evaluation of chronological age based on third molar development in the spanish population‘, International journal of legal medicine, Springer, 2005, vol. 119, no. 6, p. 349–354.