Bone age estimation with the Greulich-Pyle atlas using 3T MR images of hand and wrist

Forensic bone age assessment of hand and wrist joint MRI images in Chinese han male adolescents based on deep convolutional neural networks

In Chinese criminal law, the ages of 12, 14, 16, and 18 years old play a significant role in the determination of criminal responsibility. In this study, we developed an epiphyseal grading system based on magnetic resonance image (MRI) of the hand and wrist for the Chinese Han population and explored the feasibility of employing deep learning techniques for bone age assessment based on MRI of the hand and wrist. This study selected 282 Chinese Han Chinese males aged 6.0-21.0 years old. In the course of our study, we proposed a novel deep learning model for extracting and enhancing MRI hand and wrist bone features to enhance the prediction of target MRI hand and wrist bone age and achieve precise classification of the target MRI and regression of bone age. The evaluation metric for the classification model including precision, specificity, sensitivity, and accuracy, while the evaluation metrics chosen for the regression model are MAE. The epiphyseal grading was used as a supervised method, which effectively solved the problem of unbalanced sample distribution, and the two experts showed strong consistency in the epiphyseal plate grading process. In the classification results, the accuracy in distinguishing between adults and minors was 91.1%, and the lowest accuracy in the three minor classifications (12, 14, and 16 years of age) was 94.6%, 91.1% and 96.4%, respectively. The MAE of the regression results was 1.24 years. In conclusion, the deep learning model proposed enabled the age assessment of hand and wrist bones based on MRI.

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.

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.

Enhancing skeletal age estimation accuracy using support vector regression models

OBJECTIVE

The objective of the study was to determine if support vector regression (SVR) models could enhance the accuracy of skeletal age estimation compared to original metrics.

METHOD

The study used a dataset of 5,018 individuals from Wuhan, spanning ages 1 to 17. Optimal model parameters were found using cross-validation and grid search techniques. The study compared SVR-based bone age assessment metrics with original metrics and evaluated the performance of the SVR model across different sample sizes.

RESULTS

The findings unequivocally demonstrated SVR's superior reliability over original metrics in assessing bone age among children in central China. Regardless of the training set size, constructing SVR models based on TW3, CHN05, or a combination of TW3, CHN05, and GP consistently results in top-tier predictive accuracy.

CONCLUSION

This research highlights SVR's potential for accuracy improvement and robustness with limited datasets.

Value of Magnetic Resonance Imaging for Skeletal Bone Age Assessment in Healthy Male Children

BACKGROUND

Skeletal bone age assessment for medical reasons is usually performed by conventional x-ray with use of ionizing radiation. Few pilot studies have shown the possible use of magnetic resonance imaging (MRI).

PURPOSE

To comprehensively evaluate feasibility and value of MRI for skeletal bone age (SBA) assessment in healthy male children.

MATERIALS AND METHODS

In this prospective cross-sectional study, 63 male soccer athletes with mean age of 12.35 ± 1.1 years were examined. All participants underwent 3.0 Tesla MRI with coronal T1-weighted turbo spin echo (TSE), coronal proton density (PD)-weighted turbo spin echo (TSE), and T1-weighted three-dimensional (3D) volume interpolated breath-hold examination (VIBE) sequence. Subsequently, SBA was assessed by 3 independent blinded radiologists with different levels of experience using the common Greulich-Pyle (GP) atlas and the Tanner-Whitehouse (TW2) method.

RESULTS

In a mean total acquisition time of 5:04 ± 0:47 min, MR image quality was sufficient in all cases. MRI appraisal was significantly faster ( P < 0.0001) by GP with mean duration of 1:22 ± 0:08 min vs. 7:39 ± 0:28 min by TW. SBA assessment by GP resulted in mean age of 12.8 ± 1.2 years, by TW 13.0 ± 1.4 years. Interrater reliabilities were excellent for both GP (ICC = 0.912 (95% confidence interval [CI] = 0.868-0.944) and TW (ICC = 0.988 (95% CI = 0.980-0.992) and showed statistical significance ( P < 0.001). Subdivided, for GP, ICCs were 0.822 (95% CI = 0.680-0.907) and 0.843 (95% CI = 0.713-0.919) in Under 12 and Under 14 group. For TW, ICCs were 0.978 (95% CI = 0.958-0.989) in Under 12 and 0.979 (95% CI = 0.961-0.989) in Under 14 group.

CONCLUSION

MRI is a clinically feasible, rapidly evaluable method to assess skeletal bone age of healthy male children. Using the Greulich-Pyle (GP) atlas or the Tanner-Whitehouse (TW2) method, reliable results are obtained independent of the radiologist's experience level.

Automated Skeletal Bone Age Assessment with Two-Stage Convolutional Transformer Network Based on X-ray Images

Human skeletal development is continuous and staged, and different stages have various morphological characteristics. Therefore, bone age assessment (BAA) can accurately reflect the individual's growth and development level and maturity. Clinical BAA is time consuming, highly subjective, and lacks consistency. Deep learning has made considerable progress in BAA in recent years by effectively extracting deep features. Most studies use neural networks to extract global information from input images. However, clinical radiologists are highly concerned about the ossification degree in some specific regions of the hand bones. This paper proposes a two-stage convolutional transformer network to improve the accuracy of BAA. Combined with object detection and transformer, the first stage mimics the bone age reading process of the pediatrician, extracts the hand bone region of interest (ROI) in real time using YOLOv5, and proposes hand bone posture alignment. In addition, the previous information encoding of biological sex is integrated into the feature map to replace the position token in the transformer. The second stage extracts features within the ROI by window attention, interacts between different ROIs by shifting the window attention to extract hidden feature information, and penalizes the evaluation results using a hybrid loss function to ensure its stability and accuracy. The proposed method is evaluated on the data from the Pediatric Bone Age Challenge organized by the Radiological Society of North America (RSNA). The experimental results show that the proposed method achieves a mean absolute error (MAE) of 6.22 and 4.585 months on the validation and testing sets, respectively, and the cumulative accuracy within 6 and 12 months reach 71% and 96%, respectively, which is comparable to the state of the art, markedly reducing the clinical workload and realizing rapid, automatic, and high-precision assessment.

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.

A Global-Local Feature Fusion Convolutional Neural Network for Bone Age Assessment of Hand X-ray Images

Bone age assessment plays a critical role in the investigation of endocrine, genetic, and growth disorders in children. This process is usually conducted manually, with some drawbacks, such as reliance on the pediatrician’s experience and extensive labor, as well as high variations among methods. Most deep learning models use one neural network to extract the global information from the whole input image, ignoring the local details that doctors care about. In this paper, we propose a global-local feature fusion convolutional neural network, including a global pathway to capture the global contextual information and a local pathway to extract the fine-grained information from local patches. The fine-grained information is integrated into the global context information layer-by-layer to assist in predicting bone age. We evaluated the proposed method on a dataset with 11,209 X-ray images with an age range of 4–18 years. Compared with other state-of-the-art methods, the proposed global-local network reduces the mean absolute error of the estimated ages to 0.427 years for males and 0.455 years for females; the average accuracy rate is within 6 months and 12 months, reaching 70% and 91%, respectively. In addition, the effectiveness and rationality of the model were verified on a public dataset.

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.

A probability model for assessing age relative to the 18-year old threshold based on magnetic resonance imaging of the knee combined with radiography of third molars in the lower jaw

OBJECTIVE

This study aims to generate a statistical model based on magnetic resonance imaging of the knee and radiography of third molars in the lower jaw, for assessing age relative to the 18-year old threshold.

METHODS

In total, 58 studies correlating knee or tooth development to age were assessed, 5 studies for knee and 7 studies for tooth were included in the statistical model. The relation between the development of the anatomical site, based on a binary system, and age were estimated using logistic regression. Separate meta-populations for knee and tooth were generated from the individual based data for men and women. A weighted estimate of probabilities was made by combining the probability densities for knee and tooth. Margin of errors for males and females in different age groups and knee and tooth maturity were calculated within the larger framework of transition analysis using a logit model as a base. Evidentiary values for combinations of knee and tooth maturity were evaluated with likelihood ratios.

RESULTS

For males, the sensitivity for the method was calculated to 0.78 (probability of correctly classifying adults), the specificity 0.90 (probability of correctly classifying minors), the negative predictive value 0.80 (proportion identified minors are minors) and the positive predictive value 0.89 (proportion identified adults are adults) indicating a model better at identifying minors than adults. The point at which half the female population has reached closed knee lies before the 18-year threshold, adding the knee as an indicator lowers specificity and increases sensitivity. The sensitivity when using tooth as an indicator for females is 0.24 and specificity 0.97, signifying few minors misclassified as adults but also a low probability of identifying adults. The negative predictive value for women when using tooth as the sole indicator is 0.56 and positive predictive value 0.88. Probabilities were calculated for males and females assuming a uniform age distribution between 15 and 21years. The calculated margin of error of minors classified as adults in a population between 15 and 21 years with the model was 11% for males and 12% for females. Further, the evidentiary value as well as margin of error vary for different combinations of knee and tooth maturity.

CONCLUSION

The statistical model based on the combination of MRI knee and radiography of mandibular third molars is a valid method to assess age relative to the 18-year old threshold when applied on males and of limited value in females.

Data Enhancement and Deep Learning for Bone Age Assessment using The Standards of Skeletal Maturity of Hand and Wrist for Chinese

Conventional methods for artificial age determination of skeletal bones have several problems, such as strong subjectivity, large random errors, complex evaluation processes, and long evaluation cycles. In this study, an automated age determination of skeletal bones was performed based on Deep Learning. Two methods were used to evaluate bone age, one based on examining all bones in the palm and another based on the deep convolutional neural network (CNN) method. Both methods were evaluated using the same test dataset. Moreover, we can extend the dataset and increase the generalisation ability of the network by data expansion. Consequently, a more accurate bone age can be obtained. This method can reduce the average error of the final bone age evaluation and lower the upper limit of the absolute value of the error of the single bone age. The experiments show the effectiveness of the proposed method, which can provide doctors and users with more stable, efficient and convenient diagnosis support and decision support.

3D MRI of the Hand and Wrist: Technical Considerations and Clinical Applications

In the last few years, major developments have been observed in the field of magnetic resonance imaging (MRI). Advances in both scanner hardware and software technologies have witnessed great leaps, enhancing the diagnostic quality and, therefore, the value of MRI. In musculoskeletal radiology, three-dimensional (3D) MRI has become an integral component of the diagnostic pathway at our institutions. This technique is particularly relevant in patients with hand and wrist symptoms, due to the intricate nature of the anatomical structures and the wide range of differential diagnoses for most presentations. We review the benefits of 3D MRI of the hand and wrist, commonly used pulse sequences, clinical applications, limitations, and future directions. We offer guidance for enhancing the image quality and tips for image interpretation of 3D MRI of the hand and wrist.

Computed tomographic age estimation from the pubic symphysis using the Suchey-Brooks method: A Systematic Review and Meta-analysis

Forensic age estimation is routinely applied in investigations involving identification of individuals. Over the past century a myriad of methods have been devised for age estimation. One such method, proposed by Suchey and Brooks in 1990, groups the observed changes occurring in the pubic symphysis into six phases, each defined by a corresponding age range. The present study was piloted with the focussed question being to empirically determine the accuracy of the Suchey-Brooks method in computed tomographic age estimation by analysing morphological changes occurring in the pubic symphysis. Original articles pertaining to the use of the Suchey-Brooks method for CT based age estimation were extracted from four different databases- PubMed, CENTRAL, Google Scholar and ScienceDirect. Research papers which were answering the focussed question were selected for data analysis. After assessing the risk of bias of the selected articles, the data was subjected to Meta-analysis. Pooled analysis of correctly/accurately aged individuals/remains using the random and fixed effect models yielded a prediction percentage of 78% and 86%, respectively. Higher percentages were obtained for phase-wise and subgroup analysis, indicating that the Suchey-Brooks method is a reliable method for age estimation.