Simulating X-ray beam energy and detector signal processing of an industrial CT using implicit neural representations

Research output: Journal contributionsConference article in journalResearch

Standard

Simulating X-ray beam energy and detector signal processing of an industrial CT using implicit neural representations. / Blum, Edwin; Burmeister, Moritz; Stamer, Florian et al.
In: E-Journal of nondestructive testing, Vol. 30, No. 2, 19.02.2025.

Research output: Journal contributionsConference article in journalResearch

Harvard

APA

Vancouver

Bibtex

@article{d5e11319e73f48e5a43aa39f1bc55db5,
title = "Simulating X-ray beam energy and detector signal processing of an industrial CT using implicit neural representations",
abstract = "Simulating computed tomography (CT) systems offers numerous advantages, including the optimization of scan parameters, training of specialist personnel, and quantification of measurement uncertainties. Current simulation approaches, often referred to as virtual computed tomography (vCT), predominantly rely on analytical models. However, these models require extensive system-specific tuning to produce realistic synthetic measurements, creating a significant barrier to broader adoption and efficiency. To address this challenge, this work explores the potential of implicit neural representation (INR) as an alternative to the analytical models used in vCT. INRs excel at representing complex, high-dimensional data in a continuous and differentiable manner, making them a promising substitute for traditional analytical models. As a first building block, we propose a two-stage approach for simulating the X-ray beam energy and detector signal processing in industrial CT systems. This method is trained and evaluated using real-world data. Results demonstrate that the proposed INR-based architecture can accurately generate synthetic projections for parameter configurations within the training dataset. However, its poor performance on the test dataset highlights limitations in generalization beyond the training data. Potential methods to address these shortcomings are discussed.This study underscores the potential of INRs as a flexible framework for simulating complex CT systems. By capturing subtle system-specific characteristics and reducing dependence on explicitly defined parameterizations, INRs could pave the way formore versatile and efficient simulation models.",
keywords = "Engineering, Machine Learning, Simulation, vCT, Implicit Neural Representations",
author = "Edwin Blum and Moritz Burmeister and Florian Stamer and Gisela Lanza",
year = "2025",
month = feb,
day = "19",
doi = "10.58286/30752",
language = "English",
volume = "30",
journal = "E-Journal of nondestructive testing",
issn = "1435-4934",
publisher = "NDT.net",
number = "2",
note = "14th Conference on Industrial Computed Tomography - iCT 2025, ICT 2025 ; Conference date: 04-02-2025 Through 07-02-2025",

}

RIS

TY - JOUR

T1 - Simulating X-ray beam energy and detector signal processing of an industrial CT using implicit neural representations

AU - Blum, Edwin

AU - Burmeister, Moritz

AU - Stamer, Florian

AU - Lanza, Gisela

N1 - Conference code: 14

PY - 2025/2/19

Y1 - 2025/2/19

N2 - Simulating computed tomography (CT) systems offers numerous advantages, including the optimization of scan parameters, training of specialist personnel, and quantification of measurement uncertainties. Current simulation approaches, often referred to as virtual computed tomography (vCT), predominantly rely on analytical models. However, these models require extensive system-specific tuning to produce realistic synthetic measurements, creating a significant barrier to broader adoption and efficiency. To address this challenge, this work explores the potential of implicit neural representation (INR) as an alternative to the analytical models used in vCT. INRs excel at representing complex, high-dimensional data in a continuous and differentiable manner, making them a promising substitute for traditional analytical models. As a first building block, we propose a two-stage approach for simulating the X-ray beam energy and detector signal processing in industrial CT systems. This method is trained and evaluated using real-world data. Results demonstrate that the proposed INR-based architecture can accurately generate synthetic projections for parameter configurations within the training dataset. However, its poor performance on the test dataset highlights limitations in generalization beyond the training data. Potential methods to address these shortcomings are discussed.This study underscores the potential of INRs as a flexible framework for simulating complex CT systems. By capturing subtle system-specific characteristics and reducing dependence on explicitly defined parameterizations, INRs could pave the way formore versatile and efficient simulation models.

AB - Simulating computed tomography (CT) systems offers numerous advantages, including the optimization of scan parameters, training of specialist personnel, and quantification of measurement uncertainties. Current simulation approaches, often referred to as virtual computed tomography (vCT), predominantly rely on analytical models. However, these models require extensive system-specific tuning to produce realistic synthetic measurements, creating a significant barrier to broader adoption and efficiency. To address this challenge, this work explores the potential of implicit neural representation (INR) as an alternative to the analytical models used in vCT. INRs excel at representing complex, high-dimensional data in a continuous and differentiable manner, making them a promising substitute for traditional analytical models. As a first building block, we propose a two-stage approach for simulating the X-ray beam energy and detector signal processing in industrial CT systems. This method is trained and evaluated using real-world data. Results demonstrate that the proposed INR-based architecture can accurately generate synthetic projections for parameter configurations within the training dataset. However, its poor performance on the test dataset highlights limitations in generalization beyond the training data. Potential methods to address these shortcomings are discussed.This study underscores the potential of INRs as a flexible framework for simulating complex CT systems. By capturing subtle system-specific characteristics and reducing dependence on explicitly defined parameterizations, INRs could pave the way formore versatile and efficient simulation models.

KW - Engineering

KW - Machine Learning

KW - Simulation

KW - vCT

KW - Implicit Neural Representations

U2 - 10.58286/30752

DO - 10.58286/30752

M3 - Conference article in journal

VL - 30

JO - E-Journal of nondestructive testing

JF - E-Journal of nondestructive testing

SN - 1435-4934

IS - 2

T2 - 14th Conference on Industrial Computed Tomography - iCT 2025

Y2 - 4 February 2025 through 7 February 2025

ER -

DOI

Recently viewed

Researchers

  1. Timo Janca

Publications

  1. Control of an Electromagnetic Linear Actuator Using Flatness Property and Systems Inversion
  2. Comments on "Tracking Control of Robotic Manipulators With Uncertain Kinematics and Dynamics"
  3. A Study on the Performance of Adaptive Neural Networks for Haze Reduction with a Focus on Precision
  4. Optimization of 3D laser scanning speed by use of combined variable step
  5. Effects of diversity versus segregation on automatic approach and avoidance behavior towards own and other ethnic groups
  6. Different facets of tree sapling diversity influence browsing intensity by deer dependent on spatial scale
  7. The role of task meaning on output in groups
  8. Dynamic capabilities and routinization
  9. Scaffolding Learner Agency in Technology-Enhanced Language Learning Environments
  10. Comparing Web-Based and Blended Training for Coping With Challenges of Flexible Work Designs
  11. Continental mapping of forest ecosystem functions reveals a high but unrealised potential for forest multifunctionality.
  12. End-to-End Active Speaker Detection
  13. Fermentative utilization of coffee mucilage using Bacillus coagulans and investigation of down-stream processing of fermentation broth for optically pure L(+)-lactic acid production
  14. Planar Multipole Resonance Probe: A kinetic model based on a functional analytic description
  15. Timing matters: Distinct effects of nitrogen and phosphorus fertilizer application timing on root system architecture responses
  16. Dealing with inclusion–teachers’ assessment of internal and external resources
  17. Reconfigurable Control System for Plants with Variable Structure
  18. Possible underestimations of risks for the environment due to unregulated emissions of biocides from households to wastewater
  19. Reconciling conservation and development in protected areas of the Global South
  20. Modelling scenarios to identify a combined sediment-water management strategy for the large reservoirs of the Tuyamuyun hydro-complex
  21. Identifying determinants of teachers' judgment (in)accuracy regarding students' school-related motivations using a Bayesian cross-classified multi-level model
  22. Design rules for environmental biodegradability of phenylalanine alkyl ester linked ionic liquids
  23. Empirical research on mathematical modelling
  24. Assessing the costs and cost-effectiveness of ICare internet-based interventions (protocol)
  25. Higher Wages in Exporting Firms
  26. From GUI to No-UI
  27. Model of mobility demands for future short distance public transport systems
  28. Material utilization of organic residues
  29. Demarcating transdisciplinary research in sustainability science—Five clusters of research modes based on evidence from 59 research projects
  30. Brennball
  31. Energy-aware system design for autonomous wireless sensor nodes
  32. Third International Mathematics and Science Study and Trends in Mathematics and Science Studies (TIMSS)
  33. Development of a magnesium secondary alloy system for mixed magnesium post-consumer scrap