论文部分内容阅读
多模态医学图象的配准在医学诊断和治疗计划中起着重要的作用。本文提出一种基于轮廓特征的迭代最近点（ＳＶＤ－ＩＣＰ）的配准方法。这种方法结合了ＳＶＤ最优化解析方法和迭代搜索的优点来解决图象轮廓点的匹配问题，适用于不同模态医学图象之间的配准。我们关于ＣＴ－ＭＲＩ和ＰＥＴ－ＭＲＩ二维图象的配准实验证明了该方法的有效性。
Registration of multimodal medical images plays an important role in medical diagnosis and treatment planning. This paper presents a registration method based on contour feature of iterative nearest neighbor (SVD-ICP). This method combines the advantages of SVD optimization method and iterative search to solve the problem of image contour matching. It is suitable for the registration of different modal medical images. Our experimental results on the registration of two-dimensional CT-MRI and PET-MRI images demonstrate the effectiveness of this method.