Prediction of forearm bone shape based on partial least squares regression from partial shape
Prediction of forearm bone shape based on partial least squares regression from partial shape
复制标题
DOI：
10.1002/rcs.1807
复制
发表时间：
2017-09-01
影响因子：
2.5
通讯作者：
Sato, Yoshinobu
中科院分区：
文献类型：
--
作者：
Oura, Keiichiro;Otake, Yoshito;Sato, Yoshinobu
背景：以对侧正常形状的镜像作为参考，计算机辅助矫正截骨术的应用越来越广泛。相反，我们建议使用统计学习预测的形状来处理双侧异常的病例，如双侧创伤、先天性疾病和代谢性疾病。方法对100例正常前臂进行CT扫描。整个骨头的形状是基于对其他99块骨头的统计学习，从部分形状预测出来的。通过平均对称表面距离（ASD）、平移和旋转误差来评估精度。结果预测形状的asd范围为0.71 ~ 1.03mm。平均绝对平移和旋转误差分别为0.48 ~ 1.76mm和0.99 ~ 6.08°。结论采用统计学习方法，从部分骨形态预测正常骨形态具有可接受的准确性。预测形状可以替代镜像，这可以减少辐射暴露和检查成本。
BackgroundComputer-assisted corrective osteotomy using a mirror image of the normal contralateral shape as reference is increasingly used. Instead, we propose to use the shape predicted by statistical learning to deal with cases demonstrating bilateral abnormality, such as bilateral trauma, congenital disease, and metabolic disease.MethodsComputed tomography (CT) scans of 100 normal forearms were used in this study. The whole bone shape was predicted from its partial shape based on statistical learning of the other 99 bones. Accuracy was evaluated by average symmetric surface distance (ASD), and translational and rotational errors.ResultsASDs for predicted shapes were 0.71-1.03mm. Mean absolute translational and rotational errors were 0.48-1.76mm and 0.99-6.08 degrees, respectively.ConclusionNormal bone shape was predicted with an acceptable accuracy from its partial shape using statistical learning. Predicted shape can be an alternative to a mirror image, which may enable reduced radiation exposure and examination costs.