Abstract

Aim: Bone age assessment is an important measure of skeletal maturity in children with a growth development disorder. Furthermore, age estimation is an important method applied in various situations such as growth observation, immigrant registration, legal criminal justice, and body detection. In this study, we aimed to develop a computer-assisted bone age detection system.
Materials and Methods: This detection is usually evaluated by a trained physician using a radiological examination of the left wrist and a reference model. However, this evaluation method was stated to cause differences brought by interobserver and intraobserver variabilities. Several automated approaches have been proposed to overcome these problems, but none of them have been proven to be generalized according to different races, age ranges, and gender. Considering today's technology, it is observed that developments in the software are already used in the field of health. In this study, bone age was determined from X-rays of the left wrist using convolutional neural networks, which are a popular subject of recent years.
Results: In the study, in which a total of 150 patients' images were used, different deep learning architectures were used and the results were compared. On average, the success rate was best at 98.39% with different training-testing split rates.
Conclusion: This study demonstrated that deep learning could be used to determine bone age.

Key words: Age estimation; deep learning; greulich and Pyle; X-ray of the wrist