Artificial Intelligence (AI)-Based Systems for Automatic Skeletal Maturity Assessment through Bone and Teeth Analysis: A Revolution in the Radiological Workflow?

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 (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 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.

Taking Matters into Your Own Hands.

Bone age (BA) assessment is essential for monitoring growth and maturation and guiding therapeutic interventions. While deep learning (DL) models offer high-speed automated BA prediction, their generalizability to rare pathological and diagnostically complex populations remains a significant concern. This study aims to validate the open-source DL system Deeplasia on external data from pediatric patients with various syndromic, endocrine, and lysosomal storage disorders (LSDs) and to compare its accuracy and consistency against multiple expert human raters. We retrospectively assembled 1,138 hand radiographs from multiple centers, including patients with SHOX deficiency; Noonan syndrome; Silver-Russell syndrome; Ullrich-Turner syndrome; pseudohypoparathyroidism; congenital adrenal hyperplasia (CAH); precocious puberty and precocious pseudopuberty (cohort 1); mucopolysaccharidosis types I, II, III, IV, and VI; alpha-mannosidosis; and unclassified LSDs (cohort 2). For each radiograph, BA was evaluated using the Greulich and Pyle method by two to five human experts to obtain a mean BA reference. Model performance was assessed using the mean absolute error (MAE), root mean squared error (RMSE), and 1-year accuracy for each cohort and underlying conditions, sex, and age groups. Furthermore, Deeplasia's performance was compared with that of individual raters by testing each rater and the model against the remaining experts. Deeplasia achieved a mean MAE of 5.95 months, an RMSE of 8.01 months, and a 1-year accuracy of 89.9% for cohort 1 (endocrine and syndromic conditions). For cohort 2 (lysosomal storage disorders), Deeplasia achieved a mean MAE of 7.13 months, an RMSE of 9.56 months, and a 1-year accuracy of 81.2%. In direct comparisons between Deeplasia and individual raters tested against the remaining experts, Deeplasia outperformed all human raters. Deeplasia was validated as a highly consistent, robust, and reliable tool for BA assessment in complex cases. It demonstrated superior accuracy compared with individual human raters and may assist clinicians in BA evaluation.

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 (BAA) evaluates individual skeletal maturity by comparing the characteristics of skeletal development to the standard in a specific population. The X-ray image examination for bone age is tedious and subjective, and it requires high professional skills. Therefore, AI techniques are desired to innovate and improve BAA methods. Most of the BAA method use the whole X-ray image in an end-to-end model directly. Such whole-image-based approaches fail to characterize local changes and provide limited aid for diagnosis and understanding disease progress. To address these issues, we collected and curated a dataset of 2129 cases for the study of BAA with fine-grained skeletal maturity level labels of the 13 ROIs in hand bone based on the expert knowledge from TW method. We designed a four-stage automatic BAA model based on recursive feature pyramid network. Firstly, the palm region was segmented using U-Net, followed by the extraction of multi-target ROIs of hand bone using a recursive feature pyramid network. Given the extracted ROIs, we employed a transfer learning model with attention mechanism to predict the skeletal maturity level of each ROI. Finally, the bone age is assessed based on the percentile curve of bone maturity. The proposed BAA model can automate the BAA. In addition, it provides the detection result of the 13 ROIs and their ROI-level skeletal maturity. The MAE can reach 0.61 years on the dataset with the labeling precision of one year. All the data and annotations used in this paper are released publicly.

Background: In managing pediatric knee conditions, an accurate bone age assessment is often critical for diagnostic, prognostic, and treatment purposes. Historically, the Greulich and Pyle atlas (hand atlas) has been the gold standard bone age assessment tool. In 2013, a shorthand bone age assessment tool based on this atlas (hand shorthand) was devised as a simpler and more efficient alternative. Recently, a knee magnetic resonance imaging (MRI) bone age atlas (MRI atlas) was created to circumvent the need for a left-hand radiograph. Purpose: To create a shorthand version of the knee MRI atlas. Study Design: Cohort study (diagnosis); Level of evidence, 2. Methods: A shorthand bone age assessment method was created utilizing the previously published MRI atlas, which utilizes several criteria that are visualized across a series of images. The MRI shorthand draws on characteristic criteria for each age that are best observed on a single MRI scan. For validation, we performed a retrospective assessment of skeletally immature patients. One reader performed the bone age assessment using the MRI atlas and the MRI shorthand on 200 patients. Then, 4 readers performed the bone age assessment with the hand atlas, hand shorthand, MRI atlas, and MRI shorthand on a subset of 22 patients in a blinded fashion. All 22 patients had a knee MRI scan and a left-hand radiograph within 4 weeks of each other. Interobserver and intraobserver reliability, as well as variability among observers, were evaluated. Results: A total of 200 patients with a mean age of 13.5 years (range, 9.08-17.98 years) were included in this study. Also, 22 patients with a mean age of 13.3 years (range, 9.0-15.6 years) had a knee MRI scan and a left-hand radiograph within 4 weeks. The intraobserver and interobserver reliability of all 4 assessment tools were acceptable (intraclass correlation coefficient [ICC] ≥ 0.8; P < .001). When comparing the MRI shorthand with the MRI atlas, there was excellent agreement (ICC = 0.989), whereas the hand shorthand compared with the hand atlas had good agreement (ICC = 0.765). The MRI shorthand also had perfect agreement in 50% of readings among all 4 readers, and 95% of readings had agreement within 1 year, whereas the hand shorthand had perfect agreement in 32% of readings and 77% agreement within 1 year. Conclusion: The MRI shorthand is a simple and efficient means of assessing the skeletal maturity of adolescent patients with a knee MRI scan. This bone age assessment technique had interobserver and intraobserver reliability equivalent to or better than the standard method of utilizing a left-hand radiograph.

Bone age estimation is very useful in children undergoing epiphysiodesis or guided growth surgery especially during the years of accelerated growth. It may be noted that no data are available on bone age estimation for Indian children of this age group. Sauvegrain (French) method is a very useful and simple method for bone age assessment during the years of accelerated growth. We decided to check the usefulness and the accuracy of the Sauvegrain method in Indian children. A team of two pediatric orthopaedic surgeons and a radiologist scored elbow X-rays of 80 healthy children (40 boys and 40 girls), using the Sauvegrain method twice. Interobserver reliability and intraobserver reproducibility of the Sauvegrain scoring were assessed. There was a very strong correlation between all observers in both rounds (r = > 0.8) and an excellent reproducibility by the same observer in both rounds (r = 0.955). Chronological and bone age are considered the same if the difference between them is less than 6 months. With this criterion bone and chronological ages matched in >37% of boys and girls, similar to the study done in French children. In the nonmatching group, more children had delayed bone age compared to their chronological age. The Sauvegrain method of bone age assessment described for French children was found to be useful in estimating bone age in Indian children. It is especially helpful in the clinical practice for detecting mismatch between the chronological and the radiological age before undertaking guided growth or epiphysiodesis.

Bone age assessment based on hand X‐ray imaging is important in pediatry medicine. At present, prediction of bone age is mainly performed by the manual comparison with the existing atlas. To develop an automatic regression framework based on deep learning with high performance and efficiency. A landmark‐based multi‐region convolutional neural networks for automatic bone age assessment based on left hand X‐ray images was proposed. The deep alignment network localized multiple landmarks distributed over the hand, and cropped the local regions to establish the multi‐region ensemble convolutional neural networks with different sub‐network combinations. The modified loss function and the optimized bone sub‐regions were applied to train the networks. The experiments on Digital Hand Atlas Database revealed that the mean absolute error of bone age assessment was 0.52 ± 0.25 years. It is the first study to predict bone age using deep learning methods throughout the entire process including image preprocessing, landmark localization and bone age predication. The proposed method outperformed most of the existing state‐of‐the‐art deep learning methods and achieved good results compared with the expert's experience. It can improve the efficiency of the medical doctors while minimizing the subjective errors.

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.

The aim of the study was to validate dual-energy X-ray absorptiometry (DXA) as a method to assess bone age in children. Paired dual-energy X-ray absorptiometry (DXA) scans and X-rays of the left hand were performed in 95 children who attended the paediatric endocrinology outpatient clinic of University Hospital Rotterdam, the Netherlands. We compared bone age assessments by DXA scan with those performed by X-ray. Bone age assessment was performed by two blinded observers according to the reference method of Greulich and Pyle. Intra-observer and interobserver reproducibility were investigated using the intraclass correlation coefficient (ICC), and agreement was tested using Bland and Altman plots. The intra-observer ICCs for both observers were 0.997 and 0.991 for X-ray and 0.993 and 0.987 for DXA assessments. The interobserver ICC was 0.993 and 0.991 for X-ray and DXA assessments, respectively. The mean difference between bone age assessed by X-ray and DXA was 0.11 years. The limits of agreement ranged from -0.82 to 1.05 years, which means that 95% of all differences between the methods were covered by this range. Results of bone age assessment by DXA scan are similar to those obtained by X-ray. The DXA method seems to be an alternative for assessing bone age in a paediatric hospital-based population.

BackgroundThe applicability and accuracy of artificial intelligence (AI)-assisted bone age assessment and adult height prediction methods in girls with early puberty are unknown.ObjectiveTo analyze the performance of AI-assisted bone age assessment methods by comparing the corresponding methods for predicted adult height with actual adult height.Materials and methodsThis retrospective review included 726 girls with early puberty, 87 of whom had reached adult height at last follow-up. Bone age was evaluated using the Greulich–Pyle (GP), Tanner–Whitehouse (TW3–RUS) and China 05 RUS–CHN (RUS-CHN) methods. Predicted adult height was calculated using the China 05 (CH05), TW3 and Bayley–Pinneau (BP) methods.ResultsWe analyzed 1,663 left-hand radiographs, including 155 from girls who had reached adult height. In the 6–8- and 9–11-years age groups, bone age differences were smaller than those in the 12–14-years group; however, the differences between predicted adult height and actual adult height were larger than those in the 12–14-years group. TW3 overestimated adult height by 0.4±2.8 cm, while CH05 and BP significantly underestimated adult height by 2.9±3.6 cm and 1.3±3.8 cm, respectively. TW3 yielded the highest proportion of predicted adult height within ±5 cm of actual adult height (92.9%), with the highest correlation between predicted and actual adult heights.ConclusionThe differences in measured bone ages increased with increasing bone age. However, the corresponding method for predicting adult height was more accurate when the bone age was older. TW3 might be more suitable than CH05 and BP for predicting adult height in girls with early puberty. Methods for predicting adult height should be optimized for populations of the same ethnicity and disease.

IntroductionA deep learning-based automatic bone age identification system (ABAIs) was introduced in medical imaging. This ABAIs enhanced accurate, consistent, and timely clinical diagnostics and enlightened research fields of deep learning and artificial intelligence (AI) in medical imaging.AimThe goal of this study was to use the Deep Neural Network (DNN) model to assess bone age in months based on a database of pediatric left-hand radiographs.MethodsThe Inception Resnet V2 model with a Global Average Pooling layer to connect to a single fully connected layer with one neuron using the Rectified Linear Unit (ReLU) activation function consisted of the DNN model for bone age assessment (BAA) in this study. The medical data in each case contained posterior view of X-ray image of left hand, information of age, gender and weight, and clinical skeletal bone assessment.ResultsA database consisting of 8,061 hand radiographs with their gender and age (0–18 years) as the reference standard was used. The DNN model’s accuracies on the testing set were 77.4%, 95.3%, 99.1% and 99.7% within 0.5, 1, 1.5 and 2 years of the ground truth respectively. The MAE for the study subjects was 0.33 and 0.25 year for male and female models, respectively.ConclusionIn this study, Inception Resnet V2 model was used for automatic interpretation of bone age. The convolutional neural network based on feature extraction has good performance in the bone age regression model, and further improves the accuracy and efficiency of image-based bone age evaluation. This system helps to greatly reduce the burden on clinical personnel.