File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Low-count whole-body PET/MRI restoration: an evaluation of dose reduction spectrum and five state-of-the-art artificial intelligence models

TitleLow-count whole-body PET/MRI restoration: an evaluation of dose reduction spectrum and five state-of-the-art artificial intelligence models
Authors
KeywordsCNN
Deep learning
PET restoration
Transformer model
Whole-body PET imaging
Issue Date2023
Citation
European Journal of Nuclear Medicine and Molecular Imaging, 2023 How to Cite?
AbstractPurpose: To provide a holistic and complete comparison of the five most advanced AI models in the augmentation of low-dose 18F-FDG PET data over the entire dose reduction spectrum. Methods: In this multicenter study, five AI models were investigated for restoring low-count whole-body PET/MRI, covering convolutional benchmarks — U-Net, enhanced deep super-resolution network (EDSR), generative adversarial network (GAN) — and the most cutting-edge image reconstruction transformer models in computer vision to date — Swin transformer image restoration network (SwinIR) and EDSR-ViT (vision transformer). The models were evaluated against six groups of count levels representing the simulated 75%, 50%, 25%, 12.5%, 6.25%, and 1% (extremely ultra-low-count) of the clinical standard 3 MBq/kg 18F-FDG dose. The comparisons were performed upon two independent cohorts — (1) a primary cohort from Stanford University and (2) a cross-continental external validation cohort from Tübingen University — in order to ensure the findings are generalizable. A total of 476 original count and simulated low-count whole-body PET/MRI scans were incorporated into this analysis. Results: For low-count PET restoration on the primary cohort, the mean structural similarity index (SSIM) scores for dose 6.25% were 0.898 (95% CI, 0.887–0.910) for EDSR, 0.893 (0.881–0.905) for EDSR-ViT, 0.873 (0.859–0.887) for GAN, 0.885 (0.873–0.898) for U-Net, and 0.910 (0.900–0.920) for SwinIR. In continuation, SwinIR and U-Net’s performances were also discreetly evaluated at each simulated radiotracer dose levels. Using the primary Stanford cohort, the mean diagnostic image quality (DIQ; 5-point Likert scale) scores of SwinIR restoration were 5 (SD, 0) for dose 75%, 4.50 (0.535) for dose 50%, 3.75 (0.463) for dose 25%, 3.25 (0.463) for dose 12.5%, 4 (0.926) for dose 6.25%, and 2.5 (0.534) for dose 1%. Conclusion: Compared to low-count PET images, with near-to or nondiagnostic images at higher dose reduction levels (up to 6.25%), both SwinIR and U-Net significantly improve the diagnostic quality of PET images. A radiotracer dose reduction to 1% of the current clinical standard radiotracer dose is out of scope for current AI techniques.
Persistent Identifierhttp://hdl.handle.net/10722/325592
ISSN
2023 Impact Factor: 8.6
2023 SCImago Journal Rankings: 2.280
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorWang, Yan Ran (Joyce)-
dc.contributor.authorWang, Pengcheng-
dc.contributor.authorAdams, Lisa Christine-
dc.contributor.authorSheybani, Natasha Diba-
dc.contributor.authorQu, Liangqiong-
dc.contributor.authorSarrami, Amir Hossein-
dc.contributor.authorTheruvath, Ashok Joseph-
dc.contributor.authorGatidis, Sergios-
dc.contributor.authorHo, Tina-
dc.contributor.authorZhou, Quan-
dc.contributor.authorPribnow, Allison-
dc.contributor.authorThakor, Avnesh S.-
dc.contributor.authorRubin, Daniel-
dc.contributor.authorDaldrup-Link, Heike E.-
dc.date.accessioned2023-02-27T07:34:37Z-
dc.date.available2023-02-27T07:34:37Z-
dc.date.issued2023-
dc.identifier.citationEuropean Journal of Nuclear Medicine and Molecular Imaging, 2023-
dc.identifier.issn1619-7070-
dc.identifier.urihttp://hdl.handle.net/10722/325592-
dc.description.abstractPurpose: To provide a holistic and complete comparison of the five most advanced AI models in the augmentation of low-dose 18F-FDG PET data over the entire dose reduction spectrum. Methods: In this multicenter study, five AI models were investigated for restoring low-count whole-body PET/MRI, covering convolutional benchmarks — U-Net, enhanced deep super-resolution network (EDSR), generative adversarial network (GAN) — and the most cutting-edge image reconstruction transformer models in computer vision to date — Swin transformer image restoration network (SwinIR) and EDSR-ViT (vision transformer). The models were evaluated against six groups of count levels representing the simulated 75%, 50%, 25%, 12.5%, 6.25%, and 1% (extremely ultra-low-count) of the clinical standard 3 MBq/kg 18F-FDG dose. The comparisons were performed upon two independent cohorts — (1) a primary cohort from Stanford University and (2) a cross-continental external validation cohort from Tübingen University — in order to ensure the findings are generalizable. A total of 476 original count and simulated low-count whole-body PET/MRI scans were incorporated into this analysis. Results: For low-count PET restoration on the primary cohort, the mean structural similarity index (SSIM) scores for dose 6.25% were 0.898 (95% CI, 0.887–0.910) for EDSR, 0.893 (0.881–0.905) for EDSR-ViT, 0.873 (0.859–0.887) for GAN, 0.885 (0.873–0.898) for U-Net, and 0.910 (0.900–0.920) for SwinIR. In continuation, SwinIR and U-Net’s performances were also discreetly evaluated at each simulated radiotracer dose levels. Using the primary Stanford cohort, the mean diagnostic image quality (DIQ; 5-point Likert scale) scores of SwinIR restoration were 5 (SD, 0) for dose 75%, 4.50 (0.535) for dose 50%, 3.75 (0.463) for dose 25%, 3.25 (0.463) for dose 12.5%, 4 (0.926) for dose 6.25%, and 2.5 (0.534) for dose 1%. Conclusion: Compared to low-count PET images, with near-to or nondiagnostic images at higher dose reduction levels (up to 6.25%), both SwinIR and U-Net significantly improve the diagnostic quality of PET images. A radiotracer dose reduction to 1% of the current clinical standard radiotracer dose is out of scope for current AI techniques.-
dc.languageeng-
dc.relation.ispartofEuropean Journal of Nuclear Medicine and Molecular Imaging-
dc.subjectCNN-
dc.subjectDeep learning-
dc.subjectPET restoration-
dc.subjectTransformer model-
dc.subjectWhole-body PET imaging-
dc.titleLow-count whole-body PET/MRI restoration: an evaluation of dose reduction spectrum and five state-of-the-art artificial intelligence models-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1007/s00259-022-06097-w-
dc.identifier.pmid36633614-
dc.identifier.scopuseid_2-s2.0-85146174106-
dc.identifier.eissn1619-7089-
dc.identifier.isiWOS:000913086400001-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats