Shape-driven deep neural networks for fast acquisition of aortic 3D pressure and velocity flow fields.
Shape-driven deep neural networks for fast acquisition of aortic 3D pressure and velocity flow fields.
复制标题
DOI：
10.1371/journal.pcbi.1011055
复制
发表时间：
2023-04
影响因子：
4.3
通讯作者：
中科院分区：
文献类型：
--
作者：
计算流体动力学（CFD）可用于模拟血管血液动力学和分析潜在的治疗方案。CFD已被证明有利于改善患者的预后。然而，CFD在常规临床应用中的实施尚未实现。CFD的障碍包括高计算资源、设计模拟设置所需的专家经验以及长处理时间。本研究的目的是探索使用机器学习（ML），通过自动和快速回归模型复制传统主动脉CFD。用于训练/测试模型的数据包括对合成生成的3D主动脉形状进行的3，000次CFD模拟。这些受试者是根据建立在真实的患者特异性动脉瘤上的统计形状模型（SSM）生成的（N = 67）。对200个测试形状进行推断，压力和速度的平均误差分别为6.01% ±3.12 SD和3.99% ±0.93 SD。我们基于ML的模型在10.075秒内执行CFD（比求解器快4，000倍）。这项概念验证研究表明，传统血管CFD的结果可以使用ML以更快的速度、自动化过程和合理的准确度再现。在儿科疾病（即先天性心脏病）的临床管理中，“何时”和“如何”进行干预的指征往往不清楚。已经发现，诸如计算流体动力学（CFD）模拟的血液动力学建模工具在帮助临床医生和外科医生更好地了解患者状况并确定任何潜在的风险因素方面是有用的。虽然该工具在研究能力方面仍然很有用，但其与临床环境的分离是一个持续的障碍，阻碍了CFD在医疗保健中的全面采用。由于运行模拟需要大量的时间、计算和人力资源，将CFD转化为临床是一个持续的挑战。应用机器学习（ML）探索将传统CFD转换为临床适用模型的潜在方法是最近的一个现象，正在获得显着的势头。
Computational fluid dynamics (CFD) can be used to simulate vascular haemodynamics and analyse potential treatment options. CFD has shown to be beneficial in improving patient outcomes. However, the implementation of CFD for routine clinical use is yet to be realised. Barriers for CFD include high computational resources, specialist experience needed for designing simulation set-ups, and long processing times. The aim of this study was to explore the use of machine learning (ML) to replicate conventional aortic CFD with automatic and fast regression models. Data used to train/test the model consisted of 3,000 CFD simulations performed on synthetically generated 3D aortic shapes. These subjects were generated from a statistical shape model (SSM) built on real patient-specific aortas (N = 67). Inference performed on 200 test shapes resulted in average errors of 6.01% ±3.12 SD and 3.99% ±0.93 SD for pressure and velocity, respectively. Our ML-based models performed CFD in ∼0.075 seconds (4,000x faster than the solver). This proof-of-concept study shows that results from conventional vascular CFD can be reproduced using ML at a much faster rate, in an automatic process, and with reasonable accuracy. In the clinical management of pediatric disease (namely congenital heart defects), the indications for ‘when’ and ‘how’ to intervene are often unclear. It has been found that haemodynamic modelling tools such as computational fluid dynamics (CFD) simulations are useful in assisting clinicians and surgeons to better understand patient conditions and establish any potential risk factors. While this tool remains useful in a research capacity, its separation from clinical settings is an ongoing hindrance which prevents the full adoption of CFD in healthcare. The translation of CFD towards clinics is a continuous challenge, due to large time, computational and human resource requirements for running simulations. The application of machine learning (ML) for exploring potential methods to transform conventional CFD into clinically-suitable models is a recent phenomenon which is gaining significant momentum.
登录
查看更多内容
DOI：
10.1136/heartjnl-2015-308044
发表时间：
2016-01
期刊：
Heart (British Cardiac Society)
影响因子：
--
作者：
Morris PD;Narracott A;von Tengg-Kobligk H;Silva Soto DA;Hsiao S;Lungu A;Evans P;Bressloff NW;Lawford PV;Hose DR;Gunn JP
通讯作者：
Gunn JP
影响因子：
8.3
作者：
Lee, Sang-Wook;Antiga, Luca;Steinman, David A.
通讯作者：
Steinman, David A.
影响因子：
2.4
作者：
Morbiducci, Umberto;Ponzini, Raffaele;Rizzo, Giovanna
通讯作者：
Rizzo, Giovanna
DOI：
10.1002/cnm.3387
发表时间：
2020-10
影响因子：
2.1
作者：
Hoeijmakers MJMM;Waechter-Stehle I;Weese J;Van de Vosse FN
通讯作者：
Van de Vosse FN
DOI：
10.1186/s12968-022-00891-z
发表时间：
2022-11-07
期刊：
Journal of cardiovascular magnetic resonance : official journal of the Society for Cardiovascular Magnetic Resonance
影响因子：
--
作者：
通讯作者：
--