Construction and Validation of A Deep Learning-based Bone Age Prediction Model for Children Living in Both Plain and Highland Regions

Objective Construct and validate a deep learning-based bone age prediction model for children living in both plain and highland regions. Methods A model named “Ethnicity Vision Gender-Bone Age Net (EVG-BANet)” was trained using three datasets， including the Radiology Society of North America (RSNA) dataset training set(n=12611)， validation set (n=1425)， test set (n=200)， the Radiological Hand Pose Estimation (RHPE) datasettraining set (n=5491)， validation set (n=713)， test set (n=79) and a self-established datasettraining set (n=825)， test set (n=351) ， and validated using an external test set. Self-established dataset retrospectively recruited 1176 left-hand DR images of children from Peking Union Medical College Hospital (n=745， all were Han) and Tibet Autonomous Region People’s Hospital (n=431， Han were 114， Tibetan were 317). External test set included images from Peoples’s Hospital of Nagqu (n=256， all were Tibetan). Mean absolute difference (MAD) and accuracy within 1 year were used as indicators. Results EVG-BANet exhibited MAD of 0.34 and 0.52 years in RSNA and RHPE test sets respectively. In the self-established test set， the model achieved MAD of 0.47 years (95% CI: 0.43-0.50) with accuracy within 1 year of 97.72% (95% CI: 95.56-99.01%). For the external test set， MAD was 0.53 years (95% CI: 0.48-0.58)， with accuracy within 1 year of 89.45% (95% CI: 85.03-92.93). Conclusion EVG-BANet demonstrated high accuracy and can be applied in children living in both plain and highland.