A Study on Deep Learning Based Sauvegrain Method for Measurement of Puberty Bone Age

This study applies a technique to expand the number of images to a level that allows deep learning. And the applicability of the Sauvegrain method through deep learning with relatively few elbow X-rays is studied. The study was composed of processes similar to the physicians' bone age assessment procedures. The selected reference images were learned without being included in the evaluation data, and at the same time, the data was extended to accommodate the number of cases. In addition, we adjusted the X-ray images to better images using U-Net and selected the ROI with RPN + so as to be able to perform bone age estimation through CNN. The mean absolute error of the Sauvegrain method based on deep learning is 2.8 months and the Mean Absolute Percentage Error (MAPE) is 0.018. This result shows that X - ray analysis using the Sauvegrain method shows higher accuracy than that of the age group of puberty even in the deep learning base. This means that deep learning of the Suvegrain method can be measured at a level similar to that of an expert, based on the extended X-ray image with the image data extension technique. Finally, we applied the Sauvegrain method to deep learning for accurate measurement of bone age at puberty. As a result, the present study is based on deep learning, and compared with the evaluation results of experts, it is possible to overcome limitations of the method of measuring bone age based on machine learning which was in TW3 or Greulich & Pyle due to lack of X- I confirmed the fact. And we also presented the Sauvegrain method, which is applicable to adolescents as well.