Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 7-Day Trial for You or Your Team.

Learn More →

Numerical prediction of ureter stone size using an integrated CFD-ML approach

Numerical prediction of ureter stone size using an integrated CFD-ML approach Ureteral flow parameters provide significant details about its physical attributes. Ureter is a single transport medium for urine transmission from kidney to ureter and its health is very important for a healthy human body. Understanding the fluid flow behavior can contribute toward the ureter health monitoring including estimation of any kind of blockage in the flow. Using ANSYS Fluent, Computational Fluid Dynamics (CFD) analysis and the grid independence study are carried out through iterative simulation process to achieve the solution independence. The CFD modeling provides tools and techniques to observe varying fluid parameters such as pressure, velocity and effect of the flow on smooth walls. Fluid Structure Interaction (FSI), an effective technique to analyze the effects of such flows on the ureter walls is also employed. Although the exact modeling of the ureter wall is not possible due to its complex physical parameters, some of its available physiological properties can be used to visualize the model of the ureter numerically. The present study is intended to predict the ureter stone size by using the FSI analysis. The simulations are carried out by increasing the stone size gradually from 1.7 to 3.4 mm and the input flow parameters are compared with the output flow parameters within the same solution setup and boundary conditions via artificial neural network in MATLAB. The output results obtained from the FSI simulations are then utilized to generate a prediction model for the ureter stone size. It is observed that the increasing stone size has a significant effect on the ureter wall, causing high stress regions in the point of interaction. The findings also revealed that the predicted size of the ureter stone is the closest to the actual size and with the least mean squared error at 80 optimal neurons. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Neural Computing and Applications Springer Journals

Numerical prediction of ureter stone size using an integrated CFD-ML approach

Download PDF
17 pages

Loading next page...
 
/lp/springer-journals/numerical-prediction-of-ureter-stone-size-using-an-integrated-cfd-ml-cNm9oTzEVs

References (31)

Publisher
Springer Journals
Copyright
Copyright © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024
ISSN
0941-0643
eISSN
1433-3058
DOI
10.1007/s00521-024-10880-1
Publisher site
See Article on Publisher Site

Abstract

Ureteral flow parameters provide significant details about its physical attributes. Ureter is a single transport medium for urine transmission from kidney to ureter and its health is very important for a healthy human body. Understanding the fluid flow behavior can contribute toward the ureter health monitoring including estimation of any kind of blockage in the flow. Using ANSYS Fluent, Computational Fluid Dynamics (CFD) analysis and the grid independence study are carried out through iterative simulation process to achieve the solution independence. The CFD modeling provides tools and techniques to observe varying fluid parameters such as pressure, velocity and effect of the flow on smooth walls. Fluid Structure Interaction (FSI), an effective technique to analyze the effects of such flows on the ureter walls is also employed. Although the exact modeling of the ureter wall is not possible due to its complex physical parameters, some of its available physiological properties can be used to visualize the model of the ureter numerically. The present study is intended to predict the ureter stone size by using the FSI analysis. The simulations are carried out by increasing the stone size gradually from 1.7 to 3.4 mm and the input flow parameters are compared with the output flow parameters within the same solution setup and boundary conditions via artificial neural network in MATLAB. The output results obtained from the FSI simulations are then utilized to generate a prediction model for the ureter stone size. It is observed that the increasing stone size has a significant effect on the ureter wall, causing high stress regions in the point of interaction. The findings also revealed that the predicted size of the ureter stone is the closest to the actual size and with the least mean squared error at 80 optimal neurons.

Journal

Neural Computing and Applications – Springer Journals

Published: Mar 1, 2025

Keywords: Computational fluid dynamic; Fluid structure interaction; Artificial neural network; Ureter stone size

There are no references for this article.