Evaluating Children’s Growth Based on Carpal Bones in Left-Hand X-Ray Images Using Deep Learning
This study demonstrates that a deep learning model trained exclusively on carpal bones from left-hand X-rays, with specific preprocessing techniques, achieves accurate bone age assessment (8.38 ± 0.39 months MAE) on the RSNA dataset, proving that the carpal region alone encodes sufficient information for evaluating children's growth.