Cargando…

A deep learning-based whole-body solution for PET/MRI attenuation correction

BACKGROUND: Deep convolutional neural networks have demonstrated robust and reliable PET attenuation correction (AC) as an alternative to conventional AC methods in integrated PET/MRI systems. However, its whole-body implementation is still challenging due to anatomical variations and the limited MR...

Descripción completa

Detalles Bibliográficos
Autores principales: Ahangari, Sahar, Beck Olin, Anders, Kinggård Federspiel, Marianne, Jakoby, Bjoern, Andersen, Thomas Lund, Hansen, Adam Espe, Fischer, Barbara Malene, Littrup Andersen, Flemming
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer International Publishing 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9385907/
https://www.ncbi.nlm.nih.gov/pubmed/35978211
http://dx.doi.org/10.1186/s40658-022-00486-8
_version_ 1784769687907729408
author Ahangari, Sahar
Beck Olin, Anders
Kinggård Federspiel, Marianne
Jakoby, Bjoern
Andersen, Thomas Lund
Hansen, Adam Espe
Fischer, Barbara Malene
Littrup Andersen, Flemming
author_facet Ahangari, Sahar
Beck Olin, Anders
Kinggård Federspiel, Marianne
Jakoby, Bjoern
Andersen, Thomas Lund
Hansen, Adam Espe
Fischer, Barbara Malene
Littrup Andersen, Flemming
author_sort Ahangari, Sahar
collection PubMed
description BACKGROUND: Deep convolutional neural networks have demonstrated robust and reliable PET attenuation correction (AC) as an alternative to conventional AC methods in integrated PET/MRI systems. However, its whole-body implementation is still challenging due to anatomical variations and the limited MRI field of view. The aim of this study is to investigate a deep learning (DL) method to generate voxel-based synthetic CT (sCT) from Dixon MRI and use it as a whole-body solution for PET AC in a PET/MRI system. MATERIALS AND METHODS: Fifteen patients underwent PET/CT followed by PET/MRI with whole-body coverage from skull to feet. We performed MRI truncation correction and employed co-registered MRI and CT images for training and leave-one-out cross-validation. The network was pretrained with region-specific images. The accuracy of the AC maps and reconstructed PET images were assessed by performing a voxel-wise analysis and calculating the quantification error in SUV obtained using DL-based sCT (PET(sCT)) and a vendor-provided atlas-based method (PET(Atlas)), with the CT-based reconstruction (PET(CT)) serving as the reference. In addition, region-specific analysis was performed to compare the performances of the methods in brain, lung, liver, spine, pelvic bone, and aorta. RESULTS: Our DL-based method resulted in better estimates of AC maps with a mean absolute error of 62 HU, compared to 109 HU for the atlas-based method. We found an excellent voxel-by-voxel correlation between PET(CT) and PET(sCT) (R(2) = 0.98). The absolute percentage difference in PET quantification for the entire image was 6.1% for PET(sCT) and 11.2% for PET(Atlas). The regional analysis showed that the average errors and the variability for PET(sCT) were lower than PET(Atlas) in all regions. The largest errors were observed in the lung, while the smallest biases were observed in the brain and liver. CONCLUSIONS: Experimental results demonstrated that a DL approach for whole-body PET AC in PET/MRI is feasible and allows for more accurate results compared with conventional methods. Further evaluation using a larger training cohort is required for more accurate and robust performance. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1186/s40658-022-00486-8.
format Online
Article
Text
id pubmed-9385907
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Springer International Publishing
record_format MEDLINE/PubMed
spelling pubmed-93859072022-08-19 A deep learning-based whole-body solution for PET/MRI attenuation correction Ahangari, Sahar Beck Olin, Anders Kinggård Federspiel, Marianne Jakoby, Bjoern Andersen, Thomas Lund Hansen, Adam Espe Fischer, Barbara Malene Littrup Andersen, Flemming EJNMMI Phys Original Research BACKGROUND: Deep convolutional neural networks have demonstrated robust and reliable PET attenuation correction (AC) as an alternative to conventional AC methods in integrated PET/MRI systems. However, its whole-body implementation is still challenging due to anatomical variations and the limited MRI field of view. The aim of this study is to investigate a deep learning (DL) method to generate voxel-based synthetic CT (sCT) from Dixon MRI and use it as a whole-body solution for PET AC in a PET/MRI system. MATERIALS AND METHODS: Fifteen patients underwent PET/CT followed by PET/MRI with whole-body coverage from skull to feet. We performed MRI truncation correction and employed co-registered MRI and CT images for training and leave-one-out cross-validation. The network was pretrained with region-specific images. The accuracy of the AC maps and reconstructed PET images were assessed by performing a voxel-wise analysis and calculating the quantification error in SUV obtained using DL-based sCT (PET(sCT)) and a vendor-provided atlas-based method (PET(Atlas)), with the CT-based reconstruction (PET(CT)) serving as the reference. In addition, region-specific analysis was performed to compare the performances of the methods in brain, lung, liver, spine, pelvic bone, and aorta. RESULTS: Our DL-based method resulted in better estimates of AC maps with a mean absolute error of 62 HU, compared to 109 HU for the atlas-based method. We found an excellent voxel-by-voxel correlation between PET(CT) and PET(sCT) (R(2) = 0.98). The absolute percentage difference in PET quantification for the entire image was 6.1% for PET(sCT) and 11.2% for PET(Atlas). The regional analysis showed that the average errors and the variability for PET(sCT) were lower than PET(Atlas) in all regions. The largest errors were observed in the lung, while the smallest biases were observed in the brain and liver. CONCLUSIONS: Experimental results demonstrated that a DL approach for whole-body PET AC in PET/MRI is feasible and allows for more accurate results compared with conventional methods. Further evaluation using a larger training cohort is required for more accurate and robust performance. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1186/s40658-022-00486-8. Springer International Publishing 2022-08-17 /pmc/articles/PMC9385907/ /pubmed/35978211 http://dx.doi.org/10.1186/s40658-022-00486-8 Text en © The Author(s) 2022 https://creativecommons.org/licenses/by/4.0/Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Original Research
Ahangari, Sahar
Beck Olin, Anders
Kinggård Federspiel, Marianne
Jakoby, Bjoern
Andersen, Thomas Lund
Hansen, Adam Espe
Fischer, Barbara Malene
Littrup Andersen, Flemming
A deep learning-based whole-body solution for PET/MRI attenuation correction
title A deep learning-based whole-body solution for PET/MRI attenuation correction
title_full A deep learning-based whole-body solution for PET/MRI attenuation correction
title_fullStr A deep learning-based whole-body solution for PET/MRI attenuation correction
title_full_unstemmed A deep learning-based whole-body solution for PET/MRI attenuation correction
title_short A deep learning-based whole-body solution for PET/MRI attenuation correction
title_sort deep learning-based whole-body solution for pet/mri attenuation correction
topic Original Research
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9385907/
https://www.ncbi.nlm.nih.gov/pubmed/35978211
http://dx.doi.org/10.1186/s40658-022-00486-8
work_keys_str_mv AT ahangarisahar adeeplearningbasedwholebodysolutionforpetmriattenuationcorrection
AT beckolinanders adeeplearningbasedwholebodysolutionforpetmriattenuationcorrection
AT kinggardfederspielmarianne adeeplearningbasedwholebodysolutionforpetmriattenuationcorrection
AT jakobybjoern adeeplearningbasedwholebodysolutionforpetmriattenuationcorrection
AT andersenthomaslund adeeplearningbasedwholebodysolutionforpetmriattenuationcorrection
AT hansenadamespe adeeplearningbasedwholebodysolutionforpetmriattenuationcorrection
AT fischerbarbaramalene adeeplearningbasedwholebodysolutionforpetmriattenuationcorrection
AT littrupandersenflemming adeeplearningbasedwholebodysolutionforpetmriattenuationcorrection
AT ahangarisahar deeplearningbasedwholebodysolutionforpetmriattenuationcorrection
AT beckolinanders deeplearningbasedwholebodysolutionforpetmriattenuationcorrection
AT kinggardfederspielmarianne deeplearningbasedwholebodysolutionforpetmriattenuationcorrection
AT jakobybjoern deeplearningbasedwholebodysolutionforpetmriattenuationcorrection
AT andersenthomaslund deeplearningbasedwholebodysolutionforpetmriattenuationcorrection
AT hansenadamespe deeplearningbasedwholebodysolutionforpetmriattenuationcorrection
AT fischerbarbaramalene deeplearningbasedwholebodysolutionforpetmriattenuationcorrection
AT littrupandersenflemming deeplearningbasedwholebodysolutionforpetmriattenuationcorrection