A Novel Approach for Bone Age Assessment using Deep Learning

Abstract

In this paper, we propose a detailed approach to create a Bone age assessment model. Bone age assessment is a common medical practice in the assessment of child development, who are less than 18 years of age. In this proposed model, the Xception architecture is being used for transfer learning. Using feature extraction and transfer learning, the pre-trained convolutional neural network were custom trained. The dataset used for training the model is obtained from the Kaggle RNSA Bone Age dataset containing 12811 male and female bone images of different age groups. Finally, we were able to attain a mean absolute error (MAE) of 8.175 months in male and female patients, which aligns with our initial goal of achieving MAE in under a year.