Zhang Weiwei, Noble J Alison, Brady J Mike
Wolfson Medical Vision Lab, Department of Engineering Science, University of Oxford, Parks Road, Oxford, United Kingdom.
Inf Process Med Imaging. 2007;20:50-61. doi: 10.1007/978-3-540-73273-0_5.
We present a new method to non-rigidly co-register a real-time 3D ultrasound volume slice to a cardiovascular MR image. The motivation for our research is to assist a clinician to automatically fuse the information from multiple imaging modalities for the early diagnosis and therapy of cardiac disease. The local phase presentation of both images is utilized as an image descriptor of the "featureness". The local deformation of ventricles is modeled by a polyaffine transformation. The anchor points (or control points) used in the polyaffine transformation are automatically detected and refined by calculating a local mis-match measure based on phase mutual information. The registration process is built in an adaptive multi-scale framework to maximize the phase-based similarity measure by optimizing the parameters of the polyaffine transformation. Registration results have demonstrated that this novel method is superior to our prior work, yielding an accurate registration to local cardiac regions.
我们提出了一种新方法，用于将实时三维超声体积切片与心血管磁共振图像进行非刚性配准。我们开展这项研究的动机是协助临床医生自动融合来自多种成像模态的信息，以实现心脏病的早期诊断和治疗。将这两种图像的局部相位呈现用作“特征性”的图像描述符。心室的局部变形通过多仿射变换建模。多仿射变换中使用的锚点（或控制点）通过基于相位互信息计算局部不匹配度量来自动检测和优化。配准过程构建在自适应多尺度框架中，通过优化多仿射变换的参数来最大化基于相位的相似性度量。配准结果表明，这种新方法优于我们之前的工作，能够对心脏局部区域进行精确配准。
