Clinical application of automated Greulich-Pyle bone age determination in children with short stature
Clinical application of automated Greulich-Pyle bone age determination in children with short stature
复制标题
DOI：
10.1007/s00247-008-1114-4
复制
发表时间：
2009-06-01
影响因子：
2.3
通讯作者：
Ranke, Michael B.
中科院分区：
文献类型：
--
作者：
Martin, David D.;Deusch, Dorothee;Ranke, Michael B.
骨龄（BA）评级耗时且高度依赖于评级者。为了调整全自动BoneXpert方法，使其与5名评级者的手动Greulich和Pyle BA（GP BA）评级一致，并验证矮小儿童的准确性。来自188名矮小儿童的共计1，097张左手X线照片，包括生长激素缺乏症（44%）和特纳综合征（29%）。BoneXpert拒绝了1，097张X光片中的14张，27张X光片偏离操作员BA超过1.9年。这些都是由四个操作员盲目重新评级。在27个新评级中，26个在自动BA值的1.9年内。手动和自动评级之间的均方根偏差为0.72岁（95% CI 0.69-0.75）。BoneXpert能够自动处理99%的图像而不会出现错误，并与操作员达成良好的一致，这表明该方法对矮小儿童有效且可靠。
Bone age (BA) rating is time consuming and highly rater dependent.To adjust the fully automated BoneXpert method to agree with the manual Greulich and Pyle BA (GP BA) ratings of five raters and to validate the accuracy for short children.A total of 1,097 left hand radiographs from 188 children with short stature, including growth hormone deficiency (44%) and Turner syndrome (29%) were evaluated.BoneXpert rejected 14 of the 1,097 radiographs, and deviated by more than 1.9 years from the operator BA for 27 radiographs. These were rerated blindly by four operators. Of the 27 new ratings, 26 were within 1.9 years of the automatic BA values. The root mean square deviation between manual and automatic rating was 0.72 years (95% CI 0.69-0.75).BoneXpert's ability to process 99% of images automatically without errors, and to obtain good agreement with an operator suggests that the method is efficient and reliable for short children.