Computer Engineering and Applications ›› 2011, Vol. 47 ›› Issue (12): 169-172.

• 图形、图像、模式识别 • Previous Articles     Next Articles

Novel location algorithm research for phalange and carpal ROI based on k-cosine and shape information

RAN Longke1,2,ZHOU Lihua1,CHEN Zhong3   

  1. 1.Department of Computer and Science,Chongqing Medical University,Chongqing 400016,China
    2.Laboratory of Forensic and Biology Information Technology,Chongqing Medical University,Chongqing 400016,China
    3.Institute for Pattern Recognition & Artificial Intelligence,Huazhong University of Science and Technology,Wuhan 430074,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-04-21 Published:2011-04-21

一种新的指腕骨ROI的定位算法研究—基于k余弦和形状信息

冉隆科1,2,周丽华1,2,陈 忠3   

  1. 1.重庆医科大学 计算机教研室,重庆 400016
    2.重庆医科大学 法医学及生物信息技术研究室,重庆 400016
    3.华中科技大学 图像识别与人工智能研究所,武汉 430074

Abstract: 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.

Key words: k-cosine, skeletal bone age assessment, Phalangeal Regions Of Interest(PROI), Carpal Regions Of Interest(CROI), localization, extraction

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。

关键词: k余弦, 骨龄评定, 指骨感兴趣区(PROI), 腕骨感兴趣区(CROI), 定位, 提取