A Survey of Deep Learning Based Fully Automatic Bone Age Assessment Algorithms

Abstract

Bone age assessment (BAA) is a technique for assessing the maturity of individual skeletal development, and it is the most accurate and objective method for assessing the deviation of individual development in clinical practice. It is used in the diagnosis of pediatric endocrine diseases, age determination of suspects in juvenile delinquency cases, height prediction, and athlete selection. Early computer-aided BAA mainly segments the skeleton of the hand and gives a final bone age by comparing the morphological descriptions of bones to standard atlas. In recent years, deep learning methods have developed rapidly, and a large number of end-to-end BAA methods based on deep learning have emerged, which have brought new development to the automatic BAA technology. This paper summarizes the technical basis, research status of automatic BAA. Firstly, the basic theory of medical BAA is introduced, then the commonly used traditional segmentation methods in BAA are analyzed. After that, we summarized the most popular methods of BAA based on deep learning, including the network model, data set and the assessment results. This survey also draws attention to a number of research challenges in the fully automatic BAA with deep learning.