Cargando…

Fast dynamic brain PET imaging using stochastic variational prediction for recurrent frame generation

PURPOSE: We assess the performance of a recurrent frame generation algorithm for prediction of late frames from initial frames in dynamic brain PET imaging. METHODS: Clinical dynamic (18)F‐DOPA brain PET/CT studies of 46 subjects with ten folds cross‐validation were retrospectively employed. A novel...

Descripción completa

Detalles Bibliográficos
Autores principales: Sanaat, Amirhossein, Mirsadeghi, Ehsan, Razeghi, Behrooz, Ginovart, Nathalie, Zaidi, Habib
Formato: Online Artículo Texto
Lenguaje:English
Publicado: John Wiley and Sons Inc. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8518550/
https://www.ncbi.nlm.nih.gov/pubmed/34174787
http://dx.doi.org/10.1002/mp.15063
_version_ 1784584250439237632
author Sanaat, Amirhossein
Mirsadeghi, Ehsan
Razeghi, Behrooz
Ginovart, Nathalie
Zaidi, Habib
author_facet Sanaat, Amirhossein
Mirsadeghi, Ehsan
Razeghi, Behrooz
Ginovart, Nathalie
Zaidi, Habib
author_sort Sanaat, Amirhossein
collection PubMed
description PURPOSE: We assess the performance of a recurrent frame generation algorithm for prediction of late frames from initial frames in dynamic brain PET imaging. METHODS: Clinical dynamic (18)F‐DOPA brain PET/CT studies of 46 subjects with ten folds cross‐validation were retrospectively employed. A novel stochastic adversarial video prediction model was implemented to predict the last 13 frames (25–90 minutes) from the initial 13 frames (0–25 minutes). The quantitative analysis of the predicted dynamic PET frames was performed for the test and validation dataset using established metrics. RESULTS: The predicted dynamic images demonstrated that the model is capable of predicting the trend of change in time‐varying tracer biodistribution. The Bland‐Altman plots reported the lowest tracer uptake bias (−0.04) for the putamen region and the smallest variance (95% CI: −0.38, +0.14) for the cerebellum. The region‐wise Patlak graphical analysis in the caudate and putamen regions for eight subjects from the test and validation dataset showed that the average bias for [Formula: see text] and distribution volume was 4.3%, 5.1% and 4.4%, 4.2%, (P‐value <0.05), respectively. CONCLUSION: We have developed a novel deep learning approach for fast dynamic brain PET imaging capable of generating the last 65 minutes time frames from the initial 25 minutes frames, thus enabling significant reduction in scanning time.
format Online
Article
Text
id pubmed-8518550
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher John Wiley and Sons Inc.
record_format MEDLINE/PubMed
spelling pubmed-85185502021-10-21 Fast dynamic brain PET imaging using stochastic variational prediction for recurrent frame generation Sanaat, Amirhossein Mirsadeghi, Ehsan Razeghi, Behrooz Ginovart, Nathalie Zaidi, Habib Med Phys QUANTITATIVE IMAGING AND IMAGE PROCESSING PURPOSE: We assess the performance of a recurrent frame generation algorithm for prediction of late frames from initial frames in dynamic brain PET imaging. METHODS: Clinical dynamic (18)F‐DOPA brain PET/CT studies of 46 subjects with ten folds cross‐validation were retrospectively employed. A novel stochastic adversarial video prediction model was implemented to predict the last 13 frames (25–90 minutes) from the initial 13 frames (0–25 minutes). The quantitative analysis of the predicted dynamic PET frames was performed for the test and validation dataset using established metrics. RESULTS: The predicted dynamic images demonstrated that the model is capable of predicting the trend of change in time‐varying tracer biodistribution. The Bland‐Altman plots reported the lowest tracer uptake bias (−0.04) for the putamen region and the smallest variance (95% CI: −0.38, +0.14) for the cerebellum. The region‐wise Patlak graphical analysis in the caudate and putamen regions for eight subjects from the test and validation dataset showed that the average bias for [Formula: see text] and distribution volume was 4.3%, 5.1% and 4.4%, 4.2%, (P‐value <0.05), respectively. CONCLUSION: We have developed a novel deep learning approach for fast dynamic brain PET imaging capable of generating the last 65 minutes time frames from the initial 25 minutes frames, thus enabling significant reduction in scanning time. John Wiley and Sons Inc. 2021-07-21 2021-09 /pmc/articles/PMC8518550/ /pubmed/34174787 http://dx.doi.org/10.1002/mp.15063 Text en © 2021 The Authors. Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the terms of the http://creativecommons.org/licenses/by-nc-nd/4.0/ (https://creativecommons.org/licenses/by-nc-nd/4.0/) License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non‐commercial and no modifications or adaptations are made.
spellingShingle QUANTITATIVE IMAGING AND IMAGE PROCESSING
Sanaat, Amirhossein
Mirsadeghi, Ehsan
Razeghi, Behrooz
Ginovart, Nathalie
Zaidi, Habib
Fast dynamic brain PET imaging using stochastic variational prediction for recurrent frame generation
title Fast dynamic brain PET imaging using stochastic variational prediction for recurrent frame generation
title_full Fast dynamic brain PET imaging using stochastic variational prediction for recurrent frame generation
title_fullStr Fast dynamic brain PET imaging using stochastic variational prediction for recurrent frame generation
title_full_unstemmed Fast dynamic brain PET imaging using stochastic variational prediction for recurrent frame generation
title_short Fast dynamic brain PET imaging using stochastic variational prediction for recurrent frame generation
title_sort fast dynamic brain pet imaging using stochastic variational prediction for recurrent frame generation
topic QUANTITATIVE IMAGING AND IMAGE PROCESSING
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8518550/
https://www.ncbi.nlm.nih.gov/pubmed/34174787
http://dx.doi.org/10.1002/mp.15063
work_keys_str_mv AT sanaatamirhossein fastdynamicbrainpetimagingusingstochasticvariationalpredictionforrecurrentframegeneration
AT mirsadeghiehsan fastdynamicbrainpetimagingusingstochasticvariationalpredictionforrecurrentframegeneration
AT razeghibehrooz fastdynamicbrainpetimagingusingstochasticvariationalpredictionforrecurrentframegeneration
AT ginovartnathalie fastdynamicbrainpetimagingusingstochasticvariationalpredictionforrecurrentframegeneration
AT zaidihabib fastdynamicbrainpetimagingusingstochasticvariationalpredictionforrecurrentframegeneration