Related Experiment Video
Updated: Jul 13, 2026
06:45
Automated Joint Space Detection Improves Bone Segmentation Accuracy
Published on: November 28, 2025
Dual-input deep learning bone age assessment in late adolescence using hand and knee radiographs
Zishuai Peng1, Nanxin Li1, Yajia Wu1
1College of Electrical Engineering, Sichuan University, Jiuyanqiao Wangjiang Road, Chengdu, 610065, Sichuan, China.
Skeletal Radiology
|July 11, 2026
Summary
A new AI model using hand-wrist and knee X-rays accurately assesses bone age in late adolescents. This dual-input approach shows promising results for clinical use.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Pediatric Endocrinology
Background:
- Accurate bone age assessment is crucial for evaluating growth and development in adolescents.
- Traditional methods rely on single radiograph sites, potentially limiting accuracy in late adolescence.
- Developing advanced AI models can improve the precision and efficiency of bone age determination.
Purpose of the Study:
- To develop and internally evaluate an AI model for bone age assessment in late adolescents.
- To utilize paired hand-wrist and knee radiographs as dual inputs for enhanced accuracy.
- To incorporate chronological age and sex as auxiliary variables in the model.
Main Methods:
- A retrospective study of 547 adolescents (aged 13-19 years) with paired hand-wrist and knee radiographs.
- A ShuffleNet v2-based deep learning model was trained using both radiograph types and demographic data.
- Model performance was evaluated using mean absolute error, root mean square error, and intraclass correlation coefficient on a held-out test set.
Main Results:
- The dual-input model achieved a mean absolute error of 3.77 months and an intraclass correlation coefficient of 0.984.
- 98.18% of predictions were within 12 months of the reference standard.
- Paired hand-knee inputs with demographic variables outperformed single-site inputs, demonstrating the benefit of the dual-input approach.
Conclusions:
- The age-assisted dual-input AI framework demonstrates promising internal performance for bone age assessment in late adolescence.
- Further independent, multicenter external validation is necessary before clinical or legal application.
- Knee radiographs should only be used when medically justified, not as routine additional imaging.
Related Concept Videos
01:09Changes in the Appendicular Skeleton with Age
The upper and lower limb initially develops as a small bulge called a limb bud, which appears on the lateral side of the early embryo. The upper limb bud appears near the end of the fourth week of development, with the lower limb bud appearing shortly after.
Initially, the limb buds consist of a core of mesenchyme covered by a layer of ectoderm. The ectoderm at the end of the limb bud thickens to form a narrow crest called the apical ectodermal ridge. This ridge stimulates the underlying...
Initially, the limb buds consist of a core of mesenchyme covered by a layer of ectoderm. The ectoderm at the end of the limb bud thickens to form a narrow crest called the apical ectodermal ridge. This ridge stimulates the underlying...
01:18Classification of Bones
The bones of the human skeletal system are of varied shapes, sizes, and functions. They can be classified based on their shape and function into four major classes: long bones, short bones, flat bones, and irregular bones. Some classifications include a fifth type, the sesamoid bones, as a separate class, whereas others categorize them under short bones.
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The long...
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The long...