Deep learning image enhancement algorithms in PET/CT imaging: a phantom and sarcoma patient radiomic evaluation.

Authors

Bonney LM,Kalisvaart GM,van Velden FHP,Bradley KM,Hassan AB,Grootjans W,McGowan DR

Affiliations (8)

  • Sir William Dunn School of Pathology, University of Oxford, Oxford, UK. [email protected].
  • Department of Medical Physics and Clinical Engineering, Oxford University Hospitals NHS Foundation Trust, Oxford, UK. [email protected].
  • Sir William Dunn School of Pathology, University of Oxford, Oxford, UK.
  • Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands.
  • Wales Research and Diagnostic PET Imaging Centre, University of Cardiff, Cardiff, UK.
  • Oncology and Haematology, Oxford University Hospitals NHS Foundation Trust, Oxford, UK.
  • Department of Medical Physics and Clinical Engineering, Oxford University Hospitals NHS Foundation Trust, Oxford, UK.
  • Department of Oncology, University of Oxford, Oxford, UK.

Abstract

PET/CT imaging data contains a wealth of quantitative information that can provide valuable contributions to characterising tumours. A growing body of work focuses on the use of deep-learning (DL) techniques for denoising PET data. These models are clinically evaluated prior to use, however, quantitative image assessment provides potential for further evaluation. This work uses radiomic features to compare two manufacturer deep-learning (DL) image enhancement algorithms, one of which has been commercialised, against 'gold-standard' image reconstruction techniques in phantom data and a sarcoma patient data set (N=20). All studies in the retrospective sarcoma clinical [ <math xmlns="http://www.w3.org/1998/Math/MathML"><mmultiscripts><mrow></mrow> <mrow></mrow> <mn>18</mn></mmultiscripts> </math> F]FDG dataset were acquired on either a GE Discovery 690 or 710 PET/CT scanner with volumes segmented by an experienced nuclear medicine radiologist. The modular heterogeneous imaging phantom used in this work was filled with [ <math xmlns="http://www.w3.org/1998/Math/MathML"><mmultiscripts><mrow></mrow> <mrow></mrow> <mn>18</mn></mmultiscripts> </math> F]FDG, and five repeat acquisitions of the phantom were acquired on a GE Discovery 710 PET/CT scanner. The DL-enhanced images were compared to 'gold-standard' images the algorithms were trained to emulate and input images. The difference between image sets was tested for significance in 93 international biomarker standardisation initiative (IBSI) standardised radiomic features. Comparing DL-enhanced images to the 'gold-standard', 4.0% and 9.7% radiomic features measured significantly different (p<sub>critical</sub> < 0.0005) in the phantom and patient data respectively (averaged over the two DL algorithms). Larger differences were observed comparing DL-enhanced images to algorithm input images with 29.8% and 43.0% of radiomic features measuring significantly different in the phantom and patient data respectively (averaged over the two DL algorithms). DL-enhanced images were found to be similar to images generated using the 'gold-standard' target image reconstruction method with more than 80% of radiomic features not significantly different in all comparisons across unseen phantom and sarcoma patient data. This result offers insight into the performance of the DL algorithms, and demonstrate potential applications for DL algorithms in harmonisation for radiomics and for radiomic features in quantitative evaluation of DL algorithms.

Topics

Positron Emission Tomography Computed TomographyDeep LearningPhantoms, ImagingSarcomaImage EnhancementAlgorithmsJournal Article

Ready to Sharpen Your Edge?

Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.