An evaluation of statistical models for age estimation and the assessment of the 18-year threshold using conventional pelvic radiographs

Bone age assessment based on different MRI modalities of the proximal humerus epiphysis: the comparisons of T1WI, T2WI, and PDWI

Bone age assessment (BAA) is crucial in various fields, including legal proceedings, athletic competitions, and clinical medicine. However, the use of X-ray methods for age estimation without medical indication is subject to ethical debate, especially in forensic and athletic fields. The application of magnetic resonance imaging (MRI) with non-ionizing radiation can overcome this limitation in BAA. This study aimed to compare the application value of several MRI modalities of proximal humeral in BAA. A total of 468 patients with shoulder MRIs were retrospectively collected from a Chinese Han population aged 12-30 years (259 males and 209 females) for training and testing, including T1 weighted MRI (T1WI), T2 weighted MRI (T2WI), and Proton density weighted MRI (PDWI). Optimal regression models were established for age estimation, yielding mean absolute error (MAE) values below 2.0 years. The MAE values of T1WI were the lowest, with 1.700 years in males and 1.798 years in females. The area under the curve (AUC) and accuracy values of different MRI modalities of 16-year and 18-year thresholds were all around 0.9. For the 18-year threshold, T1WI outperformed T2WI and PDWI. In conclusion, the three MRI modalities of the proximal humerus can serve as reliable indicators for age assessment, while the T1WI performed better in age assessment and classification.

Machine learning and regression analysis for age estimation from the iliac crest based on computed tomographic explorations in an Indian population

Age estimation constitutes an integral parameter of identification. In children, sub-adults, and young adults, accurate age estimation is vital on various aspects of civil, criminal, and immigration law. The iliac crest presents as a suitable age marker within these age cohorts, and the modified Risser method constitutes a relatively novel and unexplored method for iliac crest age estimation. The present study attempted to ascertain the applicability of this modified method for age estimation in the Indian population, an aspect previously unexplored, through computed tomographic examination of the iliac crest. Computed tomography scans of consenting individuals undergoing routine examinations of the pelvis/ abdomen for various clinically indicated reasons were collected and scored using the modified Risser stages. Computed tomographic examinations of the iliac crest indicate that the recalibrated method accurately depicts the temporal progression of ossification and fusion changes. Different regression and machine learning models were subsequently derived and/or trained to evaluate the accuracy and precision associated with the method. Amongst the ten regression models derived herein, compound regression exhibited the lowest inaccuracy (4.78 years) and root mean squared error values (5.46 years). Machine learning yielded further reduced error rates, with decision tree regression achieving inaccuracy and root mean squared error values of 1.88 years and 2.28 years, respectively. A comparative evaluation of error computations obtained from regression analysis and machine learning illustrates the statistical superiority of machine learning for forensic age estimation. Error computations obtained with machine learning suggest that the modified Risser method is capable of permitting reliable age estimation within criminal and civil proceedings.

Postmortem computed tomography assessment of skeletal and dental age in Polish children, adolescents, and young adults

This paper presents a retrospective analysis of postmortem computed tomography (PMCT) scans of secondary ossification centers in the medial clavicular epiphysis, iliac crest apophysis, proximal humeral epiphysis, distal femoral epiphysis, proximal tibial epiphysis, and distal tibial epiphysis. At the same time, we analyzed PMCT scans of the maxillary and mandibular incisors, canines, premolars, and molars. We assessed 203 corpses, whose age ranged from 2 to 30 years, including 156 males and 47 females. The purpose of our study was to compare the processes of secondary ossification center fusion and permanent tooth maturation. Our research hypothesis was that certain stages of skeletal and dental maturation occur along consistent timelines that can be related to the chronological age. Secondary ossification center fusion was evaluated based on Kreitner and also McKern and Steward's classifications. The process of permanent tooth maturation was evaluated with Demirjian's method. Spearman's correlation coefficients (Rho) were positive in all analyses, which indicates that epiphyseal fusion progresses with age. The strongest relationship between the age and the stages of ossification was observed in the proximal tibial epiphysis (p < 0.001; Rho = 0.93) in females and in the medial clavicular epiphysis (p < 0.001; Rho = 0.77) in males. Studies show the importance of concomitant analysis of skeletal and dental maturation with a subsequent comparison of the results to achieve a greater precision in age estimation. A comparison of the results obtained in the study population of Polish children, adolescents, and young adults with the results of other studies in populations of similar ages showed a number of similarities in the time windows of dental and skeletal maturation. These similarities may help in age estimation.

Automated bone age assessment from knee joint by integrating deep learning and MRI-based radiomics

Bone age assessment (BAA) is a crucial task in clinical, forensic, and athletic fields. Since traditional age estimation methods are suffered from potential radiation damage, this study aimed to develop and evaluate a deep learning radiomics method based on multiparametric knee MRI for noninvasive and automatic BAA. This retrospective study enrolled 598 patients (age range,10.00-29.99 years) who underwent MR examinations of the knee joint (T1/T2*/PD-weighted imaging). Three-dimensional convolutional neural networks (3D CNNs) were trained to extract and fuse multimodal and multiscale MRI radiomic features for age estimation and compared to traditional machine learning models based on hand-crafted features. The age estimation error was greater in individuals aged 25-30 years; thus, this method may not be suitable for individuals over 25 years old. In the test set aged 10-25 years (n = 95), the 3D CNN (a fusion of T1WI, T2*WI, and PDWI) demonstrated the lowest mean absolute error of 1.32 ± 1.01 years, which is higher than that of other MRI modalities and the hand-crafted models. In the classification for 12-, 14-, 16-, and 18- year thresholds, accuracies and the areas under the ROC curves were all over 0.91 and 0.96, which is similar to the manual methods. Visualization of important features showed that 3D CNN estimated age by focusing on the epiphyseal plates. The deep learning radiomics method enables non-invasive and automated BAA from multimodal knee MR images. The use of 3D CNN and MRI-based radiomics has the potential to assist radiologists or medicolegists in age estimation.

Machine learning and deep learning enabled age estimation on medial clavicle CT images

The medial clavicle epiphysis is a crucial indicator for bone age estimation (BAE) after hand maturation. This study aimed to develop machine learning (ML) and deep learning (DL) models for BAE based on medial clavicle CT images and evaluate the performance on normal and variant clavicles. This study retrospectively collected 1049 patients (mean± SD: 22.50±4.34 years) and split them into normal training and test sets, and variant training and test sets. An additional 53 variant clavicles were incorporated into the variant test set. The development stages of normal MCE were used to build a linear model and support vector machine (SVM) for BAE. The CT slices of MCE were automatically segmented and used to train DL models for automated BAE. Comparisons were performed by linear versus ML versus DL, and normal versus variant clavicles. Mean absolute error (MAE) and classification accuracy was the primary parameter of comparison. For BAE, the SVM had the best MAE of 1.73 years, followed by the commonly-used CNNs (1.77-1.93 years), the linear model (1.94 years), and the hybrid neural network CoAt Net (2.01 years). In DL models, SE Net 18 was the best-performing DL model with similar results to SVM in the normal test set and achieved an MAE of 2.08 years in the external variant test. For age classification, all the models exhibit superior performance in the classification of 18-, 20-, 21-, and 22-year thresholds with limited value in the 16-year threshold. Both ML and DL models produce desirable performance in BAE based on medial clavicle CT.

Analysis of various radiological age-assessment methods in children, adolescents and young adults regarding the differences between the sexes and sides of the body - A comparative review

A total of 76 articles published within the last twenty years, indexed in the PubMed and ResearchGate databases, were reviewed in order to compare medical imaging-based methods of age estimation of children, adolescents and young adults. The evaluated studies were analyzed for any statistically significant differences between the sexes and sides of the body, sample sizes, and population age. Irrespective of the evaluation method, there were some studies that showed a statistically significant differences in ossification stages between the male and female groups. Most of the studies whose authors conducted a statistical analysis demonstrated no significant differences between the left and right side of the body.

The fusion of ossification centers - A comparative review of radiographic and other imaging modalities of age assessment in living groups of children, adolescents, and young adults

A total of 227 articles published within the last twenty years, indexed in the PUBMED and Researchgate databases, were reviewed for the purpose of comparing medical imaging-based methods of age estimation. The evaluated studies were analyzed in terms of the assessed parts of the body, age, and epiphyseal fusion ages in children, adolescents, and young adults. Our analysis showed that an overwhelming majority of studies had been based on computed tomography and magnetic resonance imaging. A comparison of the studies showed that, irrespective of the imaging modality and the nationality of study population cohorts, the rates of development and the ages at which the process of ossification begins and ends show certain trends.

Forensic bone age estimation of adolescent pelvis X-rays based on two-stage convolutional neural network

In the forensic estimation of bone age, the pelvis is important for identifying the bone age of teenagers. However, studies on this topic remain insufficient as a result of lower accuracy due to the overlapping of pelvic organs in X-ray images. Segmentation networks have been used to automate the location of key pelvic areas and minimize restrictions like doubling images of pelvic organs to increase the accuracy of estimation. This study conducted a retrospective analysis of 2164 pelvis X-ray images of Chinese Han teenagers ranging from 11 to 21 years old. Key areas of the pelvis were detected with a U-Net segmentation network, and the findings were combined with the original X-ray image for regional augmentation. Bone age estimation was conducted with the enhanced and not enhanced pelvis X-ray images by separately using three convolutional neural networks (CNNs). The root mean square errors (RMSE) of the Inception-V3, Inception-ResNet-V2, and VGG19 convolutional neural networks were 0.93 years, 1.12 years, and 1.14 years, respectively, and the mean absolute errors (MAE) of these networks were 0.67 years, 0.77 years, and 0.88 years, respectively. For comparison, a network without segmentation was employed to conduct the estimation, and it was found that the RMSE of the three CNNs above became 1.22 years, 1.25 years, and 1.63 years, respectively, and the MAE became 0.93 years, 0.96 years, and 1.23 years. Bland-Altman plots and attention maps were also generated to provide a visual comparison. The proposed segmentation network can be used to reduce the influence of restrictions like image overlapping of organs and can thus increase the accuracy of pelvic bone age estimation.