中文摘要：

在骨龄自动化评价的研究中，如何对指骨ROI和腕骨ROI的有效定位和成功提取是其研究的难点和急需解决的关键问题之一。在利用手指骨和腕骨形状信息的基础上，提出了用二元三次线性回归方法来拟合图像背景，从而移除图像背景；用基于k余弦的方法来定位腕骨ROI和指骨ROI的关键点，最后成功提取出腕骨ROI和指骨ROI。通过超过60例的临床骨龄X光片图像数据验证最后提取的正确率在93％以上。使用该方法不用考虑骨龄图像背景灰度值的改变、图像位置和方向的变化，因而具有极大的鲁棒性，可以直接应用到骨龄自动化评价的后续研究中。

英文摘要：

In the research of automatic bone age assessment,how to locate and extract phalangeal Regions Of Interest（ROI） and carpal ROI efficiently has become one of the most difficult and urgent key problems.The two-dimensional third order polynomial linear regression based on shape information for phalanges and carpals is proposed,though which the background images can be fitted and removed.And it locates the key points of phalangeal ROI and carpal ROI accurately by using k-cosine algorithm, so phalangeal ROI and carpal ROI can be extracted.Experiments on more than 60 left hand radiograph data show that the correct extracted rates of the proposed method are higher than 93%.Moreover,the method is robust for gray value variation of background, the position and orientation of the hand, so it can be used directly for automatic skeletal bone age assessment in the follow-up study.