编织支架展开模拟的机器学习和降阶建模
Machine learning and reduced order modelling for the simulation of braided stent deployment
摘要:
使用血流导向装置的腔内重建代表了颅内动脉瘤微创治疗的新范例。一旦在载瘤血管内展开,这些非常致密的编织支架所呈现的构型就不容易预测,并且单独的医学体积图像可能不足以令人满意地规划治疗。因此,在这里,我们提出了一个快速,准确的机器学习和降阶建模框架,有限元模拟的基础上,以协助从业人员在规划和干预阶段。它包括第一个分类步骤,以从临床角度先验确定模拟是否成功(支架和血管之间的良好贴合性),然后是回归步骤,提供展开支架配置的近似解。后者是使用一个非侵入性的降阶建模方案,结合适当的正交分解算法和高斯过程回归。在理想化的颅内动脉囊状动脉瘤上验证了工作流程,并研究了6个几何和手术参数对支架展开结局的影响。两步工作流程允许以高达95%的准确度对展开条件进行分类,并实时预测支架展开配置,平均预测误差不大于3D旋转血管造影的空间分辨率(0.15 mm)。这些结果是有希望的,因为它们证明了这些技术能够在几毫秒内实现模拟,同时保持支架展开配置的机械真实性和可预测性。
英文摘要:
Endoluminal reconstruction using flow diverters represents a novel paradigm for the minimally invasive treatment of intracranial aneurysms. The configuration assumed by these very dense braided stents once deployed within the parent vessel is not easily predictable and medical volumetric images alone may be insufficient to plan the treatment satisfactorily. Therefore, here we propose a fast and accurate machine learning and reduced order modelling framework, based on finite element simulations, to assist practitioners in the planning and interventional stages. It consists of a first classification step to determine a priori whether a simulation will be successful (good conformity between stent and vessel) or not from a clinical perspective, followed by a regression step that provides an approximated solution of the deployed stent configuration. The latter is achieved using a non-intrusive reduced order modelling scheme that combines the proper orthogonal decomposition algorithm and Gaussian process regression. The workflow was validated on an idealised intracranial artery with a saccular aneurysm and the effect of six geometrical and surgical parameters on the outcome of stent deployment was studied. The two-step workflow allows the classification of deployment conditions with up to 95% accuracy and real-time prediction of the stent deployed configuration with an average prediction error never greater than the spatial resolution of 3D rotational angiography (0.15 mm). These results are promising as they demonstrate the ability of these techniques to achieve simulations within a few milliseconds while retaining the mechanical realism and predictability of the stent deployed configuration.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。