Age estimation using pulp/enamel volume ratio of impacted mandibular third molars measured on CBCT images in a northern Chinese population.

The present study aims to evaluate the relation between chronological age and the ratio of pulp volume (PV) to enamel volume (EV) of impacted mandibular third molars (IMTMs) by using cone-beam computed tomography (CBCT) images and an improved 3D image segmentation technique. A sample of CBCT images of IMTM was collected from 414 northern Chinese subjects (214 male and 200 female clinical patients) ranging in age from 20 to 65 years. The GrowCut effect image segmentation (GCEIS) module algorithm was used to calculate the PV and EV from CBCT images. The total sample was divided into a training group and validation group in a ratio of 7 to 3. The PV/EV ratio (PEr) in the training sample was used to develop a mathematical formula for age estimation as follows: age = - 5.817-21.726 × Ln PEr (p < 0.0001) (Ln, natural logarithm). The mean absolute error (MAE) and root mean square error (RMSE) were used to determine the precision and accuracy of the mathematical formula in the validation group and all samples. The MAEs in the male, female, and pooled gender samples were 9.223, 7.722, and 8.41, respectively, and the RMSEs in the male, female, and pooled gender samples were 10.76, 9.58, and 9.986, respectively. The precise and accurate results indicate that the PEr of IMTM in CBCT images is a potential index for dental age estimation and is possible to be used in forensic medicine.

Leverage Effective Deep Learning Searching Method for Forensic Age Estimation.

Dental age estimation is extensively employed in forensic medicine practice. However, the accuracy of conventional methods fails to satisfy the need for precision, particularly when estimating the age of adults. Herein, we propose an approach for age estimation utilizing orthopantomograms (OPGs). We propose a new dental dataset comprising OPGs of 27,957 individuals (16,383 females and 11,574 males), covering an age range from newborn to 93 years. The age annotations were meticulously verified using ID card details. Considering the distinct nature of dental data, we analyzed various neural network components to accurately estimate age, such as optimal network depth, convolution kernel size, multi-branch architecture, and early layer feature reuse. Building upon the exploration of distinctive characteristics, we further employed the widely recognized method to identify models for dental age prediction. Consequently, we discovered two sets of models: one exhibiting superior performance, and the other being lightweight. The proposed approaches, namely AGENet and AGE-SPOS, demonstrated remarkable superiority and effectiveness in our experimental results. The proposed models, AGENet and AGE-SPOS, showed exceptional effectiveness in our experiments. AGENet outperformed other CNN models significantly by achieving outstanding results. Compared to Inception-v4, with the mean absolute error (MAE) of 1.70 and 20.46 B FLOPs, our AGENet reduced the FLOPs by 2.7×. The lightweight model, AGE-SPOS, achieved an MAE of 1.80 years with only 0.95 B FLOPs, surpassing MobileNetV2 by 0.18 years while utilizing fewer computational operations. In summary, we employed an effective DNN searching method for forensic age estimation, and our methodology and findings hold significant implications for age estimation with oral imaging.