A CNN Regression Approach for Real-Time 2D/3D Registration
A CNN Regression Approach for Real-Time 2D/3D Registration
复制标题
DOI：
10.1109/tmi.2016.2521800
复制
发表时间：
2016-05-01
影响因子：
10.6
通讯作者：
Liao, Rui
中科院分区：
文献类型：
--
作者：
Miao, Shun;Wang, Z. Jane;Liao, Rui
在本文中，我们提出了一种卷积神经网络（CNN）回归方法，以解决现有基于强度的 2-D/3-D 配准技术的两个主要局限性：1）计算速度慢；2）捕获范围小。与基于优化的方法不同，基于优化的方法在表示配准质量的标量值度量函数上迭代地优化变换参数，所提出的方法利用嵌入在数字重建放射线照片和X射线图像的外观中的信息，并采用CNN回归器直接估计变换参数。引入自动特征提取步骤来计算 3D 姿态索引特征，这些特征对要回归的变量敏感，同时对其他因素具有鲁棒性。然后，CNN 回归器针对局部区域进行训练，并以分层方式应用，将复杂的回归任务分解为多个可以单独学习的更简单的子任务。此外，CNN 回归模型还采用权重共享来减少内存占用。所提出的方法已在 3 个潜在的临床应用中进行了定量评估，表明与基于强度的方法相比，其在提供高精度实时 2-D/3-D 配准方面具有显着优势，并且捕获范围显着扩大。
In this paper, we present a Convolutional Neural Network (CNN) regression approach to address the two major limitations of existing intensity-based 2-D/3-D registration technology: 1) slow computation and 2) small capture range. Different from optimization-based methods, which iteratively optimize the transformation parameters over a scalar-valued metric function representing the quality of the registration, the proposed method exploits the information embedded in the appearances of the digitally reconstructed radiograph and X-ray images, and employs CNN regressors to directly estimate the transformation parameters. An automatic feature extraction step is introduced to calculate 3-D pose-indexed features that are sensitive to the variables to be regressed while robust to other factors. The CNN regressors are then trained for local zones and applied in a hierarchical manner to break down the complex regression task into multiple simpler sub-tasks that can be learned separately. Weight sharing is furthermore employed in the CNN regression model to reduce the memory footprint. The proposed approach has been quantitatively evaluated on 3 potential clinical applications, demonstrating its significant advantage in providing highly accurate real-time 2-D/3-D registration with a significantly enlarged capture range when compared to intensity-based methods.