Bone age for chronological age determination - statement of the European Society of Paediatric Radiology musculoskeletal task force group

Performance of two different artificial intelligence (AI) methods for assessing carpal bone age compared to the standard Greulich and Pyle method

PURPOSE

Evaluate the agreement between bone age assessments conducted by two distinct machine learning system and standard Greulich and Pyle method.

MATERIALS AND METHODS

Carpal radiographs of 225 patients (mean age 8 years and 10 months, SD = 3 years and 1 month) were retrospectively analysed at two separate institutions (October 2018 and May 2022) by both expert radiologists and radiologists in training as well as by two distinct AI software programmes, 16-bit AItm and BoneXpert® in a blinded manner.

RESULTS

The bone age range estimated by the 16-bit AItm system in our sample varied between 1 year and 1 month and 15 years and 8 months (mean bone age 9 years and 5 months SD = 3 years and 3 months). BoneXpert® estimated bone age ranged between 8 months and 15 years and 7 months (mean bone age 8 years and 11 months SD = 3 years and 3 months). The average bone age estimated by the Greulich and Pyle method was between 11 months and 14 years, 9 months (mean bone age 8 years and 4 months SD = 3 years and 3 months). Radiologists' assessments using the Greulich and Pyle method were significantly correlated (Pearson's r > 0.80, p < 0.001). There was no statistical difference between BoneXpert® and 16-bit AItm (mean difference = - 0.19, 95%CI = (- 0.45; 0.08)), and the agreement between two measurements varies between - 3.45 (95%CI = (- 3.95; - 3.03) and 3.07 (95%CI - 3.03; 3.57).

CONCLUSIONS

Both AI methods and GP provide correlated results, although the measurements made by AI were closer to each other compared to the GP method.

Phantom study of a self-shielded X-ray bone age assessment instrument against scattered radiation in children

Hand-wrist radiography is the most common and accurate method for evaluating children's bone age. To reduce the scattered radiation of radiosensitive organs in bone age assessment, we designed a small X-ray instrument with radioprotection function by adding metal enclosure for X-ray shielding. We used a phantom operator to compare the scattered radiation doses received by sensitive organs under three different protection scenarios (proposed instrument, radiation personal protective equipment, no protection). The proposed instrument showed greater reduction in the mean dose of a single exposure compared with radiation personal protective equipment especially on the left side which was proximal to the X-ray machine (≥80.0% in eye and thyroid,  ≥99.9% in breast and gonad). The proposed instrument provides a new pathway towards more convenient and efficient radioprotection.

Prediction of Age Older than 18 Years in Sub-adults by MRI Segmentation of 1st and 2nd Molars

PURPOSE

To investigate prediction of age older than 18 years in sub-adults using tooth tissue volumes from MRI segmentation of the entire 1st and 2nd molars, and to establish a model for combining information from two different molars.

MATERIALS AND METHODS

We acquired T2 weighted MRIs of 99 volunteers with a 1.5-T scanner. Segmentation was performed using SliceOmatic (Tomovision©). Linear regression was used to analyse the association between mathematical transformation outcomes of tissue volumes, age, and sex. Performance of different outcomes and tooth combinations were assessed based on the p-value of the age variable, common, or separate for each sex, depending on the selected model. The predictive probability of being older than 18 years was obtained by a Bayesian approach using information from the 1st and 2nd molars both separately and combined.

RESULTS

1st molars from 87 participants, and 2nd molars from 93 participants were included. The age range was 14-24 years with a median age of 18 years. The transformation outcome (high signal soft tissue + low signal soft tissue)/total had the strongest statistical association with age for the lower right 1st (p= 7.1*10-4 for males) and 2nd molar (p=9.44×10-7 for males and p=7.4×10-10 for females). Combining the lower right 1st and 2nd molar in males did not increase the prediction performance compared to using the best tooth alone.

CONCLUSION

MRI segmentation of the lower right 1st and 2nd molar might prove useful in the prediction of age older than 18 years in sub-adults. We provided a statistical framework to combine the information from two molars.

Magnetic resonance imaging of the knee for chronological age estimation-a systematic review

INTRODUCTION

Radiographs of the hand and teeth are frequently used for medical age assessment, as skeletal and dental maturation correlates with chronological age. These methods have been criticized for their lack of precision, and magnetic resonance imaging (MRI) of the knee has been proposed as a more accurate method. The aim of this systematic review is to explore the scientific and statistical evidence for medical age estimation based on skeletal maturation as assessed by MRI of the knee.

MATERIALS AND METHODS

A systematic review was conducted that included studies published before April 2021 on living individuals between 8 and 30 years old, with presumptively healthy knees for whom the ossification stages had been evaluated using MRI. The correlation between "mature knee" and chronological age and the risk of misclassifying a child as an adult and vice versa was calculated.

RESULTS

We found a considerable heterogeneity in the published studies -in terms of study population, MRI protocols, and grading systems used. There is a wide variation in the correlation between maturation stage and chronological age.

CONCLUSION

Data from published literature is deemed too heterogenous to support the use of MRI of the knee for chronological age determination. Further, it is not possible to assess the sensitivity, specificity, negative predictive value, or positive predictive value for the ability of MRI to determine whether a person is over or under 18 years old.

KEY POINTS

• There is an insufficient scientific basis for the use of magnetic resonance imaging of the knee in age determination by skeleton. • It is not possible to assess the predictive value of MRI of the knee to determine whether a person is over or under 18 years of age.

High performance for bone age estimation with an artificial intelligence solution

PURPOSE

The purpose of this study was to compare the performance of an artificial intelligence (AI) solution to that of a senior general radiologist for bone age assessment.

MATERIAL AND METHODS

Anteroposterior hand radiographs of eight boys and eight girls from each age interval between five and 17 year-old from four different radiology departments were retrospectively collected. Two board-certified pediatric radiologists with knowledge of the sex and chronological age of the patients independently estimated the Greulich and Pyle bone age to determine the standard of reference. A senior general radiologist not specialized in pediatric radiology (further referred to as "the reader") then determined the bone age with knowledge of the sex and chronological age. The results of the reader were then compared to those of the AI solution using mean absolute error (MAE) in age estimation.

RESULTS

The study dataset included a total of 206 patients (102 boys of mean chronological age of 10.9 ± 3.7 [SD] years, 104 girls of mean chronological age of 11 ± 3.7 [SD] years). For both sexes, the AI algorithm showed a significantly lower MAE than the reader (P < 0.007). In boys, the MAE was 0.488 years (95% confidence interval [CI]: 0.28-0.44; r² = 0.978) for the AI algorithm and 0.771 years (95% CI: 0.64-0.90; r² = 0.94) for the reader. In girls, the MAE was 0.494 years (95% CI: 0.41-0.56; r² = 0.973) for the AI algorithm and 0.673 years (95% CI: 0.54-0.81; r² = 0.934) for the reader.

CONCLUSION

The AI solution better estimates the Greulich and Pyle bone age than a general radiologist does.

Age prediction in sub-adults based on MRI segmentation of 3rd molar tissue volumes

PURPOSE

Our aim was to investigate tissue volumes measured by MRI segmentation of the entire 3rd molar for prediction of a sub-adult being older than 18 years.

MATERIAL AND METHOD

We used a 1.5-T MR scanner with a customized high-resolution single T2 sequence acquisition with 0.37 mm iso-voxels. Two dental cotton rolls drawn with water stabilized the bite and delineated teeth from oral air. Segmentation of the different tooth tissue volumes was performed using SliceOmatic (Tomovision^©). Linear regression was used to analyze the association between mathematical transformation outcomes of the tissue volumes, age, and sex. Performance of different transformation outcomes and tooth combinations were assessed based on the p value of the age variable, combined or separated for each sex depending on the selected model. The predictive probability of being older than 18 years was obtained by a Bayesian approach.

RESULTS

We included 67 volunteers (F/M: 45/22), range 14-24 years, median age 18 years. The transformation outcome (pulp + predentine)/total volume for upper 3rd molars had the strongest association with age (p = 3.4 × 10^-9).

CONCLUSION

MRI segmentation of tooth tissue volumes might prove useful in the prediction of age older than 18 years in sub-adults.

Near-Adult Heights and Adult Height Predictions Using Automated and Conventional Greulich-Pyle Bone Age Determinations in Children with Chronic Endocrine Diseases

OBJECTIVES

To validate adult height predictions (BX) using automated and Greulich-Pyle bone age determinations in children with chronic endocrine diseases.

METHODS

Heights and near-adult heights were measured in 82 patients (48 females) with chronic endocrinopathies at the age of 10.45 ± 2.12 y and at time of transition to adult care (17.98 ± 3.02 y). Further, bone age (BA) was assessed using the conventional Greulich-Pyle (GP) method by three experts, and by BoneXpert™. PAH were calculated using conventional BP tables and BoneXpert™.

RESULTS

The conventional and the automated BA determinations revealed a mean difference of 0.25 ± 0.72 y (p = 0.0027). The automated PAH by BoneXpert™ were 156.26 ± 0.86 cm (SDS - 2.01 ± 1.07) in females and 171.75 ± 1.6 cm (SDS - 1.29 ± 1.06) in males, compared to 153.95 ± 1.12 cm (SDS - 2.56 ± 1.5) in females and 169.31 ± 1.6 cm (SDS - 1.66 ± 1.56) in males by conventional BP, respectively and in comparison to near-adult heights 156.38 ± 5.84 cm (SDS - 1.91 ± 1.15) in females and 168.94 ± 8.18 cm (SDS - 1.72 ± 1.22) in males, respectively.

CONCLUSION

BA ratings and adult height predictions by BoneXpert™ in children with chronic endocrinopathies abolish rater-dependent variability and enhance reproducibility of estimates thereby refining care in growth disorders. Conventional methods may outperform automated analyses in specific cases.

Autonomous artificial intelligence in pediatric radiology: the use and perception of BoneXpert for bone age assessment

BACKGROUND

The autonomous artificial intelligence (AI) system for bone age rating (BoneXpert) was designed to be used in clinical radiology practice as an AI-replace tool, replacing the radiologist completely.

OBJECTIVE

The aim of this study was to investigate how the tool is used in clinical practice. Are radiologists more inclined to use BoneXpert to assist rather than replace themselves, and how much time is saved?

MATERIALS AND METHODS

We sent a survey consisting of eight multiple-choice questions to 282 radiologists in departments in Europe already using the software.

RESULTS

The 97 (34%) respondents came from 18 countries. Their answers revealed that before installing the automated method, 83 (86%) of the respondents took more than 2 min per bone age rating; this fell to 20 (21%) respondents after installation. Only 17/97 (18%) respondents used BoneXpert to completely replace the radiologist; the rest used it to assist radiologists to varying degrees. For instance, 39/97 (40%) never overruled the automated reading, while 9/97 (9%) overruled more than 5% of the automated ratings. The majority 58/97 (60%) of respondents checked the radiographs themselves to exclude features of underlying disease.

CONCLUSION

BoneXpert significantly reduces reporting times for bone age determination. However, radiographic analysis involves more than just determining bone age. It also involves identification of abnormalities, and for this reason, radiologists cannot be completely replaced. AI systems originally developed to replace the radiologist might be more suitable as AI assist tools, particularly if they have not been validated to work autonomously, including the ability to omit ratings when the image is outside the range of validity.

A Novel Shorthand Approach to Knee Bone Age Using MRI: A Validation and Reliability Study

Background:

Bone-age determination remains a difficult process. An atlas for bone age has been created from knee-ossification patterns on magnetic resonance imaging (MRI), thereby avoiding the need for radiographs and associated costs, radiation exposure, and clinical inefficiency. Shorthand methods for bone age can be less time-consuming and require less extensive training as compared with conventional methods.

Purpose:

To create and validate a novel shorthand algorithm for bone age based on knee MRIs that could correlate with conventional hand bone age and demonstrate reliability across medical trainees.

Study Design:

Cohort study (diagnosis); Level of evidence, 2.

Methods:

Included in this study were adolescent patients who underwent both knee MRI and hand bone age radiographs within 90 days between 2009 and 2018. A stepwise algorithm for predicting bone age using knee MRI was developed separately for male and female patients, and 7 raters at varying levels of training used the algorithm to determine the bone age for each MRI. The shorthand algorithm was validated using Spearman rho (r_S) to correlate each rater’s predicted MRI bone age with the recorded Greulich and Pyle (G&P) hand bone age. Interrater and intrarater reliability were also calculated using intraclass correlation coefficients (ICCs).

Results:

A total of 38 patients (44.7% female) underwent imaging at a mean age of 12.8 years (range, 9.3-15.7 years). Shorthand knee MRI bone age scores were strongly correlated with G&P hand bone age (r_S = 0.83; P < .001). The shorthand algorithm was a valid predictor of G&P hand bone age regardless of level of training, as medical students (r_S = 0.75), residents (r_S = 0.81), and attending physicians (r_S = 0.84) performed similarly. The interrater reliability of our shorthand algorithm was 0.81 (95% CI, 0.73-0.88), indicating good to excellent interobserver agreement. Respondents also demonstrated consistency, with 6 of 7 raters demonstrating excellent intrarater reliability (median ICC, 0.86 [range, 0.68-0.96]).

Conclusion:

This shorthand algorithm is a consistent, reliable, and valid way to determine skeletal maturity using knee MRI in patients aged 9 to 16 years and can be utilized across different levels of orthopaedic and radiographic expertise. This method is readily applicable in a clinical setting and may reduce the need for routine hand bone age radiographs.

Are Automated and Visual Greulich and Pyle-Based Methods Applicable to Caucasian European Children With a Moroccan Ethnic Origin When Assessing Bone Age?

Introduction To test the accuracy of the visual and automated bone age assessment base on the Greulich and Pyle (GP) method in healthy Caucasian European children with a Moroccan ethnic origin. Material and methods Moroccan Caucasian (MC) children were retrospectively and consecutively enrolled along with age- and sex-matched control group (CG) of European Caucasian (EC) children enrolled from the general population. The two groups included 423 children aged from 2 to 15 years with a normal left-hand radiograph performed to rule out a trauma between March 2008 and December 2017. One radiologist, blinded to the BoneXpert^® (Visiana, Holte, Denmark) estimates, visually reviewed the radiographs using the GP atlas. The BoneXpert^® automatically analysed all 423 radiographs. The intraclass correlation coefficient (ICC), linear regression and Bland-Altman plots were performed to describe the agreement between each method and the chronological age (CA) and the agreement between the two methods. Results Visual bone age assessment was related to the CA in both girls (MC ICC 0.97; EC ICC 0.97) and boys (MC ICC 0.95; EC ICC 0.96). Automated bone age assessment was related to the CA in both girls (MC ICC 0.97; EC ICC 0.96) and boys (MC ICC 0.88; EC ICC 0.96). Bland-Altman plots showed an excellent agreement between the two methods in both sexes and ethnicities before puberty especially in Moroccan boys. Conclusion Visual and automatic bone age assessment based on the GP method, previously validated in the general population of Caucasian European children, can be confidently used in healthy Caucasian European children with a Moroccan ethnic origin.

Dental and Skeletal Imaging in Forensic Age Estimation: Disparities in Current Approaches and the Continuing Search for Optimization

Medical imaging for forensic age estimation in living adolescents and young adults continues to be controversial and a subject of discussion. Because age estimation based on medical imaging is well studied, it is the current gold standard. However, large disparities exist between the centers conducting age estimation, both between and within countries. This review provides an overview of the most common approaches applied in Europe, with case examples illustrating the differences in imaging modalities, in staging of development, and in statistical processing of the age data. Additionally, the review looks toward the future because several European research groups have intensified studies on age estimation, exploring four strategies for optimization: (1) increasing sample sizes of the reference populations, (2) combining single-site information into multifactorial information, (3) avoiding ionizing radiation, and (4) conducting a fully automated analysis.

Applicability of two commonly used bone age assessment methods to twenty-first century UK children

Objectives

To assess the effect of secular change on skeletal maturation and thus on the applicability of the Greulich and Pyle (G&P) and Tanner and Whitehouse (TW3) methods.

Methods

BoneXpert was used to assess bone age from 392 hand trauma radiographs (206 males, 257 left). The paired sample t test was performed to assess the difference between mean bone age (BA) and mean chronological age (CA). ANOVA was used to assess the differences between groups based on socioeconomic status (taken from the Index of Multiple Deprivation).

Results

CA ranged from 2 to 15 years for females and 2.5 to 15 years for males. Numbers of children living in low, average and high socioeconomic areas were 216 (55%), 74 (19%) and 102 (26%) respectively. We found no statistically significant difference between BA and CA when using G&P. However, using TW3, CA was underestimated in females beyond the age of 3 years, with significant differences between BA and CA (− 0.43 years, SD 1.05, p = < 0.001) but not in males (0.01 years, SD 0.97, p = 0.76). Of the difference in females, 17.8% was accounted for by socioeconomic status.

Conclusion

No significant difference exists between BoneXpert-derived BA and CA when using the G&P atlas in our study population. There was a statistically significant underestimation of BoneXpert-derived BA compared with CA in females when using TW3, particularly in those from low and average socioeconomic backgrounds. Secular change has not led to significant advancement in skeletal maturation within our study population.

Key Points

• The Greulich and Pyle method can be applied to the present-day United Kingdom (UK) population.

• The Tanner and Whitehouse (TW3) method consistently underestimates the age of twenty-first century UK females by an average of 5 months.

• Secular change has not advanced skeletal maturity of present-day UK children compared with those of the mid-twentieth century.

Electronic supplementary material

The online version of this article (10.1007/s00330-019-06300-x) contains supplementary material, which is available to authorized users.