Age estimation based on pelvic ossification using regression models from conventional radiography

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.

Applicability of the Suchey-Brooks method for age estimation in an Indian population: A computed tomography-based exploration using Bayesian analysis and machine learning

Age estimation occupies a prominent niche in the identification process. In cases where skeletal remains present for examination, age is often estimated from markers distributed throughout the skeletal framework. Within the pelvis, the pubic symphysis constitutes one of the more commonly utilized skeletal markers for age estimation, with the Suchey-Brooks method comprising one of the more commonly employed methods for pubic symphyseal age estimation. The present study was targeted towards assessing the applicability of the Suchey-Brooks method for pubic symphyseal age estimation, an aspect largely unreported for an Indian population. In order to do so, clinically undertaken pelvic computed tomography scans of individuals were evaluated using the Suchey-Brooks method, and the error associated with the method was established using Bayesian analysis and different machine learning regression models. Amongst different supervised machine learning models, support vector regression and random forest furnished lowest error computations in both sexes. Using both Bayesian analysis and machine learning, lower error computations were observed in females, suggesting that the method demonstrates greater applicability for this sex. Inaccuracy and root mean square error obtained with Bayesian analysis and machine learning illustrates that both statistical modalities furnish comparable error computations for pubic symphyseal age estimation using the Suchey-Brooks method. However, given the numerous advantages associated with machine learning, it is recommended to use the same within medicolegal settings. Error computations obtained with the Suchey-Brooks method, regardless of the statistical modality utilized, indicate that the method should be used in amalgamation with additional markers to garner accurate estimates of age.

Forensic age estimation in adults by pubic bone mineral density using multidetector computed tomography

Radiology plays a crucial role in forensic anthropology for age estimation. However, most studies rely on morphological methods. This study aims to investigate the feasibility of using pubic bone mineral density (BMD) as a new age estimation method in the Chinese population. 468 pubic bone CT scans from living individuals in a Chinese hospital aged 18 to 87 years old were used to measure pubic BMD. The BMD of the bilateral pubic bone was measured using the Mimics software on cross-sectional CT images and the mean BMD of the bilateral pubic bone was also calculated. Regression analysis was performed to assess the correlation between pubic BMD and chronological age and to develop mathematical models for age estimation. We evaluated the accuracy of the best regression model using an independent validation sample by calculating the mean absolute error (MAE). Among all established models, the cubic regression model had the highest R2 value in both genders, with R2 = 0.550 for males and R2 = 0.634 for females. The results of the best model test showed that the MAE for predicting age using pubic BMD was 8.66 years in males and 7.69 years in females. This study highlights the potential of pubic BMD as a useful objective indicator for adult age estimation and could be used as an alternative in forensic practice when other better indicators are lacking.

An evaluation of the three-component pubic symphyseal human age estimation method: a CT-based exploration in an Indian population

Age estimation constitutes an important facet of human identification within forensic, bioarchaeological, repatriation, and humanitarian contexts. Within the human skeletal framework, the pubic symphysis comprises one of the more commonly utilized structures for age estimation. The present investigation was aimed at establishing the applicability of the McKern-Stewart pubic symphyseal age estimation method in males and females of an Indian population, an aspect previously unreported. Three hundred and eighty clinical CT scans of the pubic symphysis were collected and scored in accordance with the McKern-Stewart method. An overall accuracy of 68.90% was obtained on applying the method to males, demonstrating a limited applicability of the method in its primal form. Subsequently, Bayesian analysis was undertaken to enable accurate age estimation from individual components in both sexes. Bayesian parameters obtained with females suggest that McKern-Stewart's components fail to accommodate for age-related changes within the female pubic bone. Improved accuracy percentages and reduced inaccuracy values were obtained with Bayesian analysis in males. With females, the error computations were high. Weighted summary age models were utilized for multivariate age estimation, and furnished inaccuracy values of 11.51 years (males) and 17.92 years (females). Error computations obtained with descriptive analysis, Bayesian analysis, and principal component analysis demonstrate the limited applicability of McKern-Stewart's components in generating accurate age profiles for Indian males and females. The onset and progression of age-related changes within the male and female pubic bone may be of interest to biological anthropologists and anatomists involved in exploring the underlying basis for aging.

Applications of artificial intelligence in forensic sciences: Current potential benefits, limitations and perspectives

In recent years, new studies based on artificial intelligence (AI) have been conducted in the forensic field, posing new challenges and demonstrating the advantages and disadvantages of using AI methodologies to solve forensic well-known problems. Specifically, AI technology has tried to overcome the human subjective bias limitations of the traditional approach of the forensic sciences, which include sex prediction and age estimation from morphometric measurements in forensic anthropology or evaluating the third molar stage of development in forensic odontology. Likewise, AI has been studied as an assisting tool in forensic pathology for a quick and easy identification of the taxonomy of diatoms. The present systematic review follows the PRISMA 2020 statements and aims to explore an emerging topic that has been poorly analyzed in the forensic literature. Benefits, limitations, and forensic implications concerning AI are therefore highlighted, by providing an extensive critical review of its current applications on forensic sciences as well as its future directions. Results are divided into 5 subsections which included forensic anthropology, forensic odontology, forensic pathology, forensic genetics, and other forensic branches. The discussion offers a useful instrument to investigate the potential benefits of AI in the forensic fields as well as to point out the existing open questions and issues concerning its application on real-life scenarios. Procedural notes and technical aspects are also provided to the readers.

McKern-Stewart method as a technique for analysing age related pubic symphyseal changes: A systematic review and meta-analysis

Age estimation is one of the essential criteria in the identification process. The method of age estimation employed depends on the availability of skeletal material brought for forensic examination. McKern and Stewart's method constitutes one of the principal approaches towards pubic symphyseal age estimation. The method entails evaluating morphological changes within the pubic symphysis and subsequently allotting a specific score corresponding to the observed changes. Based on the obtained scores, an age range is then assigned to the remains presenting for examination. The present systematic review was undertaken to ascertain the applicability of the McKern-Stewart method for age estimation. Studies pertaining to the use of the McKern-Stewart method for age estimation in skeletal remains were retrieved by keying in a combination of MeSH terms and other free terms from four databases. The retrieved articles were subjected to a stringent inclusion and exclusion criteria, following which the risk of bias was assessed and the overall quality of evidence was established. Once the final tally of relevant articles was obtained, data specific to the mean age corresponding to each score was extracted. Non-parametric tests and boxplots were employed to compare the mean ages reported across multiple studies. The present systematic review concludes that the McKern-Stewart method can be applied for the purpose of age estimation in skeletal remains. Broader age cohorts for higher scores, as well as, overlapping values for age ranges in relation to the cumulative scores, however, can be considered a limitation for its applicability in forensic case work.

Computed tomographic evaluation of the acetabulum for age estimation in an Indian population using principal component analysis and regression models

The acetabulum presents as a well-preserved evidence, resistant to taphonomic degradation changes and can thus aid in the age estimation process. A CT-based examination of the acetabulum can further help simplify the process of age estimation by overcoming the time-consuming process of maceration and by doing away with the interference resulting from tissue remnants. The aim of the present study was to evaluate the role of the acetabulum for age estimation in an Indian population through a CT-based examination, using principal component analysis and regression models. CT images of 400 individuals aged 10 years and above were evaluated according to the features defined in the San-Millán-Rissech method of age estimation. Five of the seven morphological features defined by San-Millán-Rissech were appreciable on CT scans, and, to enable further statistical analysis, a cumulative score was computed using these five features. A significant correlation of 0.835 and 0.830 for the right and left acetabulum, respectively, was obtained between computed cumulative scores and chronological age of individuals. No significant sex differences were observed in the scoring of different age-related morphological changes. Regression models were generated using individual features and cumulative scores. Regression models derived using the cumulative score yielded inaccuracy values of 9.67 years for the right acetabulum and 9.15 years for the left acetabulum. Inaccuracy and bias values were computed for each individual feature, as well as for each decade, using mean point ages established within the original study. Amongst the various features, acetabular rim porosity was seen to have the lowest values of inaccuracy (11.50 years) and bias (2.32 years) and activity on outer edge of acetabular fossa the highest (inaccuracy and bias values of 22.36 years and 21.50 years, respectively). Taking into consideration this differential contribution towards age estimation, weighted coefficients and mean point ages for different morphological features were determined using principal component analysis. Subsequently, summary age models were generated from the obtained weighted coefficients and mean age values. Summary age models derived in the present study yield lower estimates of inaccuracy of 7.60 years for the right acetabulum and 7.82 years for the left acetabulum. While regression models derived in the present study allow for age estimation using even a single appreciable feature, summary age models take into account the contribution of each feature and generate more accurate estimates of age. Both statistical computations yield reduced error rates and thus can render greater applicability to the acetabulum in forensic age estimation.

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

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.

Forensic age estimation for pelvic X-ray images using deep learning

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.