Publication result detail

Machine Learning Based Scatter Correction for Industrial Computed Tomography

SUPPES, A.; MAYER, T.; ROTHE, N.; MAŠINSKÝ, P.; ŘEHÁK, I.; PETŘÍK, M.; BLAŽEK, P.; ZIKMUND, T.; KAISER, J.

Original Title

Machine Learning Based Scatter Correction for Industrial Computed Tomography

English Title

Machine Learning Based Scatter Correction for Industrial Computed Tomography

Type

Paper in proceedings outside WoS and Scopus

Original Abstract

Industrial X-ray computed tomography (CT) is a critical tool for non-destructive testing and quality control in various industries. However, scatter radiation remains a significant challenge, degrading image quality and limiting the evaluation accuracy of CT scans, especially for dense parts at higher X-ray energies, such as 450 kV. This study presents a comprehensive evaluation of traditional CT image improvement methods and introduces a novel machine learning-based approach for scatter correction to enhance image quality in industrial X-ray CT. To test the methods, we conduct an application study on a real-world part that compares the results from scans with a 300 kV micro-focus X-ray tube and a 450 kV meso-focus X-ray tube. The image quality, scanning speed, and total cost of ownership are compared.

English abstract

Industrial X-ray computed tomography (CT) is a critical tool for non-destructive testing and quality control in various industries. However, scatter radiation remains a significant challenge, degrading image quality and limiting the evaluation accuracy of CT scans, especially for dense parts at higher X-ray energies, such as 450 kV. This study presents a comprehensive evaluation of traditional CT image improvement methods and introduces a novel machine learning-based approach for scatter correction to enhance image quality in industrial X-ray CT. To test the methods, we conduct an application study on a real-world part that compares the results from scans with a 300 kV micro-focus X-ray tube and a 450 kV meso-focus X-ray tube. The image quality, scanning speed, and total cost of ownership are compared.

Keywords

Industrial computed tomography, X-ray, Scatter correction, Machine Learning, Digital Twin

Key words in English

Industrial computed tomography, X-ray, Scatter correction, Machine Learning, Digital Twin

Authors

SUPPES, A.; MAYER, T.; ROTHE, N.; MAŠINSKÝ, P.; ŘEHÁK, I.; PETŘÍK, M.; BLAŽEK, P.; ZIKMUND, T.; KAISER, J.

RIV year

2026

Released

01.08.2025

Publisher

ndt.net

Location

Paris, France

Pages from

1

Pages to

2

Pages count

2

URL

https://www.ndt.net/search/docs.php3?id=31427

BibTex

@inproceedings{BUT201159,
  author="Alexander {Suppes} and  {} and  {} and Petr {Mašinský} and Ivo {Řehák} and Michal {Petřík} and Pavel {Blažek} and Tomáš {Zikmund} and Jozef {Kaiser}",
  title="Machine Learning Based Scatter Correction for Industrial Computed Tomography",
  year="2025",
  pages="2",
  publisher="ndt.net",
  address="Paris, France",
  url="https://www.ndt.net/search/docs.php3?id=31427"
}