基于高效八叉树深度学习模型的瞬态血流动力学预测

Noah Maul, Katharina Zinn, Fabian Wagner, Mareike Thies, M. Rohleder, Laura Pfaff, M. Kowarschik, A. Birkhold, Andreas K. Maier
{"title":"基于高效八叉树深度学习模型的瞬态血流动力学预测","authors":"Noah Maul, Katharina Zinn, Fabian Wagner, Mareike Thies, M. Rohleder, Laura Pfaff, M. Kowarschik, A. Birkhold, Andreas K. Maier","doi":"10.48550/arXiv.2302.06557","DOIUrl":null,"url":null,"abstract":"Patient-specific hemodynamics assessment could support diagnosis and treatment of neurovascular diseases. Currently, conventional medical imaging modalities are not able to accurately acquire high-resolution hemodynamic information that would be required to assess complex neurovascular pathologies. Therefore, computational fluid dynamics (CFD) simulations can be applied to tomographic reconstructions to obtain clinically relevant information. However, three-dimensional (3D) CFD simulations require enormous computational resources and simulation-related expert knowledge that are usually not available in clinical environments. Recently, deep-learning-based methods have been proposed as CFD surrogates to improve computational efficiency. Nevertheless, the prediction of high-resolution transient CFD simulations for complex vascular geometries poses a challenge to conventional deep learning models. In this work, we present an architecture that is tailored to predict high-resolution (spatial and temporal) velocity fields for complex synthetic vascular geometries. For this, an octree-based spatial discretization is combined with an implicit neural function representation to efficiently handle the prediction of the 3D velocity field for each time step. The presented method is evaluated for the task of cerebral hemodynamics prediction before and during the injection of contrast agent in the internal carotid artery (ICA). Compared to CFD simulations, the velocity field can be estimated with a mean absolute error of 0.024 m/s, whereas the run time reduces from several hours on a high-performance cluster to a few seconds on a consumer graphical processing unit.","PeriodicalId":73379,"journal":{"name":"Information processing in medical imaging : proceedings of the ... conference","volume":"3 1","pages":"183-194"},"PeriodicalIF":0.0000,"publicationDate":"2023-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Transient Hemodynamics Prediction Using an Efficient Octree-Based Deep Learning Model\",\"authors\":\"Noah Maul, Katharina Zinn, Fabian Wagner, Mareike Thies, M. Rohleder, Laura Pfaff, M. Kowarschik, A. Birkhold, Andreas K. Maier\",\"doi\":\"10.48550/arXiv.2302.06557\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Patient-specific hemodynamics assessment could support diagnosis and treatment of neurovascular diseases. Currently, conventional medical imaging modalities are not able to accurately acquire high-resolution hemodynamic information that would be required to assess complex neurovascular pathologies. Therefore, computational fluid dynamics (CFD) simulations can be applied to tomographic reconstructions to obtain clinically relevant information. However, three-dimensional (3D) CFD simulations require enormous computational resources and simulation-related expert knowledge that are usually not available in clinical environments. Recently, deep-learning-based methods have been proposed as CFD surrogates to improve computational efficiency. Nevertheless, the prediction of high-resolution transient CFD simulations for complex vascular geometries poses a challenge to conventional deep learning models. In this work, we present an architecture that is tailored to predict high-resolution (spatial and temporal) velocity fields for complex synthetic vascular geometries. For this, an octree-based spatial discretization is combined with an implicit neural function representation to efficiently handle the prediction of the 3D velocity field for each time step. The presented method is evaluated for the task of cerebral hemodynamics prediction before and during the injection of contrast agent in the internal carotid artery (ICA). Compared to CFD simulations, the velocity field can be estimated with a mean absolute error of 0.024 m/s, whereas the run time reduces from several hours on a high-performance cluster to a few seconds on a consumer graphical processing unit.\",\"PeriodicalId\":73379,\"journal\":{\"name\":\"Information processing in medical imaging : proceedings of the ... conference\",\"volume\":\"3 1\",\"pages\":\"183-194\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-02-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Information processing in medical imaging : proceedings of the ... conference\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2302.06557\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Information processing in medical imaging : proceedings of the ... conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2302.06557","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

患者特异性血流动力学评估可以支持神经血管疾病的诊断和治疗。目前,传统的医学成像方式不能准确地获得高分辨率的血流动力学信息,这将需要评估复杂的神经血管病变。因此,计算流体动力学(CFD)模拟可以应用于层析重建,以获得临床相关信息。然而,三维(3D) CFD模拟需要大量的计算资源和与模拟相关的专家知识,这些通常在临床环境中无法获得。近年来,人们提出了基于深度学习的CFD替代方法来提高计算效率。然而,复杂血管几何形状的高分辨率瞬态CFD模拟预测对传统的深度学习模型提出了挑战。在这项工作中,我们提出了一个专门用于预测复杂合成血管几何形状的高分辨率(空间和时间)速度场的架构。为此,将基于八叉树的空间离散化与隐式神经函数表示相结合,有效地处理每个时间步长的三维速度场预测。评价了该方法在颈内动脉注射造影剂前和注射过程中的脑血流动力学预测任务。与CFD模拟相比,速度场的估计平均绝对误差为0.024 m/s,而运行时间从高性能集群上的几个小时减少到消费者图形处理单元上的几秒钟。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Transient Hemodynamics Prediction Using an Efficient Octree-Based Deep Learning Model
Patient-specific hemodynamics assessment could support diagnosis and treatment of neurovascular diseases. Currently, conventional medical imaging modalities are not able to accurately acquire high-resolution hemodynamic information that would be required to assess complex neurovascular pathologies. Therefore, computational fluid dynamics (CFD) simulations can be applied to tomographic reconstructions to obtain clinically relevant information. However, three-dimensional (3D) CFD simulations require enormous computational resources and simulation-related expert knowledge that are usually not available in clinical environments. Recently, deep-learning-based methods have been proposed as CFD surrogates to improve computational efficiency. Nevertheless, the prediction of high-resolution transient CFD simulations for complex vascular geometries poses a challenge to conventional deep learning models. In this work, we present an architecture that is tailored to predict high-resolution (spatial and temporal) velocity fields for complex synthetic vascular geometries. For this, an octree-based spatial discretization is combined with an implicit neural function representation to efficiently handle the prediction of the 3D velocity field for each time step. The presented method is evaluated for the task of cerebral hemodynamics prediction before and during the injection of contrast agent in the internal carotid artery (ICA). Compared to CFD simulations, the velocity field can be estimated with a mean absolute error of 0.024 m/s, whereas the run time reduces from several hours on a high-performance cluster to a few seconds on a consumer graphical processing unit.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信