Related Experiment Video
Updated: Jun 25, 2025
Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable
Published on: May 17, 2024
Artificial intelligence model system for bone age assessment of preschool children
Chengcheng Gao1, Chunfeng Hu1,2, Qi Qian3
1Department of Radiology, Hangzhou First People's Hospital, Hangzhou, China.
Insights
Artificial intelligence (AI) significantly improves bone age assessment (BAA) accuracy in preschool children by reducing variations between and within observers. This AI tool enhances radiologist performance in clinical settings.
Area of Science:
- Pediatric radiology
- Medical imaging analysis
- Artificial intelligence in healthcare
Background:
- Bone age assessment (BAA) is crucial for evaluating growth and development in children.
- Preschool children present unique challenges for BAA due to high variability.
- Inter- and intra-observer variations can impact the reliability of BAA.
Purpose of the Study:
- To evaluate the impact of an AI system on inter- and intra-observer variations in BAA for preschool children.
- To compare the effectiveness of AI-assisted BAA using TW3 and RUS-CHN methods.
Main Methods:
- Retrospective analysis of radiographs from 94 preschool children (3-6 years) in China.
- Four radiology reviewers assessed bone age using TW3 and RUS-CHN methods, with and without AI assistance.
- Bone age was reassessed after a 4-week interval to evaluate intra-observer reproducibility.
- Statistical analysis included accuracy metrics, ICC, and Bland-Altman plots.
Main Results:
- AI significantly improved BAA accuracy, decreasing RMSE and MAE for both methods (p < 0.001).
- AI enhanced inter-observer agreement and intra-observer reproducibility, with ICC values exceeding 0.99.
- The AI system demonstrated improved performance in both TW3 and RUS-CHN assessments.
Conclusions:
- AI systems can effectively reduce inter-observer variability and improve intra-observer reproducibility in pediatric BAA.
- AI serves as a valuable tool for radiologists, enhancing the accuracy and reliability of bone age assessment in preschool children.
- This study highlights the potential of AI in standardizing BAA, particularly for challenging age groups and specific populations like Chinese 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.
