Purpose It has been proposed that using new prediction methods, such as neural networks based on dental data, could improve age estimation. This study aimed to assess the possibility of exploiting neural networks for estimating age by means of the pulp-to-tooth ratio in canines as a non-destructive, non-expensive, and accurate method. In addition, the predictive performance of neural networks was compared with that of a linear regression model. Materials and Methods Three hundred subjects whose age ranged from 14 to 60 years and were well distributed among various age groups were included in the study. Two statistical software programs, SPSS 21 (IBM Corp., Armonk, NY, USA) and R, were used for statistical analyses. Results The results indicated that the neural network model generally performed better than the regression model for estimation of age with pulp-to-tooth ratio data. The prediction errors of the developed neural network model were acceptable, with a root mean square error (RMSE) of 4.40 years and a mean absolute error (MAE) of 4.12 years for the unseen dataset. The prediction errors of the regression model were higher than those of the neural network, with an RMSE of 10.26 years and a MAE of 8.17 years for the test dataset. Conclusion The neural network method showed relatively acceptable performance, with an MAE of 4.12 years. The application of neural networks creates new opportunities to obtain more accurate estimations of age in forensic research.

In maxillofacial imaging, cone beam computed tomography (CBCT) is currently the modality of choice for assessment of bony structures of the temporomandibular joint (TMJ). Factors affecting the quality of CBCT images can change its diagnostic accuracy. This study aimed to assess the effect of field of view (FOV) and defect size on the accuracy of CBCT scans for detection of bone defects of the TMJs. This study was conducted on 12 sound TMJs of 6 human dry skulls. Erosions and osteophytes were artificially induced in 0.5, 1, and 1.5-mm sizes on the anterior-superior part of the condyle; CBCT scans were obtained with 6, 9, and 12-inch FOVs by NewTom 3G CBCT system. Two maxillofacial radiologists evaluated the presence/absence and type of defects on CBCT scans. The Cohen kappa was calculated to assess intra- and interobserver reliability. The Mann-Whitney U test was applied to compare the diagnostic accuracy of different FOVs.In comparison of 6- and 12-inch, 9- and 12-inch FOVs in detection of different sizes of erosive lesions, difference was significant (P <0.05), whereas difference between 6- and 9 inch just in 0.5-mm erosive lesion was significant (P = 0.04). In comparison of 6- and 12-inch FOVs in detection of different sizes of osteophyte lesion, difference was significant (P < 0.05), whereas between 6- and 9-inch FOVs statistically significant difference was not observed (P > 0.05). The highest and the lowest diagnostic accuracy of CBCT scans for condyle defects were obtained with 6-inch and 12-inch FOVs, respectively. Diagnostic accuracy of CBCT scans increased with an increase in size of bone defects.