Skeletal bone age assessments for young children based on regression convolutional neural networks
Related Experiment Video
Updated: Jan 4, 2026
Scanning Skeletal Remains for Bone Mineral Density in Forensic Contexts
Published on: January 29, 2018
Peng Yi Hao1, Sharon Chokuwa1, Xu Hang Xie1
1College of Computer Science & Technology, Zhejiang University of Technology, Hangzhou, China.
Insights
This study introduces an automated bone age assessment (BAA) method using convolutional neural networks. The novel approach significantly reduces variability, achieving high accuracy in evaluating children's skeletal maturity from wrist radiographs.
Area of Science:
- Radiology
- Artificial Intelligence
- Pediatric Endocrinology
Background:
- Bone Age Assessment (BAA) is crucial for diagnosing pediatric genetic and hormonal disorders.
- Conventional BAA methods are time-consuming and prone to inter-observer variability.
- Previous automated methods have not sufficiently reduced human expert variability.
Purpose of the Study:
- To develop an automated and efficient Bone Age Assessment (BAA) system.
- To reduce inter-observer variability in skeletal age evaluation.
- To accurately assess bone age using deep learning techniques.
Main Methods:
- Utilized a regression convolutional neural network for automated BAA.
- Implemented automatic region of interest (ROI) extraction of carpal bones.
- Performed boundary extraction of carpal bones from left hand wrist radiographs.
Main Results:
- Achieved an average discrepancy of 2.75 months between clinical and automatic BAA.
- Reached 90.15% accuracy within 6 months from ground truth for males.
- Attained 99.43% accuracy within 1 year for test radiographs.
Conclusions:
- The proposed automated BAA method is efficient and accurate.
- This approach significantly reduces variability in skeletal age evaluation.
- The convolutional neural network model shows promise for clinical BAA applications.
Abstract:
Pediatricians and pediatric endocrinologists utilize Bone Age Assessment (BAA) for in-vestigations pertaining to genetic disorders, hormonal complications and abnormalities in the skeletal system maturity of children. Conventional methods dating back to 1950 were often tedious and suscep-tible to inter-observer variability, and preceding attempts to improve these traditional techniques have inadequately addressed the human expert inter-observer variability so as to significantly refine bone age evaluations. In this paper, an automated and efficient approach with regression convolutional neu-ral network is proposed. This approach automatically exploits the carpal bones as the region of interest (ROI) and performs boundary extraction of carpal bones, then based on the regression convolutional neural network it evaluates the skeletal age from the left hand wrist radiograph of young children. Experiments show that the proposed method achieves an average discrepancy of 2.75 months between clinical and automatic bone age evaluations, and achieves 90.15% accuracy within 6 months from the ground truth for male. Further experimental results with test radiographs assigned an accuracy within 1 year achieved 99.43% accuracy.
Related Concept Videos
01:18Classification of Bones
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The...
01:09Changes in the Appendicular Skeleton with Age
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...
01:40Bone Remodeling
01:55Bone Structure
01:24Bone Formation by Endochondral Ossification
01:27Growth of Cartilage and Bone Tissue