Validation and reference values of automated bone age determination for four ethnicities

Association between bone age maturity and childhood adiposity

BACKGROUND

Evidence shows that overweight and obesity are associated with advanced bone age (BA).

OBJECTIVE

To analyse the effect of adiposity on BA among Mexican children.

METHODS

This cross-sectional study included 902 children (5-18 years old). Anthropometric measurements, dual-energy X-ray absorptiometry (DXA) and automated hand X-ray-based BA measurements were obtained. BA curves of children stratified by sex and age were created based on nutritional status. We also calculated odds ratios for advanced BA associated with the body mass index (BMI), waist/height ratio and adiposity estimated using DXA (total and truncal fat mass).

RESULTS

Participants with overweight/obesity by BMI (SDS ≥1) advanced earlier in BA than did normal weight participants (6.0 vs. 12.0 years in boys and 6.0 vs. 10.3 in girls, p < 0.01); similarly, participants with a greater body fat percentage (SDS ≥1) exhibited earlier advanced BA (7.5 vs. 10.0 years in boys and 6.0 vs. 9.6 in girls, p < 0.01). Differences were also observed according to the waist/height ratio and truncal fat. Children with a BMI or DXA SDS ≥1 had greater odds of presenting an advanced BA of more than 1 year (OR 1.79-3.55, p < 0.05).

CONCLUSIONS

Increased adiposity in children, mainly in boys, is associated with advanced BA at earlier ages.

Validation of an AI-Powered Automated X-ray Bone Age Analyzer in Chinese Children and Adolescents: A Comparison with the Tanner-Whitehouse 3 Method

INTRODUCTION

Automated bone age assessment (BAA) is of growing interest because of its accuracy and time efficiency in daily practice. In this study, we validated the clinical applicability of a commercially available artificial intelligence (AI)-powered X-ray bone age analyzer equipped with a deep learning-based automated BAA system and compared its performance with that of the Tanner-Whitehouse 3 (TW-3) method.

METHODS

Radiographs prospectively collected from 30 centers across various regions in China, including 900 Chinese children and adolescents, were assessed independently by six doctors (three experts and three residents) and an AI analyzer for TW3 radius, ulna, and short bones (RUS) and TW3 carpal bone age. The experts' mean estimates were accepted as the gold standard. The performance of the AI analyzer was compared with that of each resident.

RESULTS

For the estimation of TW3-RUS, the AI analyzer had a mean absolute error (MAE) of 0.48 ± 0.42. The percentage of patients with an absolute error of < 1.0 years was 86.78%. The MAE was significantly lower than that of rater 1 (0.54 ± 0.49, P = 0.0068); however, it was not significant for rater 2 (0.48 ± 0.48) or rater 3 (0.49 ± 0.46). For TW3 carpal, the AI analyzer had an MAE of 0.48 ± 0.65. The percentage of patients with an absolute error of < 1.0 years was 88.78%. The MAE was significantly lower than that of rater 2 (0.58 ± 0.67, P = 0.0018) and numerically lower for rater 1 (0.54 ± 0.64) and rater 3 (0.50 ± 0.53). These results were consistent for the subgroups according to sex, and differences between the age groups were observed.

CONCLUSION

In this comprehensive validation study conducted in China, an AI-powered X-ray bone age analyzer showed accuracies that matched or exceeded those of doctor raters. This method may improve the efficiency of clinical routines by reducing reading time without compromising accuracy.

Acceleration of skeletal maturation in Central Europe over the last two decades: insights from two cohorts of healthy children

BACKGROUND

Deviations between the determination of bone age (BA) according to Greulich and Pyle (G&P) and chronological age (CA) are common in Caucasians. Assessing these discrepancies in a population over time requires analysis of large samples and low intra-observer variability in BA estimation, both can be achieved with artificial intelligence-based software. The latest software-based reference curve contrasting the BA determined by G&P to the CA of Central European children dates back over two decades.

OBJECTIVE

To examine whether the reference curve from a historical cohort from the Netherlands (Rotterdam cohort) between BA determined by G&P and CA still applies to a current Central European cohort and derive a current reference curve.

MATERIALS AND METHODS

This retrospective single-center study included 1,653 children and adolescents (aged 3-17 years) who had received a radiograph of the hand following trauma. The G&P BA estimated using artificial intelligence-based software was contrasted with the CA, and the deviations were compared with the Rotterdam cohort.

RESULTS

Among the participants, the mean absolute error between BA and CA was 0.92 years for girls and 0.97 years for boys. For the ages of 8 years (boys) and 11 years (girls) and upward, the mean deviation was significantly greater in the current cohort than in the Rotterdam cohort. The reference curves of both cohorts also differed significantly from each other (P < 0.001 for both boys and girls).

CONCLUSION

The BA of the current Central European population and that of the curve from the Rotterdam cohort from over two decades ago differ. Whether this effect can be attributed to accelerated bone maturation needs further evaluation.

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.

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.

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.

A comprehensive validation study of the latest version of BoneXpert on a large cohort of Caucasian children and adolescents

INTRODUCTION

Automated bone age assessment has recently become increasingly popular. The aim of this study was to assess the agreement between automated and manual evaluation of bone age using the method according to Tanner-Whitehouse (TW3) and Greulich-Pyle (GP).

METHODS

We evaluated 1285 bone age scans from 1202 children (657 scans from 612 boys) by using both manual and automated (TW3 as well as GP) bone age assessment. BoneXpert software versions 2.4.5.1. (BX2) and 3.2.1. (BX3) (Visiana, Holte, Denmark) were compared with manual evaluation using root mean squared error (RMSE) analysis.

RESULTS

RMSE for BX2 was 0.57 and 0.55 years in boys and 0.72 and 0.59 years in girls, respectively for TW3 and GP. For BX3, RMSE was 0.51 and 0.68 years in boys and 0.49 and 0.52 years in girls, respectively for TW3 and GP. Sex- and age-specific analysis for BX2 identified the largest differences between manual and automated TW3 evaluation in girls between 6-7, 12-13, 13-14 and 14-15 years, with RMSE 0.88, 0.81, 0.92 and 0.84 years, respectively. The BX3 version showed better agreement with manual TW3 evaluation (RMSE 0.64, 0.45, 0.46 and 0.57).

CONCLUSION

The latest version of the BoneXpert software provides improved and clinically sufficient agreement with manual bone age evaluation in children of both sexes compared to the previous version and may be used for routine bone age evaluation in non-selected cases in pediatric endocrinology care.

Automated detection of acute appendicular skeletal fractures in pediatric patients using deep learning

OBJECTIVE

We aimed to perform an external validation of an existing commercial AI software program (BoneView™) for the detection of acute appendicular fractures in pediatric patients.

MATERIALS AND METHODS

In our retrospective study, anonymized radiographic exams of extremities, with or without fractures, from pediatric patients (aged 2-21) were included. Three hundred exams (150 with fractures and 150 without fractures) were included, comprising 60 exams per body part (hand/wrist, elbow/upper arm, shoulder/clavicle, foot/ankle, leg/knee). The Ground Truth was defined by experienced radiologists. A deep learning algorithm interpreted the radiographs for fracture detection, and its diagnostic performance was compared against the Ground Truth, and receiver operating characteristic analysis was done. Statistical analyses included sensitivity per patient (the proportion of patients for whom all fractures were identified) and sensitivity per fracture (the proportion of fractures identified by the AI among all fractures), specificity per patient, and false-positive rate per patient.

RESULTS

There were 167 boys and 133 girls with a mean age of 10.8 years. For all fractures, sensitivity per patient (average [95% confidence interval]) was 91.3% [85.6, 95.3], specificity per patient was 90.0% [84.0,94.3], sensitivity per fracture was 92.5% [87.0, 96.2], and false-positive rate per patient in patients who had no fracture was 0.11. The patient-wise area under the curve was 0.93 for all fractures. AI diagnostic performance was consistently high across all anatomical locations and different types of fractures except for avulsion fractures (sensitivity per fracture 72.7% [39.0, 94.0]).

CONCLUSION

The BoneView™ deep learning algorithm provides high overall diagnostic performance for appendicular fracture detection in pediatric patients.

Current and emerging artificial intelligence applications for pediatric musculoskeletal radiology

Artificial intelligence (AI) is playing an ever-increasing role in radiology (more so in the adult world than in pediatrics), to the extent that there are unfounded fears it will completely take over the role of the radiologist. In relation to musculoskeletal applications of AI in pediatric radiology, we are far from the time when AI will replace radiologists; even for the commonest application (bone age assessment), AI is more often employed in an AI-assist mode rather than an AI-replace or AI-extend mode. AI for bone age assessment has been in clinical use for more than a decade and is the area in which most research has been conducted. Most other potential indications in children (such as appendicular and vertebral fracture detection) remain largely in the research domain. This article reviews the areas in which AI is most prominent in relation to the pediatric musculoskeletal system, briefly summarizing the current literature and highlighting areas for future research. Pediatric radiologists are encouraged to participate as members of the research teams conducting pediatric radiology artificial intelligence research.

A comparison of bone age assessments using automated and manual methods in children of Indian ethnicity

BACKGROUND

Bone age is useful for pediatric endocrinologists in evaluating various disorders related to growth and puberty. Traditional methods of bone age assessment, namely Greulich and Pyle (GP) and Tanner-Whitehouse (TW), have intra- and interobserver variations. Use of computer-automated methods like BoneXpert might overcome these subjective variations.

OBJECTIVE

The aim of our study was to assess the validity of BoneXpert in comparison to manual GP and TW methods for assessing bone age in children of Asian Indian ethnicity.

MATERIALS AND METHODS

We extracted from a previous study the deidentified left hand radiographs of 920 healthy children aged 2-19 years. We compared bone age as determined by four well-trained manual raters using GP and TW methods with the BoneXpert ratings. We computed accuracy using root mean square error (RMSE) to assess how close the bone age estimated by BoneXpert was to the reference rating.

RESULTS

The standard deviations (SDs) of rating among the four manual raters were 0.52 years, 0.52 years and 0.47 years for GP, TW2 and TW3 methods, respectively. The RMSEs between the automated bone age estimates and the true ratings were 0.39 years, 0.41 years and 0.36 years, respectively, for the same methods. The RMSE values were significantly lower in girls than in boys (0.53, 0.5 and 0.47 vs. 0.39, 0.47 and 0.4) by all the methods; however, no such difference was noted in classification by body mass index. The best agreement between BoneXpert and manual rating was obtained by using 50% weight on carpals (GP50). The carpal bone age was retarded in Indian children, more so in boys.

CONCLUSION

BoneXpert was accurate and performed well in estimating bone age by both GP and TW methods in healthy Asian Indian children; the error was larger in boys. The GP50 establishes "backward compatibility" with manual rating.

Validation of automated bone age analysis from hand radiographs in a North American pediatric population

BACKGROUND

Radiographic bone age assessment by automated software is precise and instantaneous.

OBJECTIVE

The aim of this study was to evaluate the accuracy of an automated tool for bone age assessment.

MATERIALS AND METHODS

We compared a total of 586 bone age radiographs from 451 patients, which had been assessed by three radiologists from 2013 to 2018, with bone age analysis by BoneXpert, using the Greulich and Pyle method. We made bone age comparisons in different patient groups based on gender, diagnosis and race, and in a subset with repeated bone age studies. We calculated Spearman correlation (r) and accuracy (root mean square error, or R²).

RESULTS

Bone age analyses by automated and manual assessments showed a strong correlation (r=0.98; R²=0.96; P<0.0001), with the mean bone age difference of 0.12±0.76 years. Bone age comparisons by the two methods remained strongly correlated (P<0.0001) when stratified by gender, common endocrine conditions including growth disorders and early/precocious puberty, and race. In the longitudinal analysis, we also found a strong correlation between the automated software and manual bone age over time (r=0.7852; R²=0.63; P<0.01).

CONCLUSION

Automated bone age assessment was found to be reliable and accurate in a large cohort of pediatric patients in a clinical practice setting in North America.

Accuracy and self-validation of automated bone age determination

The BoneXpert method for automated determination of bone age from hand X-rays was introduced in 2009 and is currently running in over 200 hospitals. The aim of this work is to present version 3 of the method and validate its accuracy and self-validation mechanism that automatically rejects an image if it is at risk of being analysed incorrectly. The training set included 14,036 images from the 2017 Radiological Society of North America (RSNA) Bone Age Challenge, 1642 images of normal Dutch and Californian children, and 8250 images from Tübingen from patients with Short Stature, Congenital Adrenal Hyperplasia and Precocious Puberty. The study resulted in a cross-validated root mean square (RMS) error in the Tübingen images of 0.62 y, compared to 0.72 y in the previous version. The RMS error on the RSNA test set of 200 images was 0.45 y relative to the average of six manual ratings. The self-validation mechanism rejected 0.4% of the RSNA images. 121 outliers among the self-validated images of the Tübingen study were rerated, resulting in 6 cases where BoneXpert deviated more than 1.5 years from the average of the three re-ratings, compared to 72 such cases for the original manual ratings. The accuracy of BoneXpert is clearly better than the accuracy of a single manual rating. The self-validation mechanism rejected very few images, typically with abnormal anatomy, and among the accepted images, there were 12 times fewer severe bone age errors than in manual ratings, suggesting that BoneXpert could be safer than manual rating.

External validation of deep learning-based bone-age software: a preliminary study with real world data

Artificial intelligence (AI) is increasingly being used in bone-age (BA) assessment due to its complicated and lengthy nature. We aimed to evaluate the clinical performance of a commercially available deep learning (DL)–based software for BA assessment using a real-world data. From Nov. 2018 to Feb. 2019, 474 children (35 boys, 439 girls, age 4–17 years) were enrolled. We compared the BA estimated by DL software (DL-BA) with that independently estimated by 3 reviewers (R1: Musculoskeletal radiologist, R2: Radiology resident, R3: Pediatric endocrinologist) using the traditional Greulich–Pyle atlas, then to his/her chronological age (CA). A paired t-test, Pearson’s correlation coefficient, Bland–Altman plot, mean absolute error (MAE) and root mean square error (RMSE) were used for the statistical analysis. The intraclass correlation coefficient (ICC) was used for inter-rater variation. There were significant differences between DL-BA and each reviewer’s BA (P < 0.025), but the correlation was good with one another (r = 0.983, P < 0.025). RMSE (MAE) values were 10.09 (7.21), 10.76 (7.88) and 13.06 (10.06) months between DL-BA and R1, R2, R3 BA. Compared with the CA, RMSE (MAE) values were 13.54 (11.06), 15.18 (12.11), 16.19 (12.78) and 19.53 (17.71) months for DL-BA, R1, R2, R3 BA, respectively. Bland–Altman plots revealed the software and reviewers’ tendency to overestimate the BA in general. ICC values between 3 reviewers were 0.97, 0.85 and 0.86, and the overall ICC value was 0.93. The BA estimated by DL-based software showed statistically similar, or even better performance than that of reviewers’ compared to the chronological age in the real world clinic.

Factors affecting prepubertal and pubertal bone age progression

Bone age (BA) is a clinical marker of bone maturation which indicates the developmental stage of endochondral ossification at the epiphysis and the growth plate. Hormones that promote the endochondral ossification process include growth hormone, insulin-like growth factor-1, thyroid hormone, estrogens, and androgens. In particular, estrogens are essential for growth plate fusion and closure in both sexes. Bone maturation in female children is more advanced than in male children of all ages. The promotion of bone maturation seen in females before the onset of puberty is thought to be an effect of estrogen because estrogen levels are higher in females than in males before puberty. Sex hormones are essential for bone maturation during puberty. Since females have their pubertal onset about two years earlier than males, bone maturation in females is more advanced than in males during puberty. In the present study, we aimed to review the factors affecting prepubertal and pubertal BA progression, BA progression in children with hypogonadism, and bone maturation and deformities in children with Turner syndrome.

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.

"Which skeletal imaging modality is best for assessing bone health in children and young adults compared to DXA? A systematic review and meta-analysis"

BACKGROUND

Skeletal imaging techniques have become clinically valuable methods for measuring and assessing bone mineral density in children and young people. Dual-energy X-ray absorptiometry (DXA) is the current reference standard for evaluating bone density, as recommended by the International Society for Clinical Densitometry (ISCD). Various bone imaging modalities, such as quantitative ultrasound (QUS), peripheral quantitative computed tomography (pQCT), high-resolution peripheral quantitative computed tomography (HR-pQCT), magnetic resonance imaging (MRI), and digital X-ray radiogrammetry (DXR) have been developed to further quantify bone health in children and adults. The purpose of this review, with meta-analysis, was to systematically research the literature to compare the various imaging methods and identify the best modality for assessing bone status in healthy papulations and children and young people with chronic disease (up to 18 years).

METHODS

A systematic computerized search of Medline, PubMed, and Web of Science databases was conducted to identify English-only studies published between 1st January 1990 and 1st December 2019. In this review, clinical studies comparing imaging modalities with DXA were chosen according to the inclusion criteria. The risk of bias and quality of articles was assessed using the Quality Assessment Tool for Diagnostic Accuracy Studies (QUADAS-2). The meta-analysis to estimate the overall correlation was performed using a Fisher Z transformation of the correlation coefficient. Additionally, the diagnostic accuracy measures of different imaging methods compared with DXA were calculated.

RESULTS

The initial search strategy identified 13,412 papers, 29 of which matched the inclusion and exclusion criteria. Of these, twenty-two papers were included in the meta-analysis. DXA was compared to QUS in 17 papers, to DXR in 7 and to pQCT in 4 papers. A single paper compared DXA, DXR, and pQCT. The meta-analysis demonstrated that the strongest correlation was between DXR and DXA, with a coefficient of 0.71 [95%CI: 0.43; 1.00, p-value < 0.001], while the correlation coefficients between QUS and DXA, and pQCT and DXA were 0.57 [95%CI: 0.25; 0.90, p-value < 0.001] and 0.57 [95%CI: 0.46; 0.67, p-value < 0.001], respectively. The overall sensitivity and specificity were statistically significant 0.71 and 0.80, respectively.

CONCLUSION

No current imaging modality provides a full evaluation of bone health in children and young adults, with each method having some limitations. Compared to QUS and pQCT, DXR achieved the strongest positive relationship with DXA. DXR should be further evaluated as a reliable method for assessing bone health and as a predictor of fractures in children and young people.

Traditional and New Methods of Bone Age Assessment-An Overview

Bone age is one of biological indicators of maturity used in clinical practice and it is a very important parameter of a child’s assessment, especially in paediatric endocrinology. The most widely used method of bone age assessment is by performing a hand and wrist radiograph and its analysis with Greulich-Pyle or Tanner-Whitehouse atlases, although it has been about 60 years since they were published. Due to the progress in the area of Computer-Aided Diagnosis and application of artificial intelligence in medicine, lately, numerous programs for automatic bone age assessment have been created. Most of them have been verified in clinical studies in comparison to traditional methods, showing good precision while eliminating inter- and intra-rater variability and significantly reducing the time of assessment. Additionally, there are available methods for assessment of bone age which avoid X-ray exposure, using modalities such as ultrasound or magnetic resonance imaging.

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.

Automated Bone Age Assessment Using Artificial Intelligence: The Future of Bone Age Assessment

Bone age assessments are a complicated and lengthy process, which are prone to inter- and intra-observer variabilities. Despite the great demand for fully automated systems, developing an accurate and robust bone age assessment solution has remained challenging. The rapidly evolving deep learning technology has shown promising results in automated bone age assessment. In this review article, we will provide information regarding the history of automated bone age assessments, discuss the current status, and present a literature review, as well as the future directions of artificial intelligence-based bone age assessments.

Age estimation from the biometric information of hand bones: Development of new formulas

INTRODUCTION

In the judicial context of the age estimation of living individuals, a new method was recently proposed, based on the collection of biometric information on hand bones radiographs. The aim of this study was to apply this method to a large French sample to provide new tools for age estimation MATERIALS AND METHODS: The study sample consisted of metacarpals and proximal phalanges measurements of 1003 individuals aged less than 21 years. This sample was divided into two subgroups 1-12 and 13-21 years as the age of 13 is a relevant legal threshold for most European countries. A quadratic discriminant analysis was performed to identify the group to which an individual was most likely to belong. Age estimation formulas were also constructed from linear models: for each subgroup and the total sample.

RESULTS

The belonging of an individual to the 1-12 or 13-21 subgroup was determined with a correct classification rate of 89.8%. Age estimation formulas became less precise with age, with a mean absolute error ranging between 11 and 21 months.

CONCLUSION

We proposed a two-step procedure for age estimation: firstly, the identification of the age group to which the individual is most likely to belong, and secondly, the age estimation of this individual by applying the appropriate formula.

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.

Cortical Bone Mass is Low in Boys with Klinefelter Syndrome and Improves with Oxandrolone

Context

Klinefelter syndrome (KS) is the most common sex aneuploidy in men. Affected males have hypogonadism, and, as a result, face an increased risk for osteoporosis and fractures. Androgen therapy is standard in adolescents and adults with KS but has not been used earlier in childhood.

Objective

To determine the effects of androgen treatment on bone mass in children with KS.

Methods

Randomized, double-blind, placebo-controlled clinical trial of oxandrolone (OX; 0.06 mg/kg daily; n = 38) versus placebo (PL; n = 40) for 2 years in boys with KS (ages 4-12 years). Changes in bone mass were examined by digital x-ray radiogrammetry, which determines the Bone Health Index (BHI) and standard deviation score (SDS).

Results

BHI SDS was similar between groups at baseline (–0.46 ± 1.1 vs –0.34 ± 1.0 OX vs PL, P > .05) and higher in the OX group at 2 years (–0.1 ± 1.3 vs –0.53 ± 0.9, OX vs PL, P < .01). At baseline, BHI SDS values of all subjects were not normally distributed with 25.7% of subjects plotted below –1 SDS (P < .001), suggesting a deficit in bone mass. In total, 13.5% of subjects had sustained a fracture and their BHI SDS was lower than those with no fractures (–1.6 ± 1.3 vs –0.3 ± 1.0, P = .004).

Conclusion

Bone mass using BHI SDS is reduced in some children with KS and improves with OX. Since these individuals are at risk for osteoporosis, age-appropriate androgen replacement and future studies on bone health in children with KS should be further explored.

Skeletal Maturation in the Current Pediatric Mexican Population

OBJECTIVE

The most commonly used methods for bone age (BA) reading were described in the Caucasian population decades ago. However, there are secular trends in skeletal maturation and different BA patterns between ethnic groups. Automated BA reading makes updating references easier and more precise than human reading. The objective of the present study was to present automated BA reference curves according to chronological age and gender in the Mexican population and compare the maturation tempo with that of other populations.

METHODS

The study included 923 healthy participants aged 5 to 18 years between 2017 and 2018. A hand radio-graph was analyzed using BoneXpert software to obtain the automated BA reading according to Greulich and Pyle (G&P) and Tanner-Whitehouse 2 (TW2) references. We constructed reference curves using the average difference between the BA and chronological age according to sex and age.

RESULTS

The G&P and TW2 automated reference curves showed that Mexican boys exhibit delays in BA during middle childhood by 0.5 to 0.7 (95% confidence interval &lsqb;CI], -0.9 to -0.2) years; however, they demonstrate an advanced BA of up to 1.1 (95% CI, 0.8 to 1.4) years at the end of puberty. Mexican girls exhibited a delay in BA by 0.3 to 0.6 (95% CI, -0.9 to -0.1) years before puberty and an advanced BA of up to 0.9 (95% CI, 0.7 to 1.2) years at the end of puberty.

CONCLUSION

Mexican children aged <10 years exhibited a delay in skeletal maturity, followed by an advanced BA by approximately 1 year at the end of puberty. This may affect the estimation of growth potential in this population.

Magnetic resonance imaging for forensic age estimation in living children and young adults: a systematic review

The use of MRI in forensic age estimation has been explored extensively during the last decade. The authors of this paper synthesized the available MRI data for forensic age estimation in living children and young adults to provide a comprehensive overview that can guide age estimation practice and future research. To do so, the authors searched MEDLINE, Embase and Web of Science, along with cited and citing articles and study registers. Two authors independently selected articles, conducted data extraction, and assessed risk of bias. They considered study populations including living subjects up to 30 years old. Fifty-five studies were included in qualitative analysis and 33 in quantitative analysis. Most studies had biases including use of relatively small European (Caucasian) populations, varying MR approaches and varying staging techniques. Therefore, it was not appropriate to pool the age distribution data. The authors found that reproducibility of staging was remarkably lower in clavicles than in any other anatomical structure. Age estimation performance was in line with the gold standard, radiography, with mean absolute errors ranging from 0.85 years to 2.0 years. The proportion of correctly classified minors ranged from 65% to 91%. Multifactorial age estimation performed better than that based on a single anatomical site. The authors found that more multifactorial age estimation studies are necessary, together with studies testing whether the MRI data can safely be pooled. The current review results can guide future studies, help medical professionals to decide on the preferred approach for specific cases, and help judicial professionals to interpret the evidential value of age estimation results.

Automatic assessment of bone age in Taiwanese children: A comparison of the Greulich and Pyle method and the Tanner and Whitehouse 3 method

Proper bone age assessment is crucial for the clinical diagnosis and evaluation of treatment responses. We investigated the applicability of Greulich and Pyle (GP), and Tanner and Whitehouse 3 (TW3) methods for children in modern Taiwan, using computer-aided diagnosis. Hand and wrist radiographs were obtained from 611 children (3-17 years) who came to our emergency department due to trauma. Ages 0 to 2 years old were excluded because of a limited number of cases. Skeletal maturation was assessed using the BoneXpert (version 2.5.4.1 automated software), which determines GP and TW3 bone age. The two scoring systems were evaluated for comparing the chronological ages in each subgroup. In boys, mean GP bone age vs mean chronological ages were delayed for ages 3 to 11 and advanced for age 12 to 17. In girls, mean GP bone age vs mean chronological ages was delayed for ages 4 to 8 and 17, and advanced for ages 3 and 9 to 17. In boys, the mean TW3 bone ages vs mean chronological ages were delayed for ages 5 to 10 except age 8, and advanced for ages 3 to 4, 8, and 11 to 15. In girls, the mean TW3 bone ages vs mean chronological ages were delayed for ages 4 to 12, and advanced for ages 3 and 13 to 14. By using the BoneXpert automatic software, we established bone age reference standards for children in Taiwan. Clinical application of GP and TW3 scoring methods can be adjusted according to our results to better assess bone age.

Rethinking Greulich and Pyle: A Deep Learning Approach to Pediatric Bone Age Assessment Using Pediatric Trauma Hand Radiographs

Purpose

To develop a deep learning approach to bone age assessment based on a training set of developmentally normal pediatric hand radiographs and to compare this approach with automated and manual bone age assessment methods based on Greulich and Pyle (GP).

Methods

In this retrospective study, a convolutional neural network (trauma hand radiograph-trained deep learning bone age assessment method [TDL-BAAM]) was trained on 15 129 frontal view pediatric trauma hand radiographs obtained between December 14, 2009, and May 31, 2017, from Children's Hospital of New York, to predict chronological age. A total of 214 trauma hand radiographs from Hasbro Children's Hospital were used as an independent test set. The test set was rated by the TDL-BAAM model as well as a GP-based deep learning model (GPDL-BAAM) and two pediatric radiologists (radiologists 1 and 2) using the GP method. All ratings were compared with chronological age using mean absolute error (MAE), and standard concordance analyses were performed.

Results

The MAE of the TDL-BAAM model was 11.1 months, compared with 12.9 months for GPDL-BAAM (P = .0005), 14.6 months for radiologist 1 (P < .0001), and 16.0 for radiologist 2 (P < .0001). For TDL-BAAM, 95.3% of predictions were within 24 months of chronological age compared with 91.6% for GPDL-BAAM (P = .096), 86.0% for radiologist 1 (P < .0001), and 84.6% for radiologist 2 (P < .0001). Concordance was high between all methods and chronological age (intraclass coefficient > 0.93). Deep learning models demonstrated a systematic bias with a tendency to overpredict age for younger children versus radiologists who showed a consistent mean bias.

Conclusion

A deep learning model trained on pediatric trauma hand radiographs is on par with automated and manual GP-based methods for bone age assessment and provides a foundation for developing population-specific deep learning algorithms for bone age assessment in modern pediatric populations.Supplemental material is available for this article.© RSNA, 2020See also the commentary by Halabi in this issue.

Bone Health Index and bone turnover in pediatric patients with type 1 diabetes mellitus and poor metabolic control

BACKGROUND

There is a need for a non-invasive, affordable, and reliable method for bone health screening in pediatric patients at risk.

OBJECTIVE

To assess Bone Health Index (BHI) in pediatric patients with type 1 diabetes (T1D) and its relation to bone metabolism, age at onset, duration, control, and insulin dose.

SUBJECTS AND METHODS

Left-hand radiographs were obtained from 65 patients with T1D, mean age 11.23 ± 3.89 years, mean disease duration 5.23 ± 3.76 years and mean glycosylated hemoglobin (HbA1c)-83 mmol/mol (9.7%). Blood and 24 hours urine samples were collected for bone and mineral metabolism assessment. BoneXpert was used to determine BHI, Bone Health Index standard deviation score (BHI SDS), and bone age.

RESULTS

Mean BHI SDS was -1.15 ± 1.19 (n = 54). In 20.37% (n = 11) BHI SDS was < -2SD with mean value -2.82 ± 0. 69, P < .001. These patients had lower levels of beta cross laps (0.77  ± 0.33 ng/mL vs 1.17 ± 0.47 ng/mL), osteocalcin (47.20 ± 14.07 ng/mL vs 75.91 ± 32.08 ng/mL), serum magnesium (0.79 ± 0.05 mmol/L vs 0.83 ± 0.06 mmol/L) and phosphorus (1.48 ± 0.29 mmol/L vs 1.71 ± 0.28 mmol/L) but higher ionized calcium (1.29 ± 0.04 mmol/L vs 1.26 ± 0.05 mmol/L), P < .05, compared to patients with BHI SDS in the normal range. We found a positive correlation between BHI SDS and age at manifestation (r = 0.307, P = 0.024) and a negative one with disease duration (r = -0.284, P = .038). No correlations were found with HbA1c, insulin dose, height, weight, BMI.

CONCLUSIONS

To the best of our knowledge, this is the first study to assess bone health in pediatric patients with T1D using BHI. We found significantly decreased cortical bone density and bone turnover in 20.37%. Earlier age at onset and diabetes duration may have a negative impact on cortical bone density in patients with poor control. Longitudinal studies are needed to follow changes or to assess future interventions.

Artificial intelligence in bone age assessment: accuracy and efficiency of a novel fully automated algorithm compared to the Greulich-Pyle method

Background

Bone age (BA) assessment performed by artificial intelligence (AI) is of growing interest due to improved accuracy, precision and time efficiency in daily routine. The aim of this study was to investigate the accuracy and efficiency of a novel AI software version for automated BA assessment in comparison to the Greulich-Pyle method.

Methods

Radiographs of 514 patients were analysed in this retrospective study. Total BA was assessed independently by three blinded radiologists applying the GP method and by the AI software. Overall and gender-specific BA assessment results, as well as reading times of both approaches, were compared, while the reference BA was defined by two blinded experienced paediatric radiologists in consensus by application of the Greulich-Pyle method.

Results

Mean absolute deviation (MAD) and root mean square deviation (RSMD) were significantly lower between AI-derived BA and reference BA (MAD 0.34 years, RSMD 0.38 years) than between reader-calculated BA and reference BA (MAD 0.79 years, RSMD 0.89 years; p < 0.001). The correlation between AI-derived BA and reference BA (r = 0.99) was significantly higher than between reader-calculated BA and reference BA (r = 0.90; p < 0.001). No statistical difference was found in reader agreement and correlation analyses regarding gender (p = 0.241). Mean reading times were reduced by 87% using the AI system.

Conclusions

A novel AI software enabled highly accurate automated BA assessment. It may improve efficiency in clinical routine by reducing reading times without compromising the accuracy compared with the Greulich-Pyle method.

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.

Bone age determination in eutrophic, overweight and obese Brazilian children and adolescents: a comparison between computerized BoneXpert and Greulich-Pyle methods

BACKGROUND

Bone age determination is usually employed to evaluate growth disorders and their treatment. The Greulich-Pyle method is the simplest and most frequently used type of evaluation, but it presents huge interobserver variability. The BoneXpert is a computer-automated method developed to avoid significant bone age variability among distinct observers.

OBJECTIVE

To compare the BoneXpert and Greulich-Pyle methods of bone age determination in eutrophic children and adolescents, as well as in overweight and obese pediatric patients.

MATERIALS AND METHODS

The sample comprised 515 participants, 253 boys (159 eutrophic, 53 overweight and 41 obese) and 262 girls (146 eutrophic, 76 overweight and 40 obese). Left hand and wrist radiographs were acquired for bone age determination using both methods.

RESULTS

There was a positive correlation between chronological age and Greulich-Pyle, chronological age and BoneXpert, and Greulich-Pyle and BoneXpert. There was a significant increase (P<0.05) in bone age in both the Greulich-Pyle and BoneXpert methods in obese boys when compared to eutrophic or overweight boys of the same age. In girls, there was an increase in bone age in both obese and overweight individuals when compared to eutrophic girls (P<0.05). The Greulich-Pyle bone age was advanced in comparison to that of BoneXpert in all groups, except in obese boys, in which bone age was similarly advanced in both methods.

CONCLUSION

The BoneXpert computer-automated bone age determination method showed a significant positive correlation with chronological age and Greulich-Pyle. Furthermore, the impact of being overweight or obese on bone age could be identified by both methods.

Automated age estimation from MRI volumes of the hand

Highly relevant for both clinical and legal medicine applications, the established radiological methods for estimating unknown age in children and adolescents are based on visual examination of bone ossification in X-ray images of the hand. Our group has initiated the development of fully automatic age estimation methods from 3D MRI scans of the hand, in order to simultaneously overcome the problems of the radiological methods including (1) exposure to ionizing radiation, (2) necessity to define new, MRI specific staging systems, and (3) subjective influence of the examiner. The present work provides a theoretical background for understanding the nonlinear regression problem of biological age estimation and chronological age approximation. Based on this theoretical background, we comprehensively evaluate machine learning methods (random forests, deep convolutional neural networks) with different simplifications of the image information used as an input for learning. Trained on a large dataset of 328 MR images, we compare the performance of the different input strategies and demonstrate unprecedented results. For estimating biological age, we obtain a mean absolute error of 0.37 ± 0.51 years for the age range of the subjects  ≤  18 years, i.e. where bone ossification has not yet saturated. Finally, we validate our findings by adapting our best performing method to 2D images and applying it to a publicly available dataset of X-ray images, showing that we are in line with the state-of-the-art automatic methods for this task.

Bone age assessment with various machine learning techniques: A systematic literature review and meta-analysis

BACKGROUND

The assessment of bone age and skeletal maturity and its comparison to chronological age is an important task in the medical environment for the diagnosis of pediatric endocrinology, orthodontics and orthopedic disorders, and legal environment in what concerns if an individual is a minor or not when there is a lack of documents. Being a time-consuming activity that can be prone to inter- and intra-rater variability, the use of methods which can automate it, like Machine Learning techniques, is of value.

OBJECTIVE

The goal of this paper is to present the state of the art evidence, trends and gaps in the research related to bone age assessment studies that make use of Machine Learning techniques.

METHOD

A systematic literature review was carried out, starting with the writing of the protocol, followed by searches on three databases: Pubmed, Scopus and Web of Science to identify the relevant evidence related to bone age assessment using Machine Learning techniques. One round of backward snowballing was performed to find additional studies. A quality assessment was performed on the selected studies to check for bias and low quality studies, which were removed. Data was extracted from the included studies to build summary tables. Lastly, a meta-analysis was performed on the performances of the selected studies.

RESULTS

26 studies constituted the final set of included studies. Most of them proposed automatic systems for bone age assessment and investigated methods for bone age assessment based on hand and wrist radiographs. The samples used in the studies were mostly comprehensive or bordered the age of 18, and the data origin was in most of cases from United States and West Europe. Few studies explored ethnic differences.

CONCLUSIONS

There is a clear focus of the research on bone age assessment methods based on radiographs whilst other types of medical imaging without radiation exposure (e.g. magnetic resonance imaging) are not much explored in the literature. Also, socioeconomic and other aspects that could influence in bone age were not addressed in the literature. Finally, studies that make use of more than one region of interest for bone age assessment are scarce.

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

Radiologists are sometimes requested to determine a person's age based on skeletal radiographs. Critical reviews demonstrate that this cannot be done with sufficient accuracy with existing methods.

A multi-scale data fusion framework for bone age assessment with convolutional neural networks

Bone age assessment (BAA) has various clinical applications such as diagnosis of endocrine disorders and prediction of final adult height for adolescents. Recent studies indicate that deep learning techniques have great potential in developing automated BAA methods with significant advantages over the conventional methods based on handcrafted features. In this paper, we propose a multi-scale data fusion framework for bone age assessment with X-ray images based on non-subsampled contourlet transform (NSCT) and convolutional neural networks (CNNs). Unlike the existing CNN-based BAA methods that adopt the original spatial domain image as network input directly, we pre-extract a rich set of features for the input image by performing NSCT to obtain its multi-scale and multi-direction representations. This feature pre-extraction strategy could be beneficial to network training as the number of annotated examples in the problem of BAA is typically quite limited. The obtained NSCT coefficient maps at each scale are fed into a convolutional network individually and the information from different scales are then merged to achieve the final prediction. Specifically, two CNN models with different data fusion strategies are presented for BAA: a regression model with feature-level fusion and a classification model with decision-level fusion. Experiments on the public BAA dataset Digital Hand Atlas demonstrate that the proposed method can obtain promising results and outperform many state-of-the-art BAA methods. In particular, the proposed approaches exhibit obvious advantages over the corresponding spatial domain approaches (generally with an improvement of more than 0.1 years on the mean absolute error), showing great potential in the future study of this field.

Evaluation of a Computer-Aided Diagnosis System for Automated Bone Age Assessment in Comparison to the Greulich-Pyle Atlas Method: A Multireader Study

OBJECTIVE

The aim of this study was to investigate a novel version of a computer-aided diagnosis (CAD) system developed for automated bone age (BA) assessment in comparison to the Greulich and Pyle method, regarding its accuracy and the influence of carpal bones on BA assessment.

METHODS

Total BA, BA of the left distal radius, and BA of carpal bones in 305 patients were determined independently by 3 blinded radiologists and assessed by the CAD system. Pearson product-moment correlation, Bland-Altman plot, root-mean-square deviation, and further agreement analyses were computed.

RESULTS

Mean total BA and BA of the distal radius showed high correlation between both approaches (r = 0.985 and r = 0.963). There was significantly higher correlation between values of total BA and BA of the distal radius (r = 0.969) compared with values of total BA and BA of carpal bones (r = 0.923). The assessment of carpal bones showed significantly lower interreader agreement compared with measurements of the distal radius (κ = 0.79 vs κ = 0.98).

CONCLUSION

A novel version of a CAD system enables highly accurate automated BA assessment. The assessment of carpal bones revealed lower precision and interreader agreement. Therefore, methods determining BA without analyzing carpal bones may be more precise and accurate.

MABAL: a Novel Deep-Learning Architecture for Machine-Assisted Bone Age Labeling

Bone age assessment (BAA) is a commonly performed diagnostic study in pediatric radiology to assess skeletal maturity. The most commonly utilized method for assessment of BAA is the Greulich and Pyle method (Pediatr Radiol 46.9:1269-1274, 2016; Arch Dis Child 81.2:172-173, 1999) atlas. The evaluation of BAA can be a tedious and time-consuming process for the radiologist. As such, several computer-assisted detection/diagnosis (CAD) methods have been proposed for automation of BAA. Classical CAD tools have traditionally relied on hard-coded algorithmic features for BAA which suffer from a variety of drawbacks. Recently, the advent and proliferation of convolutional neural networks (CNNs) has shown promise in a variety of medical imaging applications. There have been at least two published applications of using deep learning for evaluation of bone age (Med Image Anal 36:41-51, 2017; JDI 1-5, 2017). However, current implementations are limited by a combination of both architecture design and relatively small datasets. The purpose of this study is to demonstrate the benefits of a customized neural network algorithm carefully calibrated to the evaluation of bone age utilizing a relatively large institutional dataset. In doing so, this study will aim to show that advanced architectures can be successfully trained from scratch in the medical imaging domain and can generate results that outperform any existing proposed algorithm. The training data consisted of 10,289 images of different skeletal age examinations, 8909 from the hospital Picture Archiving and Communication System at our institution and 1383 from the public Digital Hand Atlas Database. The data was separated into four cohorts, one each for male and female children above the age of 8, and one each for male and female children below the age of 10. The testing set consisted of 20 radiographs of each 1-year-age cohort from 0 to 1 years to 14-15+ years, half male and half female. The testing set included left-hand radiographs done for bone age assessment, trauma evaluation without significant findings, and skeletal surveys. A 14 hidden layer-customized neural network was designed for this study. The network included several state of the art techniques including residual-style connections, inception layers, and spatial transformer layers. Data augmentation was applied to the network inputs to prevent overfitting. A linear regression output was utilized. Mean square error was used as the network loss function and mean absolute error (MAE) was utilized as the primary performance metric. MAE accuracies on the validation and test sets for young females were 0.654 and 0.561 respectively. For older females, validation and test accuracies were 0.662 and 0.497 respectively. For young males, validation and test accuracies were 0.649 and 0.585 respectively. Finally, for older males, validation and test set accuracies were 0.581 and 0.501 respectively. The female cohorts were trained for 900 epochs each and the male cohorts were trained for 600 epochs. An eightfold cross-validation set was employed for hyperparameter tuning. Test error was obtained after training on a full data set with the selected hyperparameters. Using our proposed customized neural network architecture on our large available data, we achieved an aggregate validation and test set mean absolute errors of 0.637 and 0.536 respectively. To date, this is the best published performance on utilizing deep learning for bone age assessment. Our results support our initial hypothesis that customized, purpose-built neural networks provide improved performance over networks derived from pre-trained imaging data sets. We build on that initial work by showing that the addition of state-of-the-art techniques such as residual connections and inception architecture further improves prediction accuracy. This is important because the current assumption for use of residual and/or inception architectures is that a large pre-trained network is required for successful implementation given the relatively small datasets in medical imaging. Instead we show that a small, customized architecture incorporating advanced CNN strategies can indeed be trained from scratch, yielding significant improvements in algorithm accuracy. It should be noted that for all four cohorts, testing error outperformed validation error. One reason for this is that our ground truth for our test set was obtained by averaging two pediatric radiologist reads compared to our training data for which only a single read was used. This suggests that despite relatively noisy training data, the algorithm could successfully model the variation between observers and generate estimates that are close to the expected ground truth.

Quantification of osteoblastic activity in epiphyseal growth plates by quantitative bone SPECT/CT

OBJECTIVE

Quantifying the function of the epiphyseal plate is worthwhile for the management of children with growth disorders. The aim of this retrospective study was to quantify the osteoblastic activity at the epiphyseal plate using the quantitative bone SPECT/CT.

MATERIALS AND METHODS

We enrolled patients under the age of 20 years who received Tc-99m hydroxymethylene diphosphonate bone scintigraphy acquired by a quantitative SPECT/CT scanner. The images were reconstructed by ordered subset conjugate-gradient minimizer, and the uptake on the distal margin of the femur was quantified by peak standardized uptake value (SUVpeak). A public database of standard body height was used to calculate growth velocities (cm/year).

RESULTS

Fifteen patients (6.9-19.7 years, 9 female, 6 male) were enrolled and a total of 25 legs were analyzed. SUVpeak in the epiphyseal plate was 18.9 ± 2.4 (average ± standard deviation) in the subjects under 15 years and decreased gradually by aging. The SUVpeak correlated significantly with the age- and sex-matched growth velocity obtained from the database (R² = 0.83, p < 0.0001).

CONCLUSION

The SUV measured by quantitative bone SPECT/CT was increased at the epiphyseal plates of children under the age of 15 years in comparison with the older group, corresponding to higher osteoblastic activity. Moreover, this study suggested a correlation between growth velocity and the SUV. Although this is a small retrospective pilot study, the objective and quantitative values measured by the quantitative bone SPECT/CT has the potential to improve the management of children with growth disorder.

Joint cartilage thickness and automated determination of bone age and bone health in juvenile idiopathic arthritis

BACKGROUND

BoneXpert is an automated method to calculate bone maturation and bone health index (BHI) in children with juvenile idiopathic arthritis (JIA). Cartilage thickness can also be seen as an indicator for bone health and arthritis damage. The objective of this study was to evaluate the relation between cartilage thickness, bone maturation and bone health in patients with JIA.

METHODS

Patients with JIA diagnosed according ILAR criteria included in a previous ultrasonography (US) study were eligible if hand radiographs were taken at the same time as the US examination. Of the 95 patients 67 met the inclusion criteria.

RESULTS

Decreased cartilage thickness was seen in 27% of the examined joints. Decreased BHI was seen in half of the JIA patient, and delayed bone maturation was seen in 33% of patients. A combination of decreased BHI and bone age was seen in 1 out of 5 JIA patients. Decreased cartilage thickness in the knee, wrist and MCP joint was negatively correlated with delayed bone maturation but not with bone health index.

CONCLUSION

Delayed bone maturation and decreased BHI were not related to a thinner cartilage, but a thicker cartilage. No relation with JADAS 10 was found. The rheumatologist should remain aware of delayed bone maturation and BHI in JIA patients with cartilage changes, even in the biologic era.

Determinants of Advanced Bone Age in Childhood Obesity

BACKGROUND

Childhood obesity is associated with advanced bone age (BA). Previous studies suggest that androgens, oestrogens, sex hormone-binding globulin, and insulin are responsible for this phenomenon, but results are contradictory and might be biased by confounders. We aim to elucidate this matter by applying a multivariate approach.

METHOD

We performed a correlation analysis of BA standard deviation score (SDS) with age- and sex-specific SDS for androgens, oestrogens, and with indicators of insulin secretion derived from oral glucose tolerance testing, in a group of obese children. A multivariate analysis was performed to investigate which parameters were independently predictive of BA SDS.

RESULTS

In this cohort (n = 101; mean age 10.9 years; mean BA 11.8 years; mean BMI SDS 3.3), BMI SDS was significantly correlated to BA SDS (r = 0.55, p < 0.001). In a regression analysis in the total cohort (B = 0.27, p < 0.001) as well as in females (B = 0.34, p = 0.042), males (B = 0.31, p = 0.006), and pubertal children (B = 0.32, p = 0.046), dehydroepiandrosterone sulphate (DHEAS) showed a positive, independent association with BA SDS. No association with indicators of insulin secretion was found.

CONCLUSION

BMI SDS is highly correlated to BA SDS in obese children. Increased DHEAS has a central role in advanced BA in obese children.
.

Automatic Determination of the Greulich-Pyle Bone Age as an Alternative Approach for Chinese Children with Discordant Bone Age

BACKGROUND

Automated bone age (BA) rating using BoneXpert is being adopted worldwide. This study investigated whether manual matching of hand radiographs could be replaced by BoneXpert for BA ratings of Chinese children with delayed or advanced BA.

METHODS

482 left-hand radiographs from 482 children (aged 2-16 years) with discordant BA were evaluated by BoneXpert and manually by 4 radiology residents using the Greulich and Pyle atlas. Radiographs whose BoneXpert BA deviated by >1 year from manual assessment were rerated by 2 attending radiologists in a blinded manner.

RESULTS

Among all 482 radiographs, 46 (9.5%) radiographs were rerated and no radiographs were rejected. Differences between BoneXpert and manual rating of 28 (5.8%) cases were >1 year. The manual BAs of the 28 radiographs were all >10 years and greater than the BoneXpert BAs. The root mean square deviation between the residents and BoneXpert was 0.56 for these children (95% CI 0.53-0.61).

CONCLUSION

BoneXpert agreed with manual BA rating in 94.2% of the images. Therefore, BoneXpert could be used as an alternative for the radiology residents to make an initial BA estimation. Modification of BoneXpert should provide greater accuracy for the estimation of BA in children aged >10 years with discordant BA.

Metacarpal bone loss in patients with rheumatoid arthritis estimated by a new Digital X-ray Radiogrammetry method - initial results

BACKGROUND

The Digital X-ray Radiogrammetry (DXR) method measures the cortical bone thickness in the shafts of the metacarpals and has demonstrated its relevance in the assessment of hand bone loss caused by rheumatoid arthritis (RA). The aim of this study was to validate a novel approach of the DXR method in comparison with the original version considering patients with RA.

METHOD

The study includes 49 patients with verified RA. The new version is an extension of the BoneXpert method commonly used in pediatrics which has these characteristics: (1) It introduces a new technique to analyze the images which automatically validates the results for most images, and (2) it defines the measurement region relative to the ends of the metacarpals. The BoneXpert method measures the Metacarpal Index (MCI) at the metacarpal bone (II to IV). Additionally, the MCI is quantified by the DXR X-posure System.

RESULTS

The new version correctly analyzed all 49 images, and 45 were automatically validated. The standard deviation between the MCI results of the two versions was 2.9% of the mean MCI. The average Larsen score was 2.6 with a standard deviation of 1.3. The correlation of MCI to Larsen score was -0.81 in both versions, and there was no significant difference in their ability to detect erosions.

CONCLUSION

The new DXR version (BoneXpert) validated 92% of the cases automatically, while the same good correlation to RA severity could be presented compared to the old version.

Psoriatic arthritis is associated with bone loss of the metacarpals

Background

BoneXpert (BX) is a newly developed medical device based on digital X-ray radiogrammetry to measure human cortical bone thickness. The aim of this study was to quantify cortical bone loss of the metacarpals in patients with psoriatic arthritis (PsA) and compare these findings with other radiological scoring methods.

Methods

The study includes 104 patients with verified PsA. The BX method was used to measure the Metacarpal Index (MCI) at the metacarpal bones (II–IV). Additionally, the T-score of the MCI (T-score_MCI) was calculated. Radiographic severity was determined by the Psoriatic Arthritis Ratingen Score (Proliferation Score and Destruction Score) as published by Wassenberg et al. and the Psoriatic Arthritis modified van der Heijde Sharp Score (Joint Space Narrowing Score and Erosion Score).

Results

For the total PsA study cohort, the T-score_MCI was significantly reduced by −1.289 ± 1.313 SD. The MCI negatively correlated with the Proliferation Score (r = −0.732; p < 0.001) and the Destruction Score (r = −0.771; p < 0.001) of the Psoriatic Arthritis Ratingen Score. Lower coefficients of correlations were observed for the Psoriatic Arthritis modified van der Heijde Sharp Score. In this context, a severity-dependent and PsA-related periarticular demineralisation as measured by the MCI was quantified. The strongest reduction of −30.8 % (p < 0.01) was observed for the MCI in the Destruction Score.

Conclusions

The BX MCI score showed periarticular demineralisation and severity-dependent bone loss in patients with PsA. The measurements of the BX technique were able to sensitively differentiate between the different stages of disease manifestation affecting bone integrity and thereby seem to achieve the potential to be a surrogate marker of radiographic progression in PsA.

Automated determination of bone age from hand X-rays at the end of puberty and its applicability for age estimation

The BoneXpert method for automated determination of bone age from hand X-rays was introduced in 2009, covering the Greulich-Pyle bone age ranges up to 17 years for boys and 15 years for girls. This paper presents an extension of the method up to bone age 19 years for boys and 18 years for girls. The extension was developed based on images from the First Zurich Longitudinal Study of 231 healthy children born in 1954-1956 and followed with annual X-rays of both hands until adulthood. The method was validated on two cross-sectional studies of healthy children from Rotterdam and Los Angeles. We found root mean square deviations from manual rating of 0.69 and 0.45 years in these two studies for boys in the bone age range 17-19 years. For girls, the deviations were 0.75 and 0.59 years, respectively, in the bone age range 15-18 years. It is shown how the automated bone age method can be applied to infer the age probability distribution for healthy Caucasian European males. Considering a population with age 15.0-21.0 years, the method can be used to decide whether the subject is above 18 years with a false positive rate (children classified as adults) of 10 % (95% confidence interval = 7-13%) and a false negative rate of 30 % (adults classified as children). To apply this method in other ethnicities will require a study of the average of "bone age - age" at the end of puberty, i.e. how much this population is shifted relative to the Greulich-Pyle standard.