An artificial intelligence-based bone age assessment model for Han and Tibetan children

Manual bone age assessment (BAA) is associated with longer interpretation time and higher cost and variability, thus posing challenges in areas with restricted medical facilities, such as the high-altitude Tibetan Plateau. The application of artificial intelligence (AI) for automating BAA could facilitate resolving this issue. This study aimed to develop an AI-based BAA model for Han and Tibetan children. A model named "EVG-BANet" was trained using three datasets, including the Radiology Society of North America (RSNA) dataset (training set = 12611, validation set = 1425, and test set = 200), the Radiological Hand Pose Estimation (RHPE) dataset (training set = 5491, validation set = 713, and test set = 79), and a self-established local dataset [training set = 825 and test set = 351 (Han = 216 and Tibetan = 135)]. An open-access state-of-the-art model BoNet was used for comparison. The accuracy and generalizability of the two models were evaluated using the abovementioned three test sets and an external test set ( = 256, all were Tibetan). Mean absolute difference (MAD) and accuracy within 1 year were used as indicators. Bias was evaluated by comparing the MAD between the demographic groups. EVG-BANet outperformed BoNet in the MAD on the RHPE test set (0.52 vs. 0.63 years, < 0.001), the local test set (0.47 vs. 0.62 years, < 0.001), and the external test set (0.53 vs. 0.66 years, < 0.001) and exhibited a comparable MAD on the RSNA test set (0.34 vs. 0.35 years, = 0.934). EVG-BANet achieved accuracy within 1 year of 97.7% on the local test set (BoNet 90%, < 0.001) and 89.5% on the external test set (BoNet 85.5%, = 0.066). EVG-BANet showed no bias in the local test set but exhibited a bias related to chronological age in the external test set. EVG-BANet can accurately predict the bone age (BA) for both Han children and Tibetan children living in the Tibetan Plateau with limited healthcare facilities.