Automated bone age assessment in rare pediatric growth disorders: a comparative study using Deeplasia.

ObjectivesThis study aimed to evaluate the performance of artificial intelligence (AI) software in bone age (BA) assessment, according to the Greulich and Pyle (G&P) method in a German pediatric cohort.Materials and methodsHand radiographs of 306 pediatric patients aged 1–18 years (153 boys, 153 girls, 18 patients per year of life)—including a subgroup of patients in the age group for which the software is declared (243 patients)—were analyzed retrospectively. Two pediatric radiologists and one endocrinologist made independent blinded BA reads. Subsequently, AI software estimated BA from the same images. Both agreements, accuracy, and interchangeability between AI and expert readers were assessed.ResultsThe mean difference between the average of three expert readers and AI software was 0.39 months with a mean absolute difference (MAD) of 6.8 months (1.73 months for the mean difference and 6.0 months for MAD in the intended use subgroup). Performance in boys was slightly worse than in girls (MAD 6.3 months vs. 5.6 months). Regression analyses showed constant bias (slope of 1.01 with a 95% CI 0.99–1.02). The estimated equivalence index for interchangeability was − 14.3 (95% CI −27.6 to − 1.1).ConclusionIn terms of BA assessment, the new AI software was interchangeable with expert readers using the G&P method.Clinical relevance statementThe use of AI software enables every physician to provide expert reader quality in bone age assessment.Key Points• A novel artificial intelligence–based software for bone age estimation has not yet been clinically validated.• Artificial intelligence showed a good agreement and high accuracy with expert radiologists performing bone age assessment.• Artificial intelligence showed to be interchangeable with expert readers.

Bone age assessment is challenging in clinical practice due to the complicated bone age assessment process. Current automatic bone age assessment methods were designed with rare consideration of the diagnostic logistics and thus may yield certain uninterpretable hidden states and outputs. Consequently, doctors can find it hard to cooperate with such models harmoniously because it is difficult to check the correctness of the model predictions. In this work, we propose a new graph-based deep learning framework for bone age assessment with hand radiographs, called Doctor Imitator (DI). The architecture of DI is designed to learn the diagnostic logistics of doctors using the scoring methods (e.g., the Tanner-Whitehouse method) for bone age assessment. Specifically, the convolutions of DI capture the local features of the anatomical regions of interest (ROIs) on hand radiographs and predict the ROI scores by our proposed Anatomy-based Group Convolution, summing up for bone age prediction. Besides, we develop a novel Dual Graph-based Attention module to compute patient-specific attention for ROI features and context attention for ROI scores. As far as we know, DI is the first automatic bone age assessment framework following the scoring methods without fully supervised hand radiographs. Experiments on hand radiographs with only bone age supervision verify that DI can achieve excellent performance with sparse parameters and provide more interpretability.

The Greulich and Pyle (GP) method is the most commonly used manual bone age assessment method but it is associated with interrater variability. The BoneXpert method is fully automated, eliminates interrater variability and has been validated for use in various populations. To compare the manual GP method with the automated BoneXpert method in performing bone age assessment of children with various paediatric endocrinology diagnoses. Three manual readers performed manual bone age assessment, and BoneXpert software performed automated bone age assessment on 260 left hand-wrist radiographs. Images where the average of three manual readers (Manual BA) deviated from BoneXpert BA by > 1.5 years, were re-read by an external reader, producing a Reference BA. Manual BA was compared to Carpal BA that was produced by the software. A composite bone age (Comp BA) for the software was defined to estimate the weighting on carpal and tubular bones to achieve the best agreement with Manual BA. The interclass correlation (ICC) between each manual reader was > 0.9, indicating a high positive correlation. The ICC between Manual BA and BoneXpert BA was 0.982. The Comp BA for BoneXpert that would achieve the best fit with Manual BA, places a 50% weighting on Carpal BA and 50% weighting on Tubular BA. The BoneXpert method is efficient, well-validated and shows a positive correlation with the manual GP method. An estimated weightage of 50% to carpal bones and 50% to tubular bones resulted in an automated Comp BA with the best agreement with Manual BA. This original research article compares manual and automated bone age assessment methods to evaluate the use of artificial intelligence tools in the South African context.

This study aimed to evaluate the clinical accuracy of automated BoneXpert (BX) vs. clinician-based Greulich-Pyle (GP) bone age (BA) assessments by comparing their respective predicted adult heights (PAH) with near-final height (NFH) in patients with congenital adrenal hyperplasia (CAH). Forty-seven patients with classic salt-wasting CAH diagnosed in the neonatal period who had reached NFH were included. Left hand-wrist radiographs obtained during the prepubertal period (6-9 years) were evaluated manually by two clinicians using the GP atlas and by the BX-GP method. PAH was calculated for both sexes using the Bayley-Pinneau (BP) method based on clinician- and BX-derived BA. PAH standard deviation scores (SDS) were compared with NFH-SDS and target height (TH)-SDS. Agreement was assessed using Bland-Altman analysis. Thirty patients (63.8 %) were female. Mean ages at bone age assessment and NFH were 7.3 and 16.1 years, respectively. Mean prepubertal height-SDS was 0.0 in girls and-0.25 in boys, while NFH-SDS was-0.79 and-1.14, respectively. Mean bone age according to clinician-GP was 7.80 years in girls and 8.16 in boys, and 7.69 and 8.14 years according to BX-GP. Clinician-based PAH-SDS was-1.0 in girls and-1.18 in boys, whereas BX-based PAH-SDS was-0.86 and-1.17, respectively. BX-based PAH was closer to NFH in girls (p<0.001), with no significant difference in boys. In both sexes, PAH-SDS and NFH-SDS were significantly lower than TH-SDS (p<0.001). PAH calculations using the BP method based on BX-derived GP bone age readings more accurately predicted NFH in patients with CAH.

Bone age assessment is of great significance to genetic diagnosis and endocrine diseases. Traditional bone age diagnosis mainly relies on experienced radiologists to examine the regions of interest in hand radiography, but it is time-consuming and may even lead to a vast error between the diagnosis result and the reference. The existing computer-aided methods predict bone age based on general regions of interest but do not explore specific regions of interest in hand radiography. This paper aims to solve such problems by performing bone age prediction on the articular surface and epiphysis from hand radiography using deep convolutional neural networks. The articular surface and epiphysis datasets are established from the Radiological Society of North America (RSNA) pediatric bone age challenge, where the specific feature regions of the articular surface and epiphysis are manually segmented from hand radiography. Five convolutional neural networks, i.e., ResNet50, SENet, DenseNet-121, EfficientNet-b4, and CSPNet, are employed to improve the accuracy and efficiency of bone age diagnosis in clinical applications. Experiments show that the best-performing model can yield a mean absolute error (MAE) of 7.34 months on the proposed articular surface and epiphysis datasets, which is more accurate and fast than the radiologists. The project is available at https://github.com/YameiDeng/BAANet/, and the annotated dataset is also published at https://doi.org/10.5281/zenodo.7947923.

Bone age assessment (BAA) is a technique for assessing the maturity of individual skeletal development, and it is the most accurate and objective method for assessing the deviation of individual development in clinical practice. It is used in the diagnosis of pediatric endocrine diseases, age determination of suspects in juvenile delinquency cases, height prediction, and athlete selection. Early computer-aided BAA mainly segments the skeleton of the hand and gives a final bone age by comparing the morphological descriptions of bones to standard atlas. In recent years, deep learning methods have developed rapidly, and a large number of end-to-end BAA methods based on deep learning have emerged, which have brought new development to the automatic BAA technology. This paper summarizes the technical basis, research status of automatic BAA. Firstly, the basic theory of medical BAA is introduced, then the commonly used traditional segmentation methods in BAA are analyzed. After that, we summarized the most popular methods of BAA based on deep learning, including the network model, data set and the assessment results. This survey also draws attention to a number of research challenges in the fully automatic BAA with deep learning.

Bone age assessment is essential for evaluating growth and pubertal disorders, but manual methods such as the Greulich-Pyle atlasare subject to inter-observer variability. Automated tools like BoneXpert may improve accuracy and consistency. To validate the accuracy and reliability of BoneXpert, an automated bone age assessment tool, compared to traditional manual methods performed by paediatric endocrinologists and radiologists in a multiethnic paediatric cohort in Singapore. This retrospective cohort study was conducted atKK Women's and Children's Hospitaland included paediatric patients aged 0years to 17years who presented to the endocrine clinic between February 2012 and September 2021. Bone age was assessed independently using the Greulich and Pyle (GP) method by radiologists and paediatric endocrinologists and compared with BoneXpert's automated assessments. The study included 200 paediatric patients with a mean age of 9.4years (± 3.5years). BoneXpert demonstrated excellent agreement with endocrinologists, with intraclass correlation coefficients (ICC) of 0.983 (95% CI: 0.977-0.987) and 0.974 (95% CI: 0.967-0.980) for Endocrinologists 1 and 2, respectively. The root mean square error (RMSE) between BoneXpert and the endocrinologists was 0.652years and 0.852years, indicating high accuracy. However, the RMSE between BoneXpert and radiologists was higher at 1.178years, reflecting greater variability. Bland-Altman plots showed good agreement between BoneXpert and manual assessments. BoneXpert provides a reliable and efficient alternative to manual bone age assessments and aligns closely with endocrinologists' evaluations. This tool could significantly reduce inter-rater variability and enhance clinical efficiency, particularly in diverse ethnic populations.

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

Bone age is an indicator of bone maturity and is useful for the treatment of different pediatric conditions as well as for legal issues. Bone age can be assessed by the analysis of different skeletal segments and teeth and through several methods; however, traditional bone age assessment is a complicated and time-consuming process, prone to inter- and intra-observer variability. There is a high demand for fully automated systems, but creating an accurate and reliable solution has proven difficult. Deep learning technology, machine learning, and Convolutional Neural Networks-based systems, which are rapidly evolving, have shown promising results in automated bone age assessment. We provide the background of bone age estimation, its usefulness and traditional methods of assessment, and review the currently artificial-intelligence-based solutions for bone age assessment and the future perspectives of these applications.

Radiographic bone age assessment (BAA) is used in the evaluation of pediatric endocrine and metabolic disorders. We previously developed an automated artificial intelligence (AI) deep learning algorithm to perform BAA using convolutional neural networks. We compared the BAA performance of a cohort of pediatric radiologists with and without AI assistance. Six board-certified, subspecialty trained pediatric radiologists interpreted 280 age- and gender-matched bone age radiographs ranging from 5 to 18years. Three of those radiologists then performed BAA with AI assistance. Bone age accuracy and root mean squared error (RMSE) were used as measures of accuracy. Intraclass correlation coefficient evaluated inter-rater variation. AI BAA accuracy was 68.2% overall and 98.6% within 1year, and the mean six-reader cohort accuracy was 63.6 and 97.4% within 1year. AI RMSE was 0.601years, while mean single-reader RMSE was 0.661years. Pooled RMSE decreased from 0.661 to 0.508years, all individually decreasing with AI assistance. ICC without AI was 0.9914 and with AI was 0.9951. AI improves radiologist's bone age assessment by increasing accuracy and decreasing variability and RMSE. The utilization of AI by radiologists improves performance compared to AI alone, a radiologist alone, or a pooled cohort of experts. This suggests that AI may optimally be utilized as an adjunct to radiologist interpretation of imaging studies to improve performance.

DNA methylation markers in combination with skeletal and dental ages to improve age estimation in children

Taking Matters into Your Own Hands.

This audit analysed the Tanner and Whitehouse II twenty bone (TW2) method of bone age assessment which was used in our department, and compared it with the Greulich and Pyle (GP) method. 50 previous bone ages were independently re-calculated by each of three registrars using both techniques, with the time taken to perform each assessment being recorded. For each method the interobserver variation was analysed in terms of the spread of results. The intraobserver variation in TW2 was determined by comparing the bone age originally reported with that subsequently calculated on the same film by the same registrar. The average spread of results was 0.74 years for TW2 method, and 0.96 years for the GP method and this difference is not statistically significant at the 5% level. The average intraobserver variation to TW2 was 0.33 years, but with 95% confidence limits of -0.87 to +1.53 years. The average time taken was 7.9 min for TW2 and 1.4 min for GP assessments. It was concluded that the GP method gave similar reproducibility and was faster than the TW2 method. Following clinical discussion the routine departmental bone age assessment method was changed from the TW2 to the GP method.

Bone age assessment (BAA) is crucial for the diagnosis of growth disorders and the optimization of treatments. However, the random error caused by different observers' experiences and the low consistency of repeated assessments harms the quality of such assessments. Thus, automated assessment methods are needed. Previous research has sought to design localization modules in a strongly or weakly supervised fashion to aggregate part regions to better recognize subtle differences. Conversely, we sought to efficiently deliver information between multi-granularity regions for fine-grained feature learning and to directly model long-distance relationships for global understanding. The proposed method has been named the "Multi-Granularity and Multi-Attention Net (2M-Net)". Specifically, we first applied the jigsaw method to generate related tasks emphasizing regions with different granularities, and we then trained the model on these tasks using a hierarchical sharing mechanism. In effect, the training signals from the extra tasks created as an inductive bias, enabling 2M-Net to discover task relatedness without the need for annotations. Next, the self-attention mechanism acted as a plug-and-play module to effectively enhance the feature representation capabilities. Finally, multi-scale features were applied for prediction. A public data set of 14,236 hand radiographs, provided by the Radiological Society of North America (RSNA), was used to develop and validate 2M-Net. In the public benchmark testing, the mean absolute error (MAE) between the bone age estimates of the model and of the reviewer was 3.98 months (3.89 months for males and 4.07 months for females). By using the jigsaw method to construct a multi-task learning strategy and inserting the self-attention module for efficient global modeling, we established 2M-Net, which is comparable to the previous best method in terms of performance.

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.