Quantitative image quality metrics enable resource-efficient quality control of clinically applied AI-based reconstructions in MRI.

Journal: Magma (New York, N.Y.)
Published Date:

Abstract

OBJECTIVE: AI-based MRI reconstruction techniques improve efficiency by reducing acquisition times whilst maintaining or improving image quality. Recent recommendations from professional bodies suggest centres should perform quality assessments on AI tools. However, monitoring long-term performance presents challenges, due to model drift or system updates. Radiologist-based assessments are resource-intensive and may be subjective, highlighting the need for efficient quality control (QC) measures. This study explores using image quality metrics (IQMs) to assess AI-based reconstructions.

Authors

  • Owen A White
    MRI Unit, The Royal Marsden NHS Foundation Trust, London, UK. owen.white@rmh.nhs.uk.
  • Joshua Shur
    Department of Radiology, Royal Marsden Hospital, London, UK.
  • Francesca Castagnoli
    Department of Radiology, Royal Marsden Hospital, London, UK. francesca.castagnoli@rmh.nhs.uk.
  • Geoff Charles-Edwards
    MRI Unit, The Royal Marsden NHS Foundation Trust, London, UK.
  • Brandon Whitcher
    Research Centre for Optimal Health, School of Life Sciences, University of Westminster, London, United Kingdom.
  • David J Collins
    MRI Unit, The Royal Marsden NHS Foundation Trust, London, UK.
  • Matthew T D Cashmore
    National Physical Laboratory, Teddington, UK.
  • Matt G Hall
    Institute of Child Health, University College London, London, UK.
  • Spencer A Thomas
    National Physical Laboratory, UK.
  • Andrew Thompson
    Beaumont Artificial Intelligence Research Laboratory, Beaumont Health Systems, Royal Oak, MI, USA.
  • Ciara A Harrison
    MRI Unit, The Royal Marsden NHS Foundation Trust, London, UK.
  • Georgina Hopkinson
    Department of Radiology, Royal Marsden Hospital, London, UK.
  • Dow-Mu Koh
    Department of Radiology, Royal Marsden Hospital, Sutton, UK.
  • Jessica M Winfield
    MRI Unit, The Royal Marsden NHS Foundation Trust, London, UK.

Keywords

No keywords available for this article.