Automatic determination of Greulich and Pyle bone age in healthy Dutch children

Abstract

Background Bone age (BA) assessment is a routine procedure in paediatric radiology, for which the Greulich and Pyle (GP) atlas is mostly used. There is rater variability, but the advent of automatic BA determination eliminates this. Objective To validate the BoneXpert method for automatic determination of skeletal maturity of healthy children against manual GP BA ratings. Materials and methods Two observers determined GP BA with knowledge of the chronological age (CA). A total of 226 boys with a BA of 3-17 years and 179 girls with a BA of 3-15 years were included in the study. BoneXpert's estimate of GP BA was calibrated to agree on average with the manual ratings based on several studies, including the present study. Results Seven subjects showed a deviation between manual and automatic BA in excess of 1.9 years. They were rerated blindly by two raters. After correcting these seven ratings, the root mean square error between manual and automatic rating in the 405 subjects was 0.71 years (range 0.66-0.76 years, 95% CI). BoneXpert's GP BA is on average 0.28 and 0.20 years behind the CA for boys and girls, respectively. Conclusion BoneXpert is a robust method for automatic determination of BA.

Validation of a New Method for Automated Determination of Bone Age in Japanese Children

“…The accuracy of BoneXpert BA determination in Japanese children was found to be 0.72 years. This is compatible with previous results on Caucasian children, which ranged from 0.72 to 0.80 years [3,4,5]. We can conclude that the maturity indicators, which were derived on a Caucasian population, are also adequate for Asian populations.…”

“…A complete description of this pure software medical device is provided elsewhere [3,4,5]; the following is a brief review.…”

“…BoneXpert validation studies [4,5] published so far have examined GP BA. The GP BA range of BoneXpert is 2.5–17 years for boys, and 2–15 years for girls.…”

“…Recently, a new method has been launched under the name of BoneXpert [3,4] which is fully automated and analyses the 13 RUS bones. BoneXpert automatically rejects radiographs with bad exposure, bad pose of the hand, or abnormal bone shapes.…”

“…BoneXpert automatically rejects radiographs with bad exposure, bad pose of the hand, or abnormal bone shapes. The method was developed on Caucasian children from Europe and has been calibrated and validated in large studies of Caucasian children [4,5]. …”