Fraunhofer IPA, Theodor-Kutzer-Ufer 1-3, 68167, Mannheim, Germany.
Department Artificial Intelligence in Biomedical Engineering (AIBE), Friedrich-Alexander University Erlangen-Nürnberg, Werner-von-Siemens-Straße 61, 91052, Erlangen, Germany.
Int J Comput Assist Radiol Surg. 2023 Sep;18(9):1735-1744. doi: 10.1007/s11548-023-02938-7. Epub 2023 May 28.
Endovascular intervention is the state-of-the-art treatment for common cardiovascular diseases, such as heart attack and stroke. Automation of the procedure may improve the working conditions of physicians and provide high-quality care to patients in remote areas, posing a major impact on overall treatment quality. However, this requires the adaption to individual patient anatomies, which currently poses an unsolved challenge.
This work investigates an endovascular guidewire controller architecture based on recurrent neural networks. The controller is evaluated in-silico on its ability to adapt to new vessel geometries when navigating through the aortic arch. The controller's generalization capabilities are examined by reducing the number of variations seen during training. For this purpose, an endovascular simulation environment is introduced, which allows guidewire navigation in a parametrizable aortic arch.
The recurrent controller achieves a higher navigation success rate of 75.0% after 29,200 interventions compared to 71.6% after 156,800 interventions for a feedforward controller. Furthermore, the recurrent controller generalizes to previously unseen aortic arches and is robust towards size changes of the aortic arch. Being trained on 2048 aortic arch geometries gives the same results as being trained with full variation when evaluated on 1000 different geometries. For interpolation a gap of 30% of the scaling range and for extrapolation additional 10% of the scaling range can be navigated successfully.
Adaption to new vessel geometries is essential in the navigation of endovascular instruments. Therefore, the intrinsic generalization to new vessel geometries poses an essential step towards autonomous endovascular robotics.
血管内介入治疗是心脏病发作和中风等常见心血管疾病的最新治疗方法。该手术的自动化可以改善医生的工作条件，并为偏远地区的患者提供高质量的护理，这对整体治疗质量有重大影响。然而，这需要适应个体患者的解剖结构，这目前仍是一个未解决的挑战。
本研究调查了一种基于递归神经网络的血管内导丝控制器架构。该控制器在通过主动脉弓进行导航时，在适应新血管几何形状的能力方面进行了计算机模拟评估。通过减少训练过程中观察到的变体数量，研究了控制器的泛化能力。为此，引入了一个血管内模拟环境，允许在可参数化的主动脉弓中进行导丝导航。
与前馈控制器相比，经过 29200 次干预后，递归控制器的导航成功率达到 75.0%，而经过 156800 次干预后，导航成功率为 71.6%。此外，递归控制器可以泛化到以前未见过的主动脉弓，并且对主动脉弓的大小变化具有鲁棒性。在 2048 个主动脉弓几何形状上进行训练可以得到与在 1000 个不同几何形状上进行完整变化训练时相同的结果。对于插值，可以成功导航 30%缩放范围的间隙，对于外推，可以成功导航另外 10%的缩放范围。
适应新的血管几何形状是血管内器械导航的关键。因此，对新血管几何形状的内在泛化是实现自主血管内机器人技术的重要步骤。
