Diagnostic performance of convolutional neural network-based Tanner-Whitehouse 3 bone age assessment system

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.

Artificial intelligence model system for bone age assessment of preschool children

BACKGROUD

Our study aimed to assess the impact of inter- and intra-observer variations when utilizing an artificial intelligence (AI) system for bone age assessment (BAA) of preschool children.

METHODS

A retrospective study was conducted involving a total sample of 53 female individuals and 41 male individuals aged 3-6 years in China. Radiographs were assessed by four mid-level radiology reviewers using the TW3 and RUS-CHN methods. Bone age (BA) was analyzed in two separate situations, with/without the assistance of AI. Following a 4-week wash-out period, radiographs were reevaluated in the same manner. Accuracy metrics, the correlation coefficient (ICC)and Bland-Altman plots were employed.

RESULTS

The accuracy of BAA by the reviewers was significantly improved with AI. The results of RMSE and MAE decreased in both methods (p < 0.001). When comparing inter-observer agreement in both methods and intra-observer reproducibility in two interpretations, the ICC results were improved with AI. The ICC values increased in both two interpretations for both methods and exceeded 0.99 with AI.

CONCLUSION

In the assessment of BA for preschool children, AI was found to be capable of reducing inter-observer variability and enhancing intra-observer reproducibility, which can be considered an important tool for clinical work by radiologists.

IMPACT

The RUS-CHN method is a special bone age method devised to be suitable for Chinese children. The preschool stage is a critical phase for children, marked by a high degree of variability that renders BA prediction challenging. The accuracy of BAA by the reviewers can be significantly improved with the aid of an AI model system. This study is the first to assess the impact of inter- and intra-observer variations when utilizing an AI model system for BAA of preschool children using both the TW3 and RUS-CHN methods.

Deep learning-based identification of spine growth potential on EOS radiographs

OBJECTIVES

To develop an automatic computer-based method that can help clinicians in assessing spine growth potential based on EOS radiographs.

METHODS

We developed a deep learning-based (DL) algorithm that can mimic the human judgment process to automatically determine spine growth potential and the Risser sign based on full-length spine EOS radiographs. A total of 3383 EOS cases were collected and used for the training and test of the algorithm. Subsequently, the completed DL algorithm underwent clinical validation on an additional 440 cases and was compared to the evaluations of four clinicians.

RESULTS

Regarding the Risser sign, the weighted kappa value of our DL algorithm was 0.933, while that of the four clinicians ranged from 0.909 to 0.930. In the assessment of spine growth potential, the kappa value of our DL algorithm was 0.944, while the kappa values of the four clinicians were 0.916, 0.934, 0.911, and 0.920, respectively. Furthermore, our DL algorithm obtained a slightly higher accuracy (0.973) and Youden index (0.952) compared to the best values achieved by the four clinicians. In addition, the speed of our DL algorithm was 15.2 ± 0.3 s/40 cases, much faster than the inference speeds of the clinicians, ranging from 177.2 ± 28.0 s/40 cases to 241.2 ± 64.1 s/40 cases.

CONCLUSIONS

Our algorithm demonstrated comparable or even better performance compared to clinicians in assessing spine growth potential. This stable, efficient, and convenient algorithm seems to be a promising approach to assist doctors in clinical practice and deserves further study.

CLINICAL RELEVANCE STATEMENT

This method has the ability to quickly ascertain the spine growth potential based on EOS radiographs, and it holds promise to provide assistance to busy doctors in certain clinical scenarios.

KEY POINTS

• In the clinic, there is no available computer-based method that can automatically assess spine growth potential. • We developed a deep learning-based method that could automatically ascertain spine growth potential. • Compared with the results of the clinicians, our algorithm got comparable results.

An artificial intelligence-based bone age assessment model for Han and Tibetan children

Background: Manual bone age assessment (BAA) is associated with longer interpretation time and higher cost and variability, thus posing challenges in areas with restricted medical facilities, such as the high-altitude Tibetan Plateau. The application of artificial intelligence (AI) for automating BAA could facilitate resolving this issue. This study aimed to develop an AI-based BAA model for Han and Tibetan children. Methods: A model named "EVG-BANet" was trained using three datasets, including the Radiology Society of North America (RSNA) dataset (training set n = 12611, validation set n = 1425, and test set n = 200), the Radiological Hand Pose Estimation (RHPE) dataset (training set n = 5491, validation set n = 713, and test set n = 79), and a self-established local dataset [training set n = 825 and test set n = 351 (Han n = 216 and Tibetan n = 135)]. An open-access state-of-the-art model BoNet was used for comparison. The accuracy and generalizability of the two models were evaluated using the abovementioned three test sets and an external test set (n = 256, all were Tibetan). Mean absolute difference (MAD) and accuracy within 1 year were used as indicators. Bias was evaluated by comparing the MAD between the demographic groups. Results: EVG-BANet outperformed BoNet in the MAD on the RHPE test set (0.52 vs. 0.63 years, p < 0.001), the local test set (0.47 vs. 0.62 years, p < 0.001), and the external test set (0.53 vs. 0.66 years, p < 0.001) and exhibited a comparable MAD on the RSNA test set (0.34 vs. 0.35 years, p = 0.934). EVG-BANet achieved accuracy within 1 year of 97.7% on the local test set (BoNet 90%, p < 0.001) and 89.5% on the external test set (BoNet 85.5%, p = 0.066). EVG-BANet showed no bias in the local test set but exhibited a bias related to chronological age in the external test set. Conclusion: EVG-BANet can accurately predict the bone age (BA) for both Han children and Tibetan children living in the Tibetan Plateau with limited healthcare facilities.

Enhancing skeletal age estimation accuracy using support vector regression models

OBJECTIVE

The objective of the study was to determine if support vector regression (SVR) models could enhance the accuracy of skeletal age estimation compared to original metrics.

METHOD

The study used a dataset of 5,018 individuals from Wuhan, spanning ages 1 to 17. Optimal model parameters were found using cross-validation and grid search techniques. The study compared SVR-based bone age assessment metrics with original metrics and evaluated the performance of the SVR model across different sample sizes.

RESULTS

The findings unequivocally demonstrated SVR's superior reliability over original metrics in assessing bone age among children in central China. Regardless of the training set size, constructing SVR models based on TW3, CHN05, or a combination of TW3, CHN05, and GP consistently results in top-tier predictive accuracy.

CONCLUSION

This research highlights SVR's potential for accuracy improvement and robustness with limited datasets.

Validation of an established TW3 artificial intelligence bone age assessment system: a prospective, multicenter, confirmatory study

Background

In 2020, our center established a Tanner-Whitehouse 3 (TW3) artificial intelligence (AI) system using a convolutional neural network (CNN), which was built upon 9059 radiographs. However, the system, upon which our study is based, lacked a gold standard for comparison and had not undergone thorough evaluation in different working environments.

Methods

To further verify the applicability of the AI system in clinical bone age assessment (BAA) and to enhance the accuracy and homogeneity of BAA, a prospective multi-center validation was conducted. This study utilized 744 left-hand radiographs of patients, ranging from 1 to 20 years of age, with 378 boys and 366 girls. These radiographs were obtained from nine different children's hospitals between August and December 2020. The BAAs were performed using the TW3 AI system and were also reviewed by experienced reviewers. Bone age accuracy within 1 year, root mean square error (RMSE), and mean absolute error (MAE) were statistically calculated to evaluate the accuracy. Kappa test and Bland-Altman (B-A) plot were conducted to measure the diagnostic consistency.

Results

The system exhibited a high level of performance, producing results that closely aligned with those of the reviewers. It achieved a RMSE of 0.52 years and an accuracy of 94.55% for the radius, ulna, and short bones series. When assessing the carpal series of bones, the system achieved a RMSE of 0.85 years and an accuracy of 80.38%. Overall, the system displayed satisfactory accuracy and RMSE, particularly in patients over 7 years old. The system excelled in evaluating the carpal bone age of patients aged 1-6. Both the Kappa test and B-A plot demonstrated substantial consistency between the system and the reviewers, although the model encountered challenges in consistently distinguishing specific bones, such as the capitate. Furthermore, the system's performance proved acceptable across different genders and age groups, as well as radiography instruments.

Conclusions

In this multi-center validation, the system showcased its potential to enhance the efficiency and consistency of healthy delivery, ultimately resulting in improved patient outcomes and reduced healthcare costs.

Region fine-grained attention network for accurate bone age assessment

Bone age assessment plays a vital role in monitoring the growth and development of adolescents. However, it is still challenging to obtain precise bone age from hand radiography due to these problems: 1) Hand bone varies greatly and is always masked by the background; 2) the hand bone radiographs with successive ages offer high similarity. To solve such issues, a region fine-grained attention network (RFGA-Net) was proposed for bone age assessment, where the region aware attention (RAA) module was developed to distinguish the skeletal regions from the background by modeling global spatial dependency; then the fine-grained feature attention (FFA) module was devised to identify similar bone radiographs by recognizing critical fine-grained feature regions. The experimental results demonstrate that the proposed RFGA-Net shows the best performance on the Radiological Society of North America (RSNA) pediatric bone dataset, achieving the mean absolute error (MAE) of 3.34 and the root mean square error (RMSE) of 4.02, respectively.

A real-time automated bone age assessment system based on the RUS-CHN method

Background

Bone age is the age of skeletal development and is a direct indicator of physical growth and development in children. Most bone age assessment (BAA) systems use direct regression with the entire hand bone map or first segmenting the region of interest (ROI) using the clinical a priori method and then deriving the bone age based on the characteristics of the ROI, which takes more time and requires more computation.

Materials and methods

Key bone grades and locations were determined using three real-time target detection models and Key Bone Search (KBS) post-processing using the RUS-CHN approach, and then the age of the bones was predicted using a Lightgbm regression model. Intersection over Union (IOU) was used to evaluate the precision of the key bone locations, while the mean absolute error (MAE), the root mean square error (RMSE), and the root mean squared percentage error (RMSPE) were used to evaluate the discrepancy between predicted and true bone age. The model was finally transformed into an Open Neural Network Exchange (ONNX) model and tested for inference speed on the GPU (RTX 3060).

Results

The three real-time models achieved good results with an average (IOU) of no less than 0.9 in all key bones. The most accurate outcomes for the inference results utilizing KBS were a MAE of 0.35 years, a RMSE of 0.46 years, and a RMSPE of 0.11. Using the GPU RTX3060 for inference, the critical bone level and position inference time was 26 ms. The bone age inference time was 2 ms.

Conclusions

We developed an automated end-to-end BAA system that is based on real-time target detection, obtaining key bone developmental grade and location in a single pass with the aid of KBS, and using Lightgbm to obtain bone age, capable of outputting results in real-time with good accuracy and stability, and able to be used without hand-shaped segmentation. The BAA system automatically implements the entire process of the RUS-CHN method and outputs information on the location and developmental grade of the 13 key bones of the RUS-CHN method along with the bone age to assist the physician in making judgments, making full use of clinical a priori knowledge.

Combined assisted bone age assessment and adult height prediction methods in Chinese girls with early puberty: analysis of three artificial intelligence systems

BACKGROUND

The applicability and accuracy of artificial intelligence (AI)-assisted bone age assessment and adult height prediction methods in girls with early puberty are unknown.

OBJECTIVE

To 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 METHODS

This 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.

RESULTS

We 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.

CONCLUSION

The 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.

Association between phthalate exposure and accelerated bone maturation in Chinese girls with early puberty onset: a propensity score-matched case-control analysis

Estrogen can promote the acceleration of bone maturation and phthalate esters (PAEs) have estrogen-mimicking effects. We investigated whether PAEs are associated with the acceleration of bone age (BA) in girls with early onset of puberty (EOP). This case–control study enrolled 254 girls with EOP from the Endocrinology Department at Shenzhen Children’s Hospital between December 2018 and August 2019. Ultra-performance liquid chromatography and tandem mass spectrometry were used to analyze the 10 metabolites of PAEs (mPAEs) in urine samples. BA was measured using an artificial intelligence system. BA exceeding the chronological age (CA) by > 2 years (BA-CA ≥ 2 years) was referred to as significant BA advancement. Participants were divided into groups A (BA-CA ≥ 2 years; case group) and B (BA-CA < 2 years; control group). Propensity score matching (PSM) was performed for both groups in a 1:2 ratio with a caliper of 0.25. To identify potential dose–response relationships between PAEs exposure and BA advancement, we grouped the participants after PSM according to the tertiles of the mPAE concentrations. After PSM, 31 and 62 girls in groups A and B were selected. The concentration of Mono-ethyl phthalate (MEP) in group A was significantly higher than in group B (11.83 μg/g vs. 7.11 μg/g, P < 0.05); there was no significant difference in the levels of other mPAEs between the groups. The degree of BA advancement and proportion of significantly advanced BA in the lowest, middle, and highest tertiles of the MEP sequentially increased, as well as in the lowest, middle, and highest tertiles of Mono-(2-ethyl-5-carboxypentyl) phthalate; however, these were only statistically different between the highest and lowest MEP tertiles (both P < 0.05). For the remaining mPAEs, differences in the degree of BA advancement among the lowest, middle, and highest tertiles, as well as differences in the proportion of significantly advanced BA among the lowest, middle, and highest tertiles, were not significant (all P > 0.05). Our findings suggested that MEP was positively associated with BA advancement in girls with EOP. Exposure to PAEs may promote accelerated bone maturation.

SMANet: multi-region ensemble of convolutional neural network model for skeletal maturity assessment

Background

Bone age assessment (BAA) is a crucial research topic in pediatric radiology. Interest in the development of automated methods for BAA is increasing. The current BAA algorithms based on deep learning have displayed the following deficiencies: (I) most methods involve end-to-end prediction, lacking integration with clinically interpretable methods; (II) BAA methods exhibit racial and geographical differences.

Methods

A novel, automatic skeletal maturity assessment (SMA) method with clinically interpretable methods was proposed based on a multi-region ensemble of convolutional neural networks (CNNs). This method predicted skeletal maturity scores and thus assessed bone age by utilizing left-hand radiographs and key regional patches of clinical concern.

Results

Experiments included 4,861 left-hand radiographs from the database of Beijing Jishuitan Hospital and revealed that the mean absolute error (MAE) was 31.4±0.19 points (skeletal maturity scores) and 0.45±0.13 years (bone age) for the carpal bones-series and 29.9±0.21 points and 0.43±0.17 years, respectively, for the radius, ulna, and short (RUS) bones series based on the Tanner-Whitehouse 3 (TW3) method.

Conclusions

The proposed automatic SMA method, which was without racial and geographical influence, is a novel, automatic method for assessing childhood bone development by utilizing skeletal maturity. Furthermore, it provides a comparable performance to endocrinologists, with greater stability and efficiency.

Construction of artificial intelligence system of carpal bone age for Chinese children based on China-05 standard

PURPOSE

The purpose of this study is to construct an automatic carpal bone age evaluation system for Chinese children based on TW3-C Carpal method by deep learning, and to evaluate the accuracies in test set and clinical test set.

METHODS

A total of 8184 radiographs of Chinese Han healthy children (2 ∼ 14 years old) were collected from the 2005 China Skeletal Development Survey data and from the accumulated radiographs in bone age researches over the years. Three experienced radiologists and the China-05 standard maker jointly evaluated each bone development stage, and the consensual stage was decided as the reference standard. According to each epiphysis development stage, 10 % of them were derived by stratified random sampling as test sets, and the remaining radiographs were used as training sets and validation sets. Furthermore, the overall performance of the model was estimated by comparing mean difference, 95 % limits of agreement, mean absolute difference (MAD) and root mean square (RMS) between model predictions and the reference standard.

RESULTS

The percentage agreement of ratings in each epiphysis in the test set ranged from 82.82 % to 90.06 %, with an average of 86.94 %. Compared with the reference standard, the automated bone age system has a mean difference of 0.01 years old, ± 0.45 years old in 95% confidence interval by single reading, a 85.93 % percentage agreement of ratings, a 90.5 % bone age accuracy rate, 0.20 years old of MAD, 0.32 years old of RMS in the clinical test set.

CONCLUSIONS

The automatic bone age system for Chinese children has a comparable accuracy and stable determination compared with experienced radiologists. This article is protected by copyright. All rights reserved.

A comparative study of three bone age assessment methods on Chinese preschool-aged children

BACKGROUND

Bone age assessment (BAA) is an essential tool utilized in outpatient pediatric clinics. Three major BAA methods, Greulich-Pyle (GP), Tanner-Whitehouse 3 (TW3), and China 05 RUS-CHN (RUS-CHN), were applied to comprehensively compare bone age (BA) and chronological age (CA) in a Chinese sample of preschool children. This study was designed to determine the most reliable method.

METHODS

The BAA sample consisted of 207 females and 183 males aged 3-6 years from the Zhejiang Province in China. The radiographs were estimated according to the GP, TW3, and RUS-CHN methods by two pediatric radiologists. The data was analyzed statistically using boxplots, the Wilcoxon rank test, and Student's t-test to explore the difference (D) between BA and CA.

RESULTS

According to the distributions of D, the boxplots showed that the median D of the TW3 method was close to zero for both male and female subjects. The TW3 and RUS-CHN methods overestimated the age of both genders. The TW3 method had the highest correct classification rate for males but a similar rate for females. The GP method did not show any significant difference between the BA and CA when applied to 3-year-old males and 4-year-old females while the TW3 method showed similar results when applied to 6-year-old females. The RUS-CHN method showed the least consistent results among the three methods.

CONCLUSION

The TW3 method was superior to the GP and RUS-CHN methods but not reliable on its own. It should be noted that a precise age diagnosis for preschool children cannot be easily made if only one of the methods is utilized. Therefore, it is advantageous to combine multiple methods when assessing bone age.

A Randomized Controlled Phase 3 Study on the Efficacy and Safety of Recombinant Human Growth Hormone in Children With Idiopathic Short Stature

BACKGROUND

To evaluate the safety and efficacy of daily somatropin (Jintropin^®), a recombinant human growth hormone, in prepubertal children with ISS in China.

METHODS

This study was a multicenter, randomized, controlled, open-label, phase 3 study. All subjects were randomized 3:1 to daily somatropin 0.05 mg/kg/day or no treatment for 52 weeks. A total of 481 subjects with a mean baseline age of 5.8 years were enrolled in the study. The primary endpoint was change in (△) height standard deviation score (HT-SDS) for chronological age (CA). Secondary endpoints included △height from baseline; △bone age (BA)/CA; △height velocity (HV) and △insulin-like growth factor 1 (IGF-1 SDS).

RESULTS

△HT-SDS at week 52 was 1.04 ± 0.31 in the treatment group and 0.20 ± 0.33 in the control group (P < 0.001). At week 52, statistical significance was observed in the treatment group compared with control for △height (10.19 ± 1.47 cm vs. 5.85 ± 1.80 cm; P < 0.001), △BA/CA (0.04 ± 0.09 vs. 0.004 ± 0.01; P < 0.001), △HV (5.17 ± 3.70 cm/year vs. 0.75 ± 4.34 cm/year; P < 0.001), and △IGF-1 SDS (2.31 ± 1.20 vs. 0.22 ± 0.98; P < 0.001). The frequencies of treatment-emergent adverse events (TEAEs) were similar for the treatment and the control groups (89.8% vs. 82.4%); most TEAEs were mild to moderate in severity and 23 AEs were considered study-drug related.

CONCLUSIONS

Daily subcutaneous administration of somatropin at 0.05 mg/kg/day for 52 weeks demonstrated improvement in growth outcomes and was well tolerated with a favorable safety profile.

TRIAL REGISTRATION

ClinicalTrials.gov (identifier: NCT03635580). URL: https://clinicaltrials.gov/ct2/show/NCT03635580.

Artificial Intelligence-Assisted Bone Age Assessment to Improve the Accuracy and Consistency of Physicians With Different Levels of Experience

BACKGROUND

The accuracy and consistency of bone age assessments (BAA) using standard methods can vary with physicians' level of experience.

METHODS

To assess the impact of information from an artificial intelligence (AI) deep learning convolutional neural network (CNN) model on BAA, specialists with different levels of experience (junior, mid-level, and senior) assessed radiographs from 316 children aged 4-18 years that had been randomly divided into two equal sets-group A and group B. Bone age (BA) was assessed independently by each specialist without additional information (group A) and with information from the model (group B). With the mean assessment of four experts as the reference standard, mean absolute error (MAE), and intraclass correlation coefficient (ICC) were calculated to evaluate accuracy and consistency. Individual assessments of 13 bones (radius, ulna, and short bones) were also compared between group A and group B with the rank-sum test.

RESULTS

The accuracies of senior, mid-level, and junior physicians were significantly better (all P < 0.001) with AI assistance (MAEs 0.325, 0.344, and 0.370, respectively) than without AI assistance (MAEs 0.403, 0.469, and 0.755, respectively). Moreover, for senior, mid-level, and junior physicians, consistency was significantly higher (all P < 0.001) with AI assistance (ICCs 0.996, 0.996, and 0.992, respectively) than without AI assistance (ICCs 0.987, 0.989, and 0.941, respectively). For all levels of experience, accuracy with AI assistance was significantly better than accuracy without AI assistance for assessments of the first and fifth proximal phalanges.

CONCLUSIONS

Information from an AI model improves both the accuracy and the consistency of bone age assessments for physicians of all levels of experience. The first and fifth proximal phalanges are difficult to assess, and they should be paid more attention.

An overview of deep learning applications in precocious puberty and thyroid dysfunction

In the last decade, deep learning methods have garnered a great deal of attention in endocrinology research. In this article, we provide a summary of current deep learning applications in endocrine disorders caused by either precocious onset of adult hormone or abnormal amount of hormone production. To give access to the broader audience, we start with a gentle introduction to deep learning and its most commonly used architectures, and then we focus on the research trends of deep learning applications in thyroid dysfunction classification and precocious puberty diagnosis. We highlight the strengths and weaknesses of various approaches and discuss potential solutions to different challenges. We also go through the practical considerations useful for choosing (and building) the deep learning model, as well as for understanding the thought process behind different decisions made by these models. Finally, we give concluding remarks and future directions.

Data governance system of the National Clinical Research Center for Child Health in China

BACKGROUND

Since the national big data strategy was unveiled at the fifth plenary session of the 18th CPC (Communist Party of China) Central Committee, the big data industry has been flourishing in China. Various successful industrial data governance systems have emerged with the rapid development of big data technologies and data management theories. City Brain and Enterprise Data Middle Platform are considered the best data governance systems in urban and corporate governance, respectively. However, in the health and medical sectors, issues of data operation occur frequently due to a lack of systematic data governance. These problems need to be urgently addressed, as health and medical data have been defined as national fundamental strategic resources. Clinical researchers have an increasing demand for data analysis.

METHODS

Therefore, the Medical Data Governance System (MDGS) has been designed to improve data quality and provide simple and convenient data analysis tools for the National Clinical Research Center for Child Health. The MDGS consists of the Medical Data Platform (MDP) and Operation Management System (OMS). The MDP comprises acquisition layer, middle platform, and application layer that persistently elevates data quality and significantly shortens data analysis duration. Organization construction, management regulations, and technical standards are included in the OMS, which guarantees the sustainable operation of the MDGS. The MDGS was established to advance state-of-the-art and state-of-practice data governance for the health and medical sectors in China.

RESULTS

With the first phase of the MDGS, the quantity and quality of research projects increase, research transformation speeds up, and the researchers' job satisfaction increased.

CONCLUSIONS

Based on our preliminary achievements, it was necessary and feasible to establish the MDGS. It is important to have comprehensive requirement study, top-level design, refined planning, phase-by-phase implementation, and continual optimization.

Performance of an artificial intelligence system for bone age assessment in Tibet

OBJECTIVE

To investigate whether bone age (BA) of children living in Tibet Highland could be accurately assessed using a fully automated artificial intelligence (AI) system.

METHODS：

Left hand radiographs of 385 children (300 Tibetan and 85 immigrant Han) aged 4-18 years who presented to the largest medical center of Tibet between September 2013 and November 2019 were consecutively collected. From these radiographs, BA was determined using the Greulich and Pyle (GP) method by experts in a consensus manner; furthermore, BA was estimated by a previously reported artificial intelligence (AI) BA system based on Han children from southern China. The performance of the AI system was compared with that of experts by using statistical analysis.

RESULTS

Compared with the experts' results, the accuracy of the AI system for Tibetan and Han children within 1 year was 84.67 and 89.41%, respectively, and its mean absolute difference (MAD) was 0.65 and 0.56 years, respectively. The discrepancy in hand-wrist bone maturation was the main cause of low accuracy of the system in the 4- to 6-year-old group.

CONCLUSION

The AI BA system developed for Han Chinese children living in flat regions could enable to assess BA accurately in Tibet where medical resources are limited.

ADVANCES IN KNOWLEDGE

AI-based BA system may serve as an effective and efficient solution to assess BA in Tibet.