Background and Objective: Liver tumor ablation is often guided by ultrasound (US). Due to poor image quality, intraoperative US is fused with preoperative computed tomography or magnetic tomography (CT/MR) images to provide visual guidance. As of today, the underlying 2D US to 3D CT/MR registration problem remains a very challenging task.

Methods: We propose a novel pipeline to address this registration problem. Contrary to previous work, we do not formulate the problem as a regression task, which - for the given registration problem - achieves a low performance regarding accuracy and robustness due to the limited US soft-tissue contrast and the inter-patient variability on liver vessels. Instead, we first estimate the US probe angle roughly by using a classification network. Given this coarse initialization, we then improve the registration by formulation of the problem as a segmentation task, estimating the US plane in the 3D CT/MR through segmentation.

Results: We benchmark our approach on 1035 clinical images from 52 patients, yielding average registration errors of 11.6${}^{\circ }$ and 4.7 mm, which outperforms the state of the art SVR method[1].

Conclusion: Our results show the efficiency of the proposed registration pipeline, which has potential to improve the robustness and accuracy of intraoperative patient registration.

背景与目的：肝肿瘤消融术通常是在超声（US）的指导下进行的。由于图像质量差，术中超声与术前计算机断层扫描或磁断层扫描（CT / MR）图像融合在一起以提供视觉指导。到目前为止，潜在的2D US到3D CT / MR注册问题仍然是一项非常具有挑战性的任务。

方法：我们提出了一种新颖的管道来解决该注册问题。与以前的工作相反，我们没有将问题描述为回归任务，对于给定的注册问题，由于美国软组织对比度有限以及肝血管之间的患者差异，在准确性和鲁棒性方面均表现不佳。取而代之的是，我们首先通过使用分类网络粗略估计美国探测角度。给定这种粗略的初始化，然后我们通过将问题表示为分段任务来改进配准，并通过分段来估计3D CT / MR中的美国飞机。

结果：我们对来自52例患者的1035张临床图像进行了基准测试，平均注册错误为11.6${}^{\circ }$ 和4.7毫米，优于现有的SVR方法[1]。

结论：我们的结果表明了拟议中的注册流程的效率，它有可能提高术中患者注册的鲁棒性和准确性。