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

Abstract

BoneXpert, an automated method for analysis of hand radiographs of children, has recently been developed and validated in European children. It determines Tanner-Whitehouse (TW) and Greulich Pyle (GP) bone ages (BA). The purpose of this work is to validate BoneXpert BA in Japanese children and determine the following two properties of the method: (1) The accuracy of the BA, i.e. the standard deviation from an experienced Japanese TW BA rater. (2) The precision of the BA, i.e. BoneXpert’s ability to yield the same BA value on a repeated radiograph. The data consist of two studies: 185 radiographs of 22 normal children followed longitudinally from approximately 7 years to full maturity, and 284 radiographs of 22 patients with growth hormone deficiency treated with growth hormone and gonadotropin-releasing hormone analogue followed from an age of 4–11 years to almost full maturity. All radiographs were rated manually according to the TW-Japan system. BoneXpert processed all images, and the accuracy (SD) of TW-Japan BA was 0.72 years (95% CI 0.68–0.76). The precision error (SD) on a single determination of GP BA was 0.17 years (95% CI 0.15–0.19). It is concluded that BoneXpert performs as well in Japanese children as it does in Caucasian children. This study accomplishes a calibration of BoneXpert to the TW-Japan standard, which performs well for the entire BA range from 4 years up to full maturity.

The Use of Bone Age in Clinical Practice – Part 1

“…The precision of BoneXpert, defined as the standard deviation (SD) on a single reading, is 0 on the same X-ray and has been conservatively estimated at 0.17 and 0.18 years, respectively, for image series [19], and for assessing the difference between the left and right hand BA of a subject [20]. Comparable human rerating studies yielded a precision SD in the range 0.25–0.82 years [12,16], depending on the experience of the rater.…”

“…The impact of a poor precision can be illustrated by two examples: for a 13-year-old boy with a height of 160 cm, BA values of 13 and 13.82 years yield a difference of 6.1 cm in adult height prediction, and for an 11-year-old girl with a height of 150 cm, BA values of 11 and 11.82 years yield a difference of 4.0 cm. In the search for an objective validation that goes beyond comparing the automated BA to that of trained manual raters, it was found that its correlation with growth potential, and therefore its ability to predict adult height, was at least as good as the GP rating and better than the TW rating of the raters of the First Zurich Longitudinal Study [21]. …”

Automatic Determination of the Greulich-Pyle Bone Age as an Alternative Approach for Chinese Children with Discordant Bone Age

“…As the morphological development of the skeleton is very similar across the races, the translation of morphology into a formal maturity index or a formal BA is considered to be universal, i.e. independent of ethnicity and whether the children show normal or abnormal maturation [8], even though BoneXpert is based on the data from European children. …”

“…This means that BoneXpert showed a consistent bias to underestimate the BA of Chinese children who were >10 years of age. Other researchers in mainland China, Taiwan and Japan have also pointed out that normal Asian children are inclined to mature faster than their counterparts in Europe [8,11,20]. Even in America, Asian children who are older than 12 years of age were about 1 year advanced relative to the GP standard [12].…”

“…As a solution to this problem, automated systems have been developed [5,6]. One fully automated image analysis method, BoneXpert, has performed well in terms of estimating BA in normal children in some countries including China, even though BoneXpert was based on data of European children [7,8,9,10,11,12]. However, only few articles have discussed the clinical application of BoneXpert for children with discordant BA development [13,14,15,16,17,18].…”