American Journal of Roentgenology 2017

Computer-Assisted Program using Deep Learning Technique in Determination of Bone Age: Evaluation of the Accuracy and Efficiency

  • Sep. 2017
  • by Jeong Rye Kim et. al.

OBJECTIVE. The purpose of this study is to evaluate the accuracy and efficiency of a new automatic software system for bone age assessment and to validate its feasibility in clinical practice.

MATERIALS AND METHODS. A Greulich-Pyle method–based deep-learning technique was used to develop the automatic software system for bone age determination. Using this software, bone age was estimated from left-hand radiographs of 200 patients (3–17 years old) using first-rank bone age (software only), computer-assisted bone age (two radiologists with software assistance), and Greulich-Pyle atlas–assisted bone age (two radiologists with Greulich-Pyle atlas assistance only). The reference bone age was determined by the consensus of two experienced radiologists.

RESULTS. First-rank bone ages determined by the automatic software system showed a 69.5% concordance rate and significant correlations with the reference bone age (r = 0.992; p < 0.001). Concordance rates increased with the use of the automatic software system for both reviewer 1 (63.0% for Greulich-Pyle atlas–assisted bone age vs 72.5% for computer-assisted bone age) and reviewer 2 (49.5% for Greulich-Pyle atlas–assisted bone age vs 57.5% for computer-assisted bone age). Reading times were reduced by 18.0% and 40.0% for reviewers 1 and 2, respectively.

CONCLUSION. Automatic software system showed reliably accurate bone age estimations and appeared to enhance efficiency by reducing reading times without compromising the diagnostic accuracy.


Jeong Rye Kim, Woo Hyun Shim, Hee Mang Yoon, Sang Hyup Hong, Jin Seong Lee, Young Ah Cho and Sangki Kim

Tag in

#VUNO Med®-BoneAge™