Refining computer tomography data with super-resolution networks to increase the accuracy of respiratory flow simulations

Future Generation Computer Systems, vol. 159, pp. 474–488

Abstract

Accurately computing the flow in the nasal cavity with computational fluid dynamics (CFD) simulations requires highly resolved computational meshes based on anatomically realistic geometries. Such geometries can only be obtained from computer tomography (CT) data with high spatial resolution, i.e., featuring a ≤1mm slice thickness. In practice, CTs are, however, recorded at a lower resolution to not expose patients to high radiation and to reduce the overall costs. To overcome this problem and to provide patients with a detailed physics-based diagnosis, e.g., for surgery planning, the potential of super-resolution networks (SRNs) to increase the CT resolution is analyzed. Therefore, an SRN is developed and trained on CT data. Its predictive performance is improved by an automated hyperparameter optimization technique. The training time is further reduced without predictive accuracy degradation by oversampling images with challenging regions. The performance of the SRN is assessed by an analysis of the reconstructed 3D surfaces of the human upper airway and by comparing results of CFD simulations. That is, surfaces and simulation results based on SRN-generated CT data at 1mm resolution are compared to those obtained from unmodified CT data-sets at low (3mm) and high (1mm) resolution, as well as from CT data interpolated to a 1mm resolution from coarse data. The findings reveal the SRN-based approach to have the lowest deviations in the physics-based CFD results when compared to those based on the original high-resolution data. The pressure loss between the inflow (nostrils) and outflow (pharynx) regions averaged for three test patients differs by only 1.3%, compared to 8.7% and 8.8% in the coarse and interpolated cases. It is concluded that the SRN-based method is a promising tool to enhance underresolved CT data to yield reliable numerical results of respiratory flows.

Authors 10

1. Xin Liu corresponding

   Forschungszentrum Jülich · Jülich Supercomputing Centre

   Affiliation as printed

   Jülich Supercomputing Centre (JSC), Forschungszentrum Jülich GmbH, Germany

2. Mario Rüttgers corresponding Aachen Institute of Aerodynamics Chair of Fluid Mechanics

   Forschungszentrum Jülich · Jülich Aachen Research Alliance · Jülich Supercomputing Centre · RWTH Aachen University

   Affiliation as printed

   Institute of Aerodynamics and Chair of Fluid Mechanics (AIA), RWTH Aachen University, Germany

   Jülich Aachen Research Alliance - Center for Simulation and Data Science (JARA-CSD), Germany

   Jülich Supercomputing Centre (JSC), Forschungszentrum Jülich GmbH, Germany

3. Alessio Quercia

   Forschungszentrum Jülich

   Affiliation as printed

   Institute of Advanced Simulations 8 (IAS-8), Forschungszentrum Jülich GmbH, Germany

4. Romain Égelé

   Argonne National Laboratory · Université Paris-Saclay

   Affiliation as printed

   Argonne National Laboratory, United States of America

   Université Paris-Saclay, France

5. Elisabeth A. G. Pfaehler

   Forschungszentrum Jülich

   Affiliation as printed

   Institute of Advanced Simulations 8 (IAS-8), Forschungszentrum Jülich GmbH, Germany

6. Rushikesh Shende Aachen Institute of Aerodynamics Chair of Fluid Mechanics

   RWTH Aachen University

   Affiliation as printed

   Institute of Aerodynamics and Chair of Fluid Mechanics (AIA), RWTH Aachen University, Germany

7. Marcel Aach

   University of Iceland · Forschungszentrum Jülich · Jülich Supercomputing Centre

   Affiliation as printed

   Jülich Supercomputing Centre (JSC), Forschungszentrum Jülich GmbH, Germany

   School of Engineering and Natural Sciences, University of Iceland, Iceland

8. Wolfgang Schröder Aachen Institute of Aerodynamics Chair of Fluid Mechanics

   Jülich Aachen Research Alliance · RWTH Aachen University

   Affiliation as printed

   Institute of Aerodynamics and Chair of Fluid Mechanics (AIA), RWTH Aachen University, Germany

   Jülich Aachen Research Alliance - Center for Simulation and Data Science (JARA-CSD), Germany

9. Prasanna Balaprakash

   Argonne National Laboratory · Oak Ridge National Laboratory

   Affiliation as printed

   Argonne National Laboratory, United States of America

   Oak Ridge National Laboratory, United States of America

10. Andreas Lintermann

    Forschungszentrum Jülich · Jülich Aachen Research Alliance · Jülich Supercomputing Centre

    Affiliation as printed

    Jülich Aachen Research Alliance - Center for Simulation and Data Science (JARA-CSD), Germany

    Jülich Supercomputing Centre (JSC), Forschungszentrum Jülich GmbH, Germany