摘要
针对基于迭代优化的传统2D-3D医学图像配准算法运行速度慢,难以达到实时配准的要求,本研究提出一种实时2D-3D配准方法。通过将空间刚体变换参数分解到两个平面上,将2D-3D配准简化为两个步骤,包含2D-2D近似刚体配准与单参数2D-3D刚体配准。同时利用深度卷积神经网络拟合患者X射线影像残差与其对应姿态差异间的非线性映射关系,从X-DRR图像对的残差回归出空间刚体变换参数。经由头颅CT数据训练后的网络,在0.04 s内完成了高精度的双X射线配准。本研究提出的配准方法满足了放疗过程中进行实时2D-3D配准工作的要求。
Based on the situation that the traditional 2 D-3 D medical image registration algorithm based on iterative optimization can not realize real-time registration due to slow running speed,a real-time 2 D-3 D registration method is proposed.By decomposing spatial rigid transformation parameters into two planes,2 D-3 D registration is simplified into two steps,including 2 D-2 D approximate rigid registration and single-parameter 2 D-3 D grid registration.Meanwhile,deep convolutional neural network is used to fit the nonlinear mapping between X-ray images residual and its corresponding postural difference,and the space rigid transformation parameters are regressed from the residual of the X-DRR image pair.The network trained by head CT data can complete the high-precision double X-ray registration within 0.04 s.The proposed registration method can satisfy the requirements of real-time 2 D-3 D registration during radiotherapy.
作者
沈延延
冯汉升
SHEN Yanyan;FENG Hansheng(School of Electrical Engineering and Automation,Anhui University,Hefei 230601,China;Institute of Plasma Physics,Chinese Academy of Sciences,Hefei 230031,China)
出处
《中国医学物理学杂志》
CSCD
2020年第3期293-298,共6页
Chinese Journal of Medical Physics
基金
中国科学院合肥物质科学研究院“十三五”规划重点支持项目(kp-2017-24)。
关键词
双X射线影像
2D-3D配准
卷积神经网络
几何分解
double X-ray image
2D-3D registration
convolutional neural network
geometric decomposition
