Age Estimation from Left-Hand Radiographs with Deep Learning Methods

Bone age is estimated in pediatric medicine for medical and legal purposes. In medicine, it aids the growth development assessment of various diseases affecting children. forensic required to determine criminal liability by age, refugee estimation, child-adult discrimination. such cases, radiologists or specialists conduct bone estimation from left hand-wrist radiographs using atlas methods that require time effort. This study aims develop a computer-based decision support system new modified deep learning approach accelerate radiologists' workflow wrist radiographs. The KCRD dataset created us was used test proposed method. performance IncepitonV3 model compared IncepitonV3, MobileNetV2, EfficientNetB7 models. Acceptably high results (MAE=4.3, RMSE=5.76, R2=0.99) were observed with transfer