Re-Assessment of Applicability of Greulich and Pyle-Based Bone Age to Korean Children Using Manual and Deep Learning-Based Automated Method

Development of a simplified prediction model for diagnosing progressive central precocious puberty using clinical and pelvic ultrasound parameters

This study aimed to explore the predictive value of clinical and pelvic ultrasound parameters for diagnosing central precocious puberty (CPP) and to establish a clinically useful simplified prediction model to differentiate progressive CPP (P-CP) from nonprogressive precocious puberty (N-PP). Girls aged <9 years with secondary sexual development who underwent a gonadotropin-releasing hormone stimulation test and pelvic ultrasound between September 2020 and November 2023 were retrospectively included and divided into the P-CP and N-PP groups. Logistic regression analysis was used to determine the significant parameters and develop prediction models. The diagnostic performance of the models was compared using the area under the receiver operating characteristic curve (AUC) analysis and the Delong method. The continuous net reclassification improvement (cNRI) and absolute integrated discrimination improvement (IDI) were used to determine the additive effects of ultrasound parameters. A nomogram scoring system was constructed based on a simplified model to predict the probability of developing P-CP. A total of 109 girls were included, with 64 (58.7%) in the P-CP group. Age, bone age, height, height minus midparental height, basal luteinizing hormone (LH), follicle-stimulating hormone, estradiol, insulin-like growth factor-I, Tanner stage, and cervical and fundus width were significant parameters for the diagnosis of P-CP. The models with ultrasound parameters yielded significantly higher cNRI and IDI values than the models without ultrasound parameters. The simplified model was composed of basal LH, estradiol, and fundus width that showed an AUC value of 0.93 (95% confidence interval: 0.88-0.98) with a cutoff value of 16. In conclusion, adding pelvic ultrasound parameters to traditional clinical results has an additive effect on P-CP screening. A simplified predictive model is effective for CPP screening in real-world clinics. These findings highlight the potential of the prediction model to overcome the limitations of the classical diagnostic approach for CPP in children.

The Impact of Artificial Intelligence on Radiologists' Reading Time in Bone Age Radiograph Assessment: A Preliminary Retrospective Observational Study

To evaluate the real-world impact of artificial intelligence (AI) on radiologists' reading time during bone age (BA) radiograph assessments. Patients (<19 year-old) who underwent left-hand BA radiographs between December 2021 and October 2023 were retrospectively included. A commercial AI software was installed from October 2022. Radiologists' reading times, automatically recorded in the PACS log, were compared between the AI-unaided and AI-aided periods using linear regression tests and factors affecting reading time were identified. A total of 3643 radiographs (M:F=1295:2348, mean age 9.12 ± 2.31 years) were included and read by three radiologists, with 2937 radiographs (80.6%) in the AI-aided period. Overall reading times were significantly shorter in the AI-aided period compared to the AI-unaided period (mean 17.2 ± 12.9 seconds vs. mean 22.3 ± 14.7 seconds, p < 0.001). Staff reading times significantly decreased in the AI-aided period (mean 15.9 ± 11.4 seconds vs. mean 19.9 ± 13.4 seconds, p < 0.001), while resident reading times increased (mean 38.3 ± 16.4 seconds vs. 33.6 ± 15.3 seconds, p = 0.013). The use of AI and years of experience in radiology were significant factors affecting reading time (all, p≤0.001). The degree of decrease in reading time as experience increased was larger when utilizing AI (-1.151 for AI-unaided, -1.866 for AI-aided, difference =-0.715, p<0.001). In terms of AI exposure time, the staff's reading time decreased by 0.62 seconds per month (standard error 0.07, p<0.001) during the AI-aided period. The reading time of radiologists for BA assessment was influenced by AI. The time-saving effect of utilizing AI became more pronounced as the radiologists' experience and AI exposure time increased.

Applicability and robustness of an artificial intelligence-based assessment for Greulich and Pyle bone age in a German cohort

PURPOSE

The determination of bone age (BA) based on the hand and wrist, using the 70-year-old Greulich and Pyle (G&P) atlas, remains a widely employed practice in various institutions today. However, a more recent approach utilizing artificial intelligence (AI) enables automated BA estimation based on the G&P atlas. Nevertheless, AI-based methods encounter limitations when dealing with images that deviate from the standard hand and wrist projections. Generally, the extent to which BA, as determined by the G&P atlas, corresponds to the chronological age (CA) of a contemporary German population remains a subject of continued discourse. This study aims to address two main objectives. Firstly, it seeks to investigate whether the G&P atlas, as applied by the AI software, is still relevant for healthy children in Germany today. Secondly, the study aims to assess the performance of the AI software in handling non-strict posterior-anterior (p. a.) projections of the hand and wrist.

MATERIALS AND METHODS

The AI software retrospectively estimated the BA in children who had undergone radiographs of a single hand using posterior-anterior and oblique planes. The primary purpose was to rule out any osseous injuries. The prediction error of BA in relation to CA was calculated for each plane and between the two planes.

RESULTS

A total of 1253 patients (aged 3 to 16 years, median age 10.8 years, 55.7 % male) were included in the study. The average error of BA in posterior-anterior projections compared to CA was 3.0 (± 13.7) months for boys and 1.7 (± 13.7) months for girls. Interestingly, the deviation from CA tended to be even slightly lower in oblique projections than in posterior-anterior projections. The mean error in the posterior-anterior projection plane was 2.5 (± 13.7) months, while in the oblique plane it was 1.8 (± 13.9) months (p = 0.01).

CONCLUSION

The AI software for BA generally corresponds to the age of the contemporary German population under study, although there is a noticeable prediction error, particularly in younger children. Notably, the software demonstrates robust performance in oblique projections.

KEY POINTS

· Bone age, as determined by artificial intelligence, aligns with the chronological age of the contemporary German cohort under study.. · As determined by artificial intelligence, bone age is remarkably robust, even when utilizing oblique X-ray projections..

CITATION FORMAT

· Pape J, Hirsch F, Deffaa O et al. Applicability and robustness of an artificial intelligence-based assessment for Greulich and Pyle bone age in a German cohort. Fortschr Röntgenstr 2024; 196: 600 - 606.

Use of artificial intelligence in determination of bone age of the healthy individuals: A scoping review

BACKGROUND

Bone age assessment, as an indicator of biological age, is widely used in orthodontics and pediatric endocrinology. Owing to significant subject variations in the manual method of assessment, artificial intelligence (AI), machine learning (ML), and deep learning (DL) play a significant role in this aspect. A scoping review was conducted to search the existing literature on the role of AI, ML, and DL in skeletal age or bone age assessment in healthy individuals.

METHODS

A literature search was conducted in PubMed, Scopus, and Web of Science from January 2012 to December 2022 using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses-Extension for Scoping Reviews (PRISMA-ScR) and Joanna Briggs Institute guidelines. Grey literature was searched using Google Scholar and OpenGrey. Hand-searching of the articles in all the reputed orthodontic journals and the references of the included articles were also searched for relevant articles for the present scoping review.

RESULTS

Nineteen articles that fulfilled the inclusion criteria were included. Ten studies used skeletal maturity indicators based on hand and wrist radiographs, two studies used magnetic resonance imaging and seven studies used cervical vertebrae maturity indicators based on lateral cephalograms to assess the skeletal age of the individuals. Most of these studies were published in non-orthodontic medical journals. BoneXpert automated software was the most commonly used software, followed by DL models, and ML models in the studies for assessment of bone age. The automated method was found to be as reliable as the manual method for assessment.

CONCLUSIONS

This scoping review validated the use of AI, ML, or DL in bone age assessment of individuals. A more uniform distribution of sufficient samples in different stages of maturation, use of three-dimensional inputs such as magnetic resonance imaging, and cone beam computed tomography is required for better training of the models to generalize the outputs for use in the target population.

Development of a deep learning model to distinguish the cause of optic disc atrophy using retinal fundus photography

The differential diagnosis for optic atrophy can be challenging and requires expensive, time-consuming ancillary testing to determine the cause. While Leber's hereditary optic neuropathy (LHON) and optic neuritis (ON) are both clinically significant causes for optic atrophy, both relatively rare in the general population, contributing to limitations in obtaining large imaging datasets. This study therefore aims to develop a deep learning (DL) model based on small datasets that could distinguish the cause of optic disc atrophy using only fundus photography. We retrospectively reviewed fundus photographs of 120 normal eyes, 30 eyes (15 patients) with genetically-confirmed LHON, and 30 eyes (26 patients) with ON. Images were split into a training dataset and a test dataset and used for model training with ResNet-18. To visualize the critical regions in retinal photographs that are highly associated with disease prediction, Gradient-Weighted Class Activation Map (Grad-CAM) was used to generate image-level attention heat maps and to enhance the interpretability of the DL system. In the 3-class classification of normal, LHON, and ON, the area under the receiver operating characteristic curve (AUROC) was 1.0 for normal, 0.988 for LHON, and 0.990 for ON, clearly differentiating each class from the others with an overall total accuracy of 0.93. Specifically, when distinguishing between normal and disease cases, the precision, recall, and F1 scores were perfect at 1.0. Furthermore, in the differentiation of LHON from other conditions, ON from others, and between LHON and ON, we consistently observed precision, recall, and F1 scores of 0.8. The model performance was maintained until only 10% of the pixel values of the image, identified as important by Grad-CAM, were preserved and the rest were masked, followed by retraining and evaluation.

Interdisiplinary and intraobserver reliability of the Greulich-Pyle method among Turkish children

OBJECTIVES

Greulich-Pyle (GP) is one of the most used method for bone age determination (BAD) in various orthopedic, pediatric, radiological, and forensic situations. We aimed to investigate the inter- and intra-observer reliability of the GP method between the most relevant disciplines and its applicability to the Turkish population.

METHODS

One-hundred and eighty (90 boys, 90 girls) patients with a chronological age younger than 18 (mean 9.33) were included. X-rays mixed by the blinded investigator were evaluated by two orthopedists, two radiologists, and two pediatric endocrinologists to determine skeletal age according to the GP atlas. A month later the process was repeated. As a statistical method, Paired t-test was used for comparison, an Intraclass Correlation Coefficients test was used for reliability and a 95 % confidence interval was determined. Results were classified according to Landis-Koch.

RESULTS

All results were consistent with chronological age (p<0.001), according to the investigators' evaluations compared with chronological age. At the initial evaluation, the interobserver reliability of the method was 0.999 (excellent); at the second evaluation, the interobserver reliability was 0.997 (excellent). The intra-observer reliability of the method was 'excellent' in all observers. When results were separately evaluated by gender, excellent intraobserver correlation and excellent correlation with chronological age were found among all researchers (>0.9). When X-rays were divided into three groups based on age ranges and evaluated, 'moderate' and 'good' correlations with chronological age were obtained during the peripubertal period.

CONCLUSIONS

The GP method used in skeletal age determination has excellent inter- and intra-observer reliability. During the peripubertal period, potential discrepancies in bone age assessments should be kept in mind. This method can be used safely and reproducibly by the relevant specialists.

Bone Age Assessment Using Artificial Intelligence in Korean Pediatric Population: A Comparison of Deep-Learning Models Trained With Healthy Chronological and Greulich-Pyle Ages as Labels

OBJECTIVE

To develop a deep-learning-based bone age prediction model optimized for Korean children and adolescents and evaluate its feasibility by comparing it with a Greulich-Pyle-based deep-learning model.

MATERIALS AND METHODS

A convolutional neural network was trained to predict age according to the bone development shown on a hand radiograph (bone age) using 21036 hand radiographs of Korean children and adolescents without known bone development-affecting diseases/conditions obtained between 1998 and 2019 (median age [interquartile range {IQR}], 9 [7-12] years; male:female, 11794:9242) and their chronological ages as labels (Korean model). We constructed 2 separate external datasets consisting of Korean children and adolescents with healthy bone development (Institution 1: n = 343; median age [IQR], 10 [4-15] years; male: female, 183:160; Institution 2: n = 321; median age [IQR], 9 [5-14] years; male: female, 164:157) to test the model performance. The mean absolute error (MAE), root mean square error (RMSE), and proportions of bone age predictions within 6, 12, 18, and 24 months of the reference age (chronological age) were compared between the Korean model and a commercial model (VUNO Med-BoneAge version 1.1; VUNO) trained with Greulich-Pyle-based age as the label (GP-based model).

RESULTS

Compared with the GP-based model, the Korean model showed a lower RMSE (11.2 vs. 13.8 months; P = 0.004) and MAE (8.2 vs. 10.5 months; P = 0.002), a higher proportion of bone age predictions within 18 months of chronological age (88.3% vs. 82.2%; P = 0.031) for Institution 1, and a lower MAE (9.5 vs. 11.0 months; P = 0.022) and higher proportion of bone age predictions within 6 months (44.5% vs. 36.4%; P = 0.044) for Institution 2.

CONCLUSION

The Korean model trained using the chronological ages of Korean children and adolescents without known bone development-affecting diseases/conditions as labels performed better in bone age assessment than the GP-based model in the Korean pediatric population. Further validation is required to confirm its accuracy.

Prediction of Fishman's skeletal maturity indicators using artificial intelligence

The present study aimed to evaluate the performance of automated skeletal maturation assessment system for Fishman's skeletal maturity indicators (SMI) for the use in dental fields. Skeletal maturity is particularly important in orthodontics for the determination of treatment timing and method. SMI is widely used for this purpose, as it is less time-consuming and practical in clinical use compared to other methods. Thus, the existing automated skeletal age assessment system based on Greulich and Pyle and Tanner-Whitehouse3 methods was further developed to include SMI using artificial intelligence. This hybrid SMI-modified system consists of three major steps: (1) automated detection of region of interest; (2) automated evaluation of skeletal maturity of each region; and (3) SMI stage mapping. The primary validation was carried out using a dataset of 2593 hand-wrist radiographs, and the SMI mapping algorithm was adjusted accordingly. The performance of the final system was evaluated on a test dataset of 711 hand-wrist radiographs from a different institution. The system achieved a prediction accuracy of 0.772 and mean absolute error and root mean square error of 0.27 and 0.604, respectively, indicating a clinically reliable performance. Thus, it can be used to improve clinical efficiency and reproducibility of SMI prediction.

Hospital-wide survey of clinical experience with artificial intelligence applied to daily chest radiographs

PURPOSE

To assess experience with and perceptions of clinical application of artificial intelligence (AI) to chest radiographs among doctors in a single hospital.

MATERIALS AND METHODS

A hospital-wide online survey of the use of commercially available AI-based lesion detection software for chest radiographs was conducted with all clinicians and radiologists at our hospital in this prospective study. In our hospital, version 2 of the abovementioned software was utilized from March 2020 to February 2021 and could detect three types of lesions. Version 3 was utilized for chest radiographs by detecting nine types of lesions from March 2021. The participants of this survey answered questions on their own experience using AI-based software in daily practice. The questionnaires were composed of single choice, multiple choices, and scale bar questions. Answers were analyzed according to the clinicians and radiologists using paired t-test and the Wilcoxon rank-sum test.

RESULTS

One hundred twenty-three doctors answered the survey, and 74% completed all questions. The proportion of individuals who utilized AI was higher among radiologists than clinicians (82.5% vs. 45.9%, p = 0.008). AI was perceived as being the most useful in the emergency room, and pneumothorax was considered the most valuable finding. Approximately 21% of clinicians and 16% of radiologists changed their own reading results after referring to AI, and trust levels for AI were 64.9% and 66.5%, respectively. Participants thought AI helped reduce reading times and reading requests. They answered that AI helped increase diagnostic accuracy and were more positive about AI after actual usage.

CONCLUSION

Actual adaptation of AI for daily chest radiographs received overall positive feedback from clinicians and radiologists in this hospital-wide survey. Participating doctors preferred to use AI and regarded it more favorably after actual working with the AI-based software in daily clinical practice.