Department of Pure Mathematics & Mathematical Statistics, University of Cambridge, Cambridge, UK.
Department of Computer Science, The Institute for Biomedical Engineering, George Washington University, Washington, DC, USA.
Int J Comput Assist Radiol Surg. 2018 Mar;13(3):353-361. doi: 10.1007/s11548-018-1702-1. Epub 2018 Jan 19.
Technical advancements have been part of modern medical solutions as they promote better surgical alternatives that serve to the benefit of patients. Particularly with cardiovascular surgeries, robotic surgical systems enable surgeons to perform delicate procedures on a beating heart, avoiding the complications of cardiac arrest. This advantage comes with the price of having to deal with a dynamic target which presents technical challenges for the surgical system. In this work, we propose a solution for cardiac motion estimation.
Our estimation approach uses a variational framework that guarantees preservation of the complex anatomy of the heart. An advantage of our approach is that it takes into account different disturbances, such as specular reflections and occlusion events. This is achieved by performing a preprocessing step that eliminates the specular highlights and a predicting step, based on a conditional restricted Boltzmann machine, that recovers missing information caused by partial occlusions.
We carried out exhaustive experimentations on two datasets, one from a phantom and the other from an in vivo procedure. The results show that our visual approach reaches an average minima in the order of magnitude of [Formula: see text] while preserving the heart's anatomical structure and providing stable values for the Jacobian determinant ranging from 0.917 to 1.015. We also show that our specular elimination approach reaches an accuracy of 99% compared to a ground truth. In terms of prediction, our approach compared favorably against two well-known predictors, NARX and EKF, giving the lowest average RMSE of 0.071.
Our approach avoids the risks of using mechanical stabilizers and can also be effective for acquiring the motion of organs other than the heart, such as the lung or other deformable objects.
技术进步是现代医疗解决方案的一部分，因为它们提供了更好的手术选择，使患者受益。特别是在心血管手术中，机器人手术系统使外科医生能够在跳动的心脏上进行精细的手术，避免心脏骤停的并发症。这种优势伴随着必须处理动态目标的代价，这对手术系统提出了技术挑战。在这项工作中，我们提出了一种心脏运动估计的解决方案。
我们的估计方法使用变分框架，保证了心脏复杂结构的保留。我们的方法的一个优点是它考虑了不同的干扰，如镜面反射和遮挡事件。这是通过执行一个预处理步骤来实现的，该步骤消除镜面反射，以及一个基于条件受限玻尔兹曼机的预测步骤，该步骤恢复了由于部分遮挡而丢失的信息。
我们在两个数据集上进行了详尽的实验，一个来自于幻影，另一个来自于体内手术。结果表明，我们的视觉方法在保持心脏解剖结构的同时，在量级上达到了平均最小值[公式：见正文]，并为雅可比行列式提供了稳定的值，范围从 0.917 到 1.015。我们还表明，我们的镜面消除方法与真实值相比达到了 99%的准确性。在预测方面，我们的方法与两个著名的预测器 NARX 和 EKF 相比具有优势，平均 RMSE 最低为 0.071。
我们的方法避免了使用机械稳定器的风险，并且对于获取除心脏以外的器官的运动也很有效，如肺或其他可变形物体。
