• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Liu, Jincheng (Liu, Jincheng.) | Li, Bao (Li, Bao.) | Yang, Yang (Yang, Yang.) | Huang, Suqin (Huang, Suqin.) | Sun, Hao (Sun, Hao.) | Liu, Jian (Liu, Jian.) | Liu, Youjun (Liu, Youjun.) (学者:刘有军)

收录:

EI Scopus SCIE

摘要:

The underuse of invasive fractional flow reserve (FFR) in clinical practice has motivated research towards noninvasive prediction of FFR. Although the non-invasive derivation of FFR (FFRCT) using computational fluid dynamics (CFD) principles has become a common practice, its clinical application has been limited due to the considerable time required for computation of resulting changes in haemodynamic conditions. An alternative to CFD technology is incorporating a neural network into the computational process to reduce the time necessary for running an effective model. In this study we propose a cascade of data -driven and physic -based neural networks (DP -NN) for predicting FFR (DL-FFRCT). The first network of cascade network DP -NN includes geometric features, and the second network includes physical features. We compare the differences between data -driven neural network (D -NN) and DP -NN for predicting FFR. The training and testing datasets were obtained by solving the three-dimensional incompressible Navier-Stokes equations. Coronary flow and geometric features were used as inputs to train D NN. In DP -NN the training process involves first training a D -NN to output resting Delta P as one input feature to the DP -NN. Secondly, the physics -based microcirculatory resistance as another input feature to the DP -NN. Using clinically measured FFR as the "gold standard", we validated the computational accuracy of DL-FFRCT in 77 patients. Compared to D -NN, DP -NN improved the prediction of Delta P (R2 = 0.87 vs. R2 = 0.92). Statistical analysis demonstrated that the diagnostic accuracy of DL-FFRCT was not inferior to FFRCT (85.71 % vs. 88.3 %) and the computational time was reduced by a factor of approximately 3000 (4.26 s vs. 3.5 h). DP -NN represents a near real-time, interpretable, and highly accurate deep -learning network, which contributes to the development of high-performance computational methods for haemodynamics. We anticipate that DP -NN will enable near real-time prediction of DL-FFRCT in personalized narrow blood vessels and provide guidance for cardiovascular disease treatments.

关键词:

Deep learning Computational FFR Coronary artery disease Cascade neural networks

作者机构:

  • [ 1 ] [Liu, Jincheng]Beijing Univ Technol, Coll Chem & Life Sci, Dept Biomed Engn, Beijing, Peoples R China
  • [ 2 ] [Li, Bao]Beijing Univ Technol, Coll Chem & Life Sci, Dept Biomed Engn, Beijing, Peoples R China
  • [ 3 ] [Yang, Yang]Beijing Univ Technol, Coll Chem & Life Sci, Dept Biomed Engn, Beijing, Peoples R China
  • [ 4 ] [Huang, Suqin]Beijing Univ Technol, Coll Chem & Life Sci, Dept Biomed Engn, Beijing, Peoples R China
  • [ 5 ] [Sun, Hao]Beijing Univ Technol, Coll Chem & Life Sci, Dept Biomed Engn, Beijing, Peoples R China
  • [ 6 ] [Liu, Youjun]Beijing Univ Technol, Coll Chem & Life Sci, Dept Biomed Engn, Beijing, Peoples R China
  • [ 7 ] [Liu, Jian]Peking Univ Peoples Hosp, Cardiovasc Dept, Beijing, Peoples R China
  • [ 8 ] [Liu, Youjun]Beijing Univ Technol, Coll Chem & Life Sci, Dept Biomed Engn, Beijing 100124, Peoples R China

通讯作者信息:

  • 刘有军

    [Liu, Youjun]Beijing Univ Technol, Coll Chem & Life Sci, Dept Biomed Engn, Beijing 100124, Peoples R China

电子邮件地址:

查看成果更多字段

相关关键词:

来源 :

COMPUTERS IN BIOLOGY AND MEDICINE

ISSN: 0010-4825

年份: 2024

卷: 169

7 . 7 0 0

JCR@2022

被引次数:

WoS核心集被引频次:

SCOPUS被引频次: 7

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 5

归属院系:

在线人数/总访问数:529/4956388
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司