Considerations for age estimation accuracy: Method-derived outcomes and practitioner interpretations.

Recent research observed 92% accuracy for age-at-death estimations by U.S. forensic anthropologists. The present study compares this case report level accuracy to method level accuracy for the most commonly used methods in U.S. casework, drawing from the Forensic Anthropology Database for Assessing Methods Accuracy (FADAMA). Method application rate (i.e., how often a method is used in casework) was analyzed for n = 641 cases and identified 15 methods with an application rate >45 cases, and the present study focused further analyses on these 15 methods. Of the 15, only four yielded accuracies greater than or equal to the 92% documented for case-report level accuracy. The other 11 methods produced accuracy rates ranging from 54% to 91%, with six of these below 70% This disconnect between highly accurate age estimations at the case report level compared to the poor performance at method level suggests that practitioner interpretation and synthesis of the methods' outcomes is a critical step for increasing the accuracy rates of the age estimations as reported on the final case report. This inference was further supported by the study's results which indicated that practitioner interpretations of frequently used method combinations improve accuracy and age range width of age estimation. The study also performed a Fisher's Exact test to assess whether case report-level accuracy differed with the number of aging methods used in a case, and found no significant differences.

Evaluating the Robustness of a Deep Learning Bone Age Algorithm to Clinical Image Variation Using Computational Stress Testing.

Purpose To evaluate the robustness of an award-winning bone age deep learning (DL) model to extensive variations in image appearance. Materials and Methods In December 2021, the DL bone age model that won the 2017 RSNA Pediatric Bone Age Challenge was retrospectively evaluated using the RSNA validation set (1425 pediatric hand radiographs; internal test set in this study) and the Digital Hand Atlas (DHA) (1202 pediatric hand radiographs; external test set). Each test image underwent seven types of transformations (rotations, flips, brightness, contrast, inversion, laterality marker, and resolution) to represent a range of image appearances, many of which simulate real-world variations. Computational "stress tests" were performed by comparing the model's predictions on baseline and transformed images. Mean absolute differences (MADs) of predicted bone ages compared with radiologist-determined ground truth on baseline versus transformed images were compared using Wilcoxon signed rank tests. The proportion of clinically significant errors (CSEs) was compared using McNemar tests. Results There was no evidence of a difference in MAD of the model on the two baseline test sets (RSNA = 6.8 months, DHA = 6.9 months; P = .05), indicating good model generalization to external data. Except for the RSNA dataset images with an appended radiologic laterality marker (P = .86), there were significant differences in MAD for both the DHA and RSNA datasets among other transformation groups (rotations, flips, brightness, contrast, inversion, and resolution). There were significant differences in proportion of CSEs for 57% of the image transformations (19 of 33) performed on the DHA dataset. Conclusion Although an award-winning pediatric bone age DL model generalized well to curated external images, it had inconsistent predictions on images that had undergone simple transformations reflective of several real-world variations in image appearance. Keywords: Pediatrics, Hand, Convolutional Neural Network, Radiography Supplemental material is available for this article. © RSNA, 2024 See also commentary by Faghani and Erickson in this issue.

Comparing a common clavicle maturation-based age estimation method to ordinary regression analyses with quadratic and sex-specific interaction terms in adolescents.

Established methods of age estimation are based on correlating defined maturation stages of bony structures with tables representing the observed range of biological ages in the majority of cases. In this retrospective monocentric study in southwestern Germany, common age estimation methodology was assessed in n = 198 subjects at the age of 25 or younger by analyzing the influence of age, quadratic age, biological sex and age-sex interaction on the ossification stages of the medial epiphysis fugue. Three readers (ICC ≥ 0.81 for left/right side) evaluated routine care computed tomography images of the clavicle with a slice thickness of 1 mm. By using least square regression analyses, to determine the real biological age a quadratic function was determined corrected for the age estimated by established methods and sex (R2 = 0.6 each side), reducing the mean absolute error and root mean squared error in the age estimation of women (2.57 and 3.19) and men (2.57 and 3.47) to 1.54 and 1.82 for women, and 1.54 and 2.25 for men. In women, the medial clavicle epiphysis seem to fuse faster, which was particularly observable from approximately 18 years of age. Before that age, the estimation method was relatively close to the ideal correlation between assessed and real age. To conclude, the presented new method enables more precise age estimation in individuals and facilitates the determination and quantification of additional variables, quantifying their influence on the maturation of the medial clavicle epiphysis based on the established ossification stages.

Forensic age estimation of the knee by post-mortem DR, CT, and MR imaging: a comparative study.

It is believed by many that reference data for age estimation purposes must be imaging-modality specific. A study from our department has however proven otherwise. We therefore found it interesting to investigate this further by looking at the level of agreement between different imaging modalities. The aim of this study was to investigate the level of agreement between the three radiological modalities, computed tomography (CT), magnetic resonance imaging (MRI), and digital radiography (DR), in assessing the ossification of the epiphyses of the knee. A total of 34 deceased individuals of 10-25 years of age, brought in for a medicolegal autopsy at our department, were scanned by CT, MRI, and DR. The ossification stages of the three bones of the right knee, distal femoral, proximal tibial, and proximal fibular epiphysis were assessed using the established combined staging method by Schmeling et al. and Kellinghaus et al. Analysis of the results by Cohen's weighted kappa showed a good agreement between CT and DR (K = 0.61-0.70), and MRI and DR (K = 0.68-0.79) but only moderate agreement between CT and MRI (K = 0.55-0.57). This leads us to conclude that different radiological images cannot be used interchangeably for age estimation purposes, so reference material needs to be imaging-modality specific. However, to make a more general conclusion research on a larger population is needed.

Evaluation of an objective staging system for assessment of cervical vertebral maturation.

BACKGROUND: The aim of this study was to evaluate an objective method for Cervical Vertebral Maturation (CVM) staging. METHODS: An initial sample of 647 Lateral Cephalometric Radiographs (LCR) were staged according to the CVM (Baccetti et al.) by 4 examiners. The final sample (n = 394) included LCR on which the staging of the 4 investigators matched. The objective staging was performed by a single operator. The sample was divided according to the maturational stages into pre-pubertal, pubertal and post-pubertal groups. Measurements were performed on the cervical vertebrae (C2, C3 and C4). The angle between posterior and superior borders for C3 and C4 was the Superior Wall Inclination Angle (SWIA). Concavity Depth (CD) for C2, C3 and C4, and Body Shape (BS) (ratio of width to height of C3 and C4). Measurements of the 3 groups were compared. RESULTS: Reliability of subjective staging was high (intra-observer reliability, 0.948; inter-observer reliability, 0.967). Good agreement was observed for the outcomes measured. Intra-observer reliability was good (0.918, 0.885 and 0.722 for CD, BS and SWIA, respectively). The same was for the inter-observer reliability results (0.902, 0.889 and 0.728 for CD, BS and SWIA, respectively). Significant differences were observed for mean values of SWIA and BS and median values of CD within maturational stage. Similar findings were observed when the outcomes were compared at different phases (P < 0.001). CONCLUSIONS: A standardized, objective staging system using linear, angular measurements and ratios was applied for the determination of cervical vertebral maturation.

The Reliability of the Modified Fels Knee Skeletal Maturity System.

BACKGROUND: The recently described Modified Fels knee skeletal maturity system (mFels) has proven utility in prediction of ultimate lower extremity length in modern pediatric patients. mFels users evaluate chronological age, sex, and 7 anteroposterior knee radiographic parameters to produce a skeletal age estimate. We developed a free mobile application to minimize the learning curve of mFels radiographic parameter evaluation. We sought to identify the reliability of mFels for new users. METHODS: Five pediatric orthopaedic surgeons, 5 orthopaedic surgery residents, 3 pediatric orthopaedic nurse practitioners, and 5 medical students completely naïve to mFels each evaluated a set of 20 pediatric anteroposterior knee radiographs with the assistance of the (What's the Skeletal Maturity?) mobile application. They were not provided any guidance beyond the instructions and examples embedded in the app. The results of their radiographic evaluations and skeletal age estimates were compared with those of the mFels app developers. RESULTS: Averaging across participant groups, inter-rater reliability for each mFels parameter ranged from 0.73 to 0.91. Inter-rater reliability of skeletal age estimates was 0.98. Regardless of group, steady proficiency was reached by the seventh radiograph measured. CONCLUSIONS: mFels is a reliable means of skeletal maturity evaluation. No special instruction is necessary for first time users at any level to utilize the (What's the Skeletal Maturity?) mobile application, and proficiency in skeletal age estimation is obtained by the seventh radiograph. LEVEL OF EVIDENCE: Level II.

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.

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.

Deeplasia: deep learning for bone age assessment validated on skeletal dysplasias.

BACKGROUND: Skeletal dysplasias collectively affect a large number of patients worldwide. Most of these disorders cause growth anomalies. Hence, evaluating skeletal maturity via the determination of bone age (BA) is a useful tool. Moreover, consecutive BA measurements are crucial for monitoring the growth of patients with such disorders, especially for timing hormonal treatment or orthopedic interventions. However, manual BA assessment is time-consuming and suffers from high intra- and inter-rater variability. This is further exacerbated by genetic disorders causing severe skeletal malformations. While numerous approaches to automate BA assessment have been proposed, few are validated for BA assessment on children with skeletal dysplasias. OBJECTIVE: We present Deeplasia, an open-source prior-free deep-learning approach designed for BA assessment specifically validated on patients with skeletal dysplasias. MATERIALS AND METHODS: We trained multiple convolutional neural network models under various conditions and selected three to build a precise model ensemble. We utilized the public BA dataset from the Radiological Society of North America (RSNA) consisting of training, validation, and test subsets containing 12,611, 1,425, and 200 hand and wrist radiographs, respectively. For testing the performance of our model ensemble on dysplastic hands, we retrospectively collected 568 radiographs from 189 patients with molecularly confirmed diagnoses of seven different genetic bone disorders including achondroplasia and hypochondroplasia. A subset of the dysplastic cohort (149 images) was used to estimate the test-retest precision of our model ensemble on longitudinal data. RESULTS: The mean absolute difference of Deeplasia for the RSNA test set (based on the average of six different reference ratings) and dysplastic set (based on the average of two different reference ratings) were 3.87 and 5.84 months, respectively. The test-retest precision of Deeplasia on longitudinal data (2.74 months) is estimated to be similar to a human expert. CONCLUSION: We demonstrated that Deeplasia is competent in assessing the age and monitoring the development of both normal and dysplastic bones.

The Modified Fels and Abbreviated Modified Fels Knee Skeletal-Maturity Systems in the Prediction of Leg-Length Discrepancy.

BACKGROUND: The Modified Fels (mFels) and Abbreviated Modified Fels (abFels) knee systems have been recently developed as options for grading skeletal maturity without the need for a separate hand radiograph. We sought to determine the interobserver reliability of these systems and to compare their prediction accuracy with that of the Greulich and Pyle (G-P) atlas in a cohort managed with epiphysiodesis for leg-length discrepancy (LLD). METHODS: Three reviewers scored 20 knee radiographs using the mFels system, which includes 5 qualitative and 2 quantitative measures as well as a quantitative output. Short leg length (SL), long leg length (LL), and LLD prediction errors at maturity using the White-Menelaus (W-M) method and G-P, mFels, or abFels skeletal age were compared in a cohort of 60 patients managed with epiphysiodesis for LLD. RESULTS: Intraclass correlation coefficients for the 2 quantitative variables and the quantitative output of the mFels system using 20 knee radiographs ranged from 0.55 to 0.98, and kappa coefficients for the 5 qualitative variables ranged from 0.56 to 1, indicating a reliability range from moderate to excellent. In the epiphysiodesis cohort, G-P skeletal age was on average 0.25 year older than mFels and abFels skeletal ages, most notably in females. The majority of average prediction errors between G-P, mFels, and abFels were <0.5 cm, with the greatest error being for the SL prediction in females, which approached 1 cm. Skeletal-age estimates with the mFels and abFels systems were statistically comparable. CONCLUSIONS: The mFels skeletal-age system is a reproducible method of determining skeletal age. Prediction errors in mFels and abFels skeletal ages were clinically comparable with those in G-P skeletal ages in this epiphysiodesis cohort. Further work is warranted to optimize and validate the accuracy of mFels and abFels skeletal ages to predict LLD and the impact of epiphysiodesis, particularly in females. Both the mFels and abFels systems are promising means of estimating skeletal age, avoiding additional radiation and health-care expenditure. LEVEL OF EVIDENCE: Prognostic Level II . See Instructions for Authors for a complete description of levels of evidence.

Evaluation of height prediction models: from traditional methods to artificial intelligence.

BACKGROUND: Traditional methods for predicting adult height (AHP) rely on manual readings of bone age (BA). However, the incorporation of artificial intelligence has recently improved the accuracy of BA readings and their incorporation into AHP models. METHODS: This study aimed to identify the AHP model that fits the current average height for adults in Mexico. Using a cross-sectional design, the study included 1173 participants (5-18 yr). BA readings were done by two experts (manually) and with an automated method (BoneXpert®). AHP was carried out using both traditional and automated methods. The best AHP model was the one that was closest to the population mean. RESULTS: All models overestimated the population mean (males: 0.7-6.7 cm, females: 0.9-3.7 cm). The AHP models with the smallest difference were BoneXpert for males and Bayley & Pinneau for females. However, the manual readings of BA showed significant interobserver variability (up to 43% of predictions between observers exceeded 5 cm using the Bayley & Pinneau method). CONCLUSION: Traditional AHP models relying on manual BA readings have high interobserver variability. Therefore, BoneXpert is the most reliable option, reducing such variability and providing AHP models that remain close to the mean population height. IMPACT: Traditional models for predicting adult height often result in overestimated height predictions. The manual reading of bone age is prone to interobserver variability, which can introduce significant biases in the prediction of adult height. The BoneXpert method minimizes the variability associated with traditional methods and demonstrates consistent results in relation to the average height of the population. This study is the first to assess adult height prediction models specifically in the current generations of Mexican children.

Forensic Diagnostics of the Skeletal Age in the Living - Backgrounds and Methodology. / Forensische Diagnostik des Skelettalters bei Lebenden ­ Hintergründe und Methodik.

BACKGROUND: The expert opinions on forensic age diagnostics requested by state institutions are used to show the exceeding of legally relevant age thresholds, especially the completed 18th year of life. According to the recommendations of the Study Group on Forensic Age Diagnostics (AGFAD), this requires - among other things - a determination of skeletal age. METHOD: Considering recent scientific knowledge, the current conditions and established skeletal age diagnostics methods are presented. Additionally, this review article sheds light on the influence of ethnicity and socioeconomic status, questions regarding indication, as well as alternative and future developments. RESULTS AND CONCLUSION: In forensic age diagnostics, particularly hand radiography and thin-slice CT of the medial clavicular epiphysis are relevant for determining skeletal age. The Atlas method of Greulich and Pyle (1959) and the clavicular stages by Schmeling et al. (2004) and Kellinghaus et al. (2010) are primarily used for this. This spectrum of methods, which is based on a very solid database, might be supplemented by MRI studies of the knee joint in the near future. KEY POINTS: · Determining skeletal age is an essential part of forensic age diagnostics commissioned by state authorities and courts.. · Hand radiography and CT of the medial clavicular epiphysis form the core of the spectrum of methods recommended by the Study Group of Forensic Age Diagnostics (AGFAD).. · Since the radiological studies required for forensic age diagnostics are not medically indicated, it must be ensured that the legal basis is specifically named in each case when commissioning expert opinions.. · MRI studies of the knee joint might increase the spectrum of methods in the near future.. CITATION FORMAT: · Wittschieber D, Hahnemann ML, Mentzel H. Forensic Diagnostics of the Skeletal Age in the Living - Backgrounds and Methodology. Fortschr Röntgenstr 2024; 196: 254 - 261.

Age estimation based on the metamorphosis of the clavicle end: A test of Falys and Prangle method in two contemporary samples.

Upon finding skeletal unidentified remains, four are the questions that must be answered: age, sex, ancestry, and stature. Regarding age estimation, clavicle has received special attention because medial epiphysis is the last epiphysis, among long bones that ossifies. Falys and Prangle proposed a method of age estimation based on three degenerative characteristics-surface topography (TOP), Porosity (POR) and Osteophyte formation (OST)-evaluated on the sternal end of the clavicle according to the descriptions and the illustrations provided in the original article producing satisfactory results. The current study aims to test the applicability of the Falys' and Prangle's method on 174 individuals from two contemporary samples, one from Greece (Cretan osteological Collection and Athens Forensic Anthropology Lab collection) and one from Thailand (Osteological collection in Chiang Mai). Composite scores were calculated, inter and intra- observer error were estimated by kappa statistics and regression equations of the original study were tested in our sample and in subsamples divided by sex and population. The Greek sample gave more accurate estimates compared to the Thai sample. Regressions of known sex gave slightly better results in most cases. When individuals <40 years old were excluded, classification increased for both Thai and Greeks. The results of this pilot study indicate that there are morphological features on the clavicle that are highly correlated with age. Thus, there is a scope of expanding research on the morphological features of the collar bone.

Micro-CT evaluation of morphological degenerative features of sterno-clavicular joint for age-at-death estimation in forensic anthropology - A qualitative analysis.

The analysis of the sternoclavicular joint holds significant importance in forensic anthropology, especially through the evaluation of medial clavicular ossification stage, which, however, is helpful only in subjects younger than 30 years of age. Given this limitation, the aim of the present work was to examine, through micro-CT, the surface of sternoclavicular joints of deceased individuals across various age groups, aiming to identify age-related degenerative changes applicable to age estimation in adults over 30 years old. A total of 41 deceased subjects were categorized into three age groups (20-39 years; 40-59 years; ≥60 years) for the analysis. Degenerative morphological features on both clavicular and sternal articular surfaces, including topography, porosity, and presence of osteophytes, were evaluated using a composite scoring system based on a modified "Falys-Prangle method.", which assigns to each parameter specific score ranges: 1-3 for surface topography (smooth, slightly irregular, markedly irregular), 1-6 for porosity (absent, micro- and macroporosity for <50 % or >50 % of surface, surface breakdown), 1-3 for osteophytes (absent, present, not evaluable). The findings revealed a positive correlation between degenerative morphological features and age for both clavicular (rs = 0.719) and sternal articular surfaces (rs = 0.750). Additionally, the combined assessment of the clavicle and sternum, or the evaluation of the clavicle alone, exhibited better differentiation among the three age groups. The micro-CT evaluation of degenerative alterations affecting the sternoclavicular joint proves to be a reliable and efficient method for age estimation in adults.

Estimating adult age categories in commingled skeletons with Transition Analysis 3.

OBJECTIVES: We estimate adult age frequencies from Unar 1 and Unar 2, two late Umm an-Nar (2400-2100 BCE) tombs in the modern-day Emirate of Ras al-Khaimah, United Arab Emirates. These collective tombs each contained hundreds of skeletons in commingled, fragmented, and variably cremated states. Previous studies placed the vast majority of this mortuary community in a generalized "adult" category, as have most analyses of similar tombs from this period. We sought to test how adult age estimation methods compare in identifying young, middle, and old-age individuals in commingled assemblages. MATERIALS AND METHODS: We employed Transition Analysis 3 (TA3) and traditional age estimation methods to generate adult age frequencies for each tomb. We compared these frequencies between tomb contexts as well as by method. RESULTS: Unar 1 and Unar 2 had similar adult age frequencies within each method, but TA3 age frequencies included significantly more middle and older adult individuals than those generated by traditional methods. DISCUSSION: These results support findings of earlier iterations of transition analysis in regard to sensitivity in old adult age estimation, compared with traditional methods. Our findings indicate a potential use of TA3 in reconstructing age frequencies and mortality profiles in commingled skeletal assemblages. Increasing our understanding of everyday life in the distant past necessitates better understandings of adult age, and here, we illustrate how age estimation method choice significantly changes bioarchaeological interpretations of aging in Bronze Age Arabia. RESEARCH HIGHLIGHTS: Adult age estimation using TA3 revealed significantly more middle and older adults than traditional methods in two commingled tombs. Similar mean maximum likelihood point estimates by side and across skeletal elements were found between tombs.

Technical note: Interest of focused fields in post-mortem computed tomography using photorealistic images for age at death estimation from the pubic symphysis.

INTRODUCTION: The morphological assessment of the pubic symphysis using the Suchey-Brooks method is considered a reliable age at death indicator. Age at death estimation methods can be adapted to the images obtained from post-mortem computed tomography (PMCT). The aim of this study is to evaluate the utility of pubic symphysis photorealistic images obtained through Global illumination rendering (GIR) for age at death estimation from whole-body PMCT and from focused PMCT on the pubic bone. MATERIALS AND METHODS: We performed virtual age at death estimation using the Suchey Brooks method from both the whole-body field of view (Large Field of View: LFOV) and the pubis-focused field of view (Small and Field of View: SFOV) of 100 PMCT. The 3D photorealistic images were evaluated by three forensic anthropologists and the results were statistically evaluated for accuracy of the two applied PMCT methods and the intra- and inter-observer errors. RESULTS: When comparing the two acquisitions of PMCT, the accuracy rate reaches 98.5% when using a pubic-focused window (SFOV) compared to 86% with a whole-body window (LFOV). Additionally, the intra- and inter-observer variability has demonstrated that the focused window provides better repeatability and reproducibility. CONCLUSION: Adding a pubic-focused field of view to standard PMCT and processing it with GIR appears to be an applicable technique that increases the accuracy rate for age at death estimation from the pubic symphysis.

Interdisiplinary and intraobserver reliability of the Greulich-Pyle method among Turkish children.

OBJECTIVES: Greulich-Pyle (GP) is one of the most used method for bone age determination (BAD) in various orthopedic, pediatric, radiological, and forensic situations. We aimed to investigate the inter- and intra-observer reliability of the GP method between the most relevant disciplines and its applicability to the Turkish population. METHODS: One-hundred and eighty (90 boys, 90 girls) patients with a chronological age younger than 18 (mean 9.33) were included. X-rays mixed by the blinded investigator were evaluated by two orthopedists, two radiologists, and two pediatric endocrinologists to determine skeletal age according to the GP atlas. A month later the process was repeated. As a statistical method, Paired t-test was used for comparison, an Intraclass Correlation Coefficients test was used for reliability and a 95 % confidence interval was determined. Results were classified according to Landis-Koch. RESULTS: All results were consistent with chronological age (p<0.001), according to the investigators' evaluations compared with chronological age. At the initial evaluation, the interobserver reliability of the method was 0.999 (excellent); at the second evaluation, the interobserver reliability was 0.997 (excellent). The intra-observer reliability of the method was 'excellent' in all observers. When results were separately evaluated by gender, excellent intraobserver correlation and excellent correlation with chronological age were found among all researchers (>0.9). When X-rays were divided into three groups based on age ranges and evaluated, 'moderate' and 'good' correlations with chronological age were obtained during the peripubertal period. CONCLUSIONS: The GP method used in skeletal age determination has excellent inter- and intra-observer reliability. During the peripubertal period, potential discrepancies in bone age assessments should be kept in mind. This method can be used safely and reproducibly by the relevant specialists.

Assessment of correlation between hand-wrist maturation and cervical vertebral maturation: a fractal analysis study.

BACKGROUND: To investigate whether fractal dimension (FD) measurements from hand-wrist radiographs and lateral cephalometric radiographs are correlated with each other and with skeletal maturation stages. METHODS: In this retrospective study conducted on hand-wrist and lateral cephalometric radiographs obtained from patients between 2017 and 2023, hand-wrist maturation stages (HWMS) and cervical vertebral maturation stages (CVMS) of 144 subjects (6 to 17 years of age) were assessed radiographically. The participants were divided into nine groups (n = 16 each) based on HWMS. Fractal analysis was performed on the radiographs of the radius, the middle finger phalanges (proximal, medial and distal), and the cervical vertebral bodies (C2, C3, C4). Mean and standard deviation values, Spearman's and Pearson correlation analyses, one-way ANOVA, Kruskal-Wallis H tests and Mann-Whitney-U test were used to evaluate the data. RESULTS: Positive correlations were found between the FD values of the radius and HWMS or CVMS (r = .559, P = .001, r = .528 P = .001 respectively). The FD values of the radius were positively correlated with those of all cervical vertebrae (C2, C3, C4), proximal and medial phalanges as well as age. FD values measured from the proximal phalanx, medial phalanx and radius showed significant differences among both HWMS and CVMS (P < .05). HWMS was strongly correlated with CVMS (r = .929, P = .001). Age was strongly correlated with HWMS (r = .795, P = .001) and CVMS (r = .756, P = .001). There was a significant difference in terms of age distribution among HWMS and CVMS (P < .05). CONCLUSIONS: FD measurements on hand-wrist radiographs can provide useful information for the assessment of skeletal maturation stage. Especially, FD measurements from the radius are important and more reliable to predict skeletal maturation stage.

Bone Age Estimation and Prediction of Final Adult Height Using Deep Learning.

PURPOSE: The appropriate evaluation of height and accurate estimation of bone age are crucial for proper assessment of the growth status of a child. We developed a bone age estimation program using a deep learning algorithm and established a model to predict the final adult height of Korean children. MATERIALS AND METHODS: A total of 1678 radiographs from 866 children, for which the interpretation results were consistent between two pediatric endocrinologists, were used to train and validate the deep learning model. The bone age estimation algorithm was based on the convolutional neural network of the deep learning system. The test set simulation was performed by a deep learning program and two raters using 150 radiographs and final height data for 100 adults. RESULTS: There was a statistically significant correlation between bone age interpreted by the artificial intelligence (AI) program and the reference bone age in the test set simulation (r=0.99, p<0.001). In the test set simulation, the AI program showed a mean absolute error (MAE) of 0.59 years and a root mean squared error (RMSE) of 0.55 years, compared with reference bone age, and showed similar accuracy to that of an experienced pediatric endocrinologist (rater 1). Prediction of final adult height by the AI program showed an MAE of 4.62 cm, compared with the actual final adult height. CONCLUSION: We developed a bone age estimation program based on a deep learning algorithm. The AI-derived program demonstrated high accuracy in estimating bone age and predicting the final adult height of Korean children and adolescents.

Relationship between skeletal maturity indicators and dental calcification stages in a sample pediatric population.

Context: Human growth shows considerable variation. In addition to constitutional differences in the timing of maturation, there are diseases, systemic disorders and environmental factors that may affect a child's physiologic maturity. Interrelationships among skeletal, somatic and sexual maturity have been shown to be consistently strong. The study was conducted to evaluate the relationship between dental calcification stages and skeletal maturity indicators. Materials and Methods: The hand wrist radiographs, the lateral cephalogram and the orthopantomogram (OPG) of 120 patients (60 males and 60 females, age group 8-14 years) were taken. The hand wrist radiographs were analyzed using Fishman's skeletal maturity index (SMI), and the cephalograms analyzed by cervical vertebrae maturation (CVM) by Baccetti. OPG was analyzed according to the Demirjian's system. Result: On assessment, cervical vertebrae maturation indicator (CVMI) staging showed significant results with a correlation coefficient of 0.716 being the highest in canines in males while assessment of dental calcification stages and its comparison with skeletal maturity indicator showed insignificant results. The correlation coefficient values were 0.11, 0.09, 0.09 and 0.13 for canine, first premolar, second premolar and second molar respectively. Conclusion: There is a strong correlation between the maturation stage of cervical vertebrae and calcification stages of canine, first premolar, second premolar and second molar as determined by Demirjian's method.