Impact of deep learning image reconstruction on volumetric accuracy and image quality of pulmonary nodules with different morphologies in low-dose CT.

Journal: Cancer imaging : the official publication of the International Cancer Imaging Society
PMID: 38720391

Abstract

BACKGROUND: This study systematically compares the impact of innovative deep learning image reconstruction (DLIR, TrueFidelity) to conventionally used iterative reconstruction (IR) on nodule volumetry and subjective image quality (IQ) at highly reduced radiation doses. This is essential in the context of low-dose CT lung cancer screening where accurate volumetry and characterization of pulmonary nodules in repeated CT scanning are indispensable.

Authors

  • L D'hondt
    Department of Human structure and repair, Faculty of Medicine and Health Sciences, Ghent University, Proeftuinstraat 86, 9000, Ghent, Belgium. louisdho.dhondt@ugent.be.
  • C Franck
    Department of Radiology, University Hospital Antwerp, Drie Eikenstraat 655, 2650 Edegem, Belgium.
  • P-J Kellens
    Department of Human structure and repair, Faculty of Medicine and Health Sciences, Ghent University, Proeftuinstraat 86, 9000, Ghent, Belgium.
  • F Zanca
    Palindromo Consulting, W. de Croylaan, 51 3000 Leuven Belgium. Electronic address: Federica.Zanca@Palindromo.Consulting.
  • D Buytaert
    Cardiovascular Research Center, OLV Ziekenhuis Aalst, Moorselbaan 164, Aalst, Belgium.
  • A Van Hoyweghen
    Department of Radiology, University Hospital Antwerp, Drie Eikenstraat 655, 2650 Edegem, Belgium.
  • H El Addouli
    Department of Radiology, Antwerp University Hospital, Drie Eikenstraat 655, Edegem, Belgium.
  • K Carpentier
    Department of Radiology, Antwerp University Hospital, Drie Eikenstraat 655, Edegem, Belgium.
  • M Niekel
    Department of Radiology, Antwerp University Hospital, Drie Eikenstraat 655, Edegem, Belgium.
  • M Spinhoven
    Department of Radiology, University Hospital Antwerp, Drie Eikenstraat 655, 2650 Edegem, Belgium.
  • K Bacher
    Department of Human structure and repair, Faculty of Medicine and Health Sciences, Ghent University, Proeftuinstraat 86, 9000, Ghent, Belgium.
  • A Snoeckx
    Department of Radiology, University Hospital Antwerp, Drie Eikenstraat 655, 2650 Edegem, Belgium.

Keywords

External Resources

Popular Topics
Recent Journals