基于CUDA的2D-3D医学图像快速配准

Rapid 2D-3D Medical Image Registration Based on CUDA

医学三维扫描体数据和二维图像配准在临床诊断、手术规划等领域应用广泛,特别是在手术导航时,三维扫描体数据和二维图像的结合既需要保证配准的精度,又要达到手术中即时应用的要求。本文提出一种混合几何和图像密度特征构成的相似度度量函数,对术前CT和术中X线图像进行快速的2D-3D配准,其实现方便、计算量小,同时计算精度可以满足正常的需要。另外,整个计算过程非常适合高度并行的数值计算,通过采用基于CUDA的硬件加速算法,能够达到手术中即时应用的要求。

The medical image registration between preoperative three-dimensional （3D） scan data and intraoperative two-dimensional （2D） image is a key technology in the surgical navigation. Most previous methods need to generate 2D digitally reconstructed radiographs （DRR） images from the 3D scan volume data, then use conventional image similarity function for comparison. This procedure includes a large amount of calculation and is difficult to archive real-time processing. In this paper, with using geometric feature and image density mixed characteristics, we proposed a new similarity measure function for fast 2D-3D registration of preoperative CT and intraoperative X-ray images. This algorithm is easy to implement, and the calculation process is very short, while the resulting registration accuracy can meet the clinical use. In addition, the entire calculation process is very suitable for highly parallel numerical calculation by using the algorithm based on CUDA hardware acceleration to satisfy the requirement of real-time application in surgery.