Cargando…

Automated Inline Analysis of Myocardial Perfusion MRI with Deep Learning

PURPOSE: To develop a deep neural network–based computational workflow for inline myocardial perfusion analysis that automatically delineates the myocardium, which improves the clinical workflow and offers a “one-click” solution. MATERIALS AND METHODS: In this retrospective study, consecutive adenos...

Descripción completa

Detalles Bibliográficos
Autores principales: Xue, Hui, Davies, Rhodri H., Brown, Louise A. E., Knott, Kristopher D., Kotecha, Tushar, Fontana, Marianna, Plein, Sven, Moon, James C., Kellman, Peter
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Radiological Society of North America 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7706884/
https://www.ncbi.nlm.nih.gov/pubmed/33330849
http://dx.doi.org/10.1148/ryai.2020200009
_version_ 1783617242792984576
author Xue, Hui
Davies, Rhodri H.
Brown, Louise A. E.
Knott, Kristopher D.
Kotecha, Tushar
Fontana, Marianna
Plein, Sven
Moon, James C.
Kellman, Peter
author_facet Xue, Hui
Davies, Rhodri H.
Brown, Louise A. E.
Knott, Kristopher D.
Kotecha, Tushar
Fontana, Marianna
Plein, Sven
Moon, James C.
Kellman, Peter
author_sort Xue, Hui
collection PubMed
description PURPOSE: To develop a deep neural network–based computational workflow for inline myocardial perfusion analysis that automatically delineates the myocardium, which improves the clinical workflow and offers a “one-click” solution. MATERIALS AND METHODS: In this retrospective study, consecutive adenosine stress and rest perfusion scans were acquired from three hospitals between October 1, 2018 and February 27, 2019. The training and validation set included 1825 perfusion series from 1034 patients (mean age, 60.6 years ± 14.2 [standard deviation]). The independent test set included 200 scans from 105 patients (mean age, 59.1 years ± 12.5). A convolutional neural network (CNN) model was trained to segment the left ventricular cavity, myocardium, and right ventricle by processing an incoming time series of perfusion images. Model outputs were compared with manual ground truth for accuracy of segmentation and flow measures derived on a global and per-sector basis with t test performed for statistical significance. The trained models were integrated onto MR scanners for effective inference. RESULTS: The mean Dice ratio of automatic and manual segmentation was 0.93 ± 0.04. The CNN performed similarly to manual segmentation and flow measures for mean stress myocardial blood flow (MBF; 2.25 mL/min/g ± 0.59 vs 2.24 mL/min/g ± 0.59, P = .94) and mean rest MBF (1.08 mL/min/g ± 0.23 vs 1.07 mL/min/g ± 0.23, P = .83). The per-sector MBF values showed no difference between the CNN and manual assessment (P = .92). A central processing unit–based model inference on the MR scanner took less than 1 second for a typical perfusion scan of three slices. CONCLUSION: The described CNN was capable of cardiac perfusion mapping and integrated an automated inline implementation on the MR scanner, enabling one-click analysis and reporting in a manner comparable to manual assessment. Published under a CC BY 4.0 license. Supplemental material is available for this article.
format Online
Article
Text
id pubmed-7706884
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Radiological Society of North America
record_format MEDLINE/PubMed
spelling pubmed-77068842020-12-14 Automated Inline Analysis of Myocardial Perfusion MRI with Deep Learning Xue, Hui Davies, Rhodri H. Brown, Louise A. E. Knott, Kristopher D. Kotecha, Tushar Fontana, Marianna Plein, Sven Moon, James C. Kellman, Peter Radiol Artif Intell Technical Development PURPOSE: To develop a deep neural network–based computational workflow for inline myocardial perfusion analysis that automatically delineates the myocardium, which improves the clinical workflow and offers a “one-click” solution. MATERIALS AND METHODS: In this retrospective study, consecutive adenosine stress and rest perfusion scans were acquired from three hospitals between October 1, 2018 and February 27, 2019. The training and validation set included 1825 perfusion series from 1034 patients (mean age, 60.6 years ± 14.2 [standard deviation]). The independent test set included 200 scans from 105 patients (mean age, 59.1 years ± 12.5). A convolutional neural network (CNN) model was trained to segment the left ventricular cavity, myocardium, and right ventricle by processing an incoming time series of perfusion images. Model outputs were compared with manual ground truth for accuracy of segmentation and flow measures derived on a global and per-sector basis with t test performed for statistical significance. The trained models were integrated onto MR scanners for effective inference. RESULTS: The mean Dice ratio of automatic and manual segmentation was 0.93 ± 0.04. The CNN performed similarly to manual segmentation and flow measures for mean stress myocardial blood flow (MBF; 2.25 mL/min/g ± 0.59 vs 2.24 mL/min/g ± 0.59, P = .94) and mean rest MBF (1.08 mL/min/g ± 0.23 vs 1.07 mL/min/g ± 0.23, P = .83). The per-sector MBF values showed no difference between the CNN and manual assessment (P = .92). A central processing unit–based model inference on the MR scanner took less than 1 second for a typical perfusion scan of three slices. CONCLUSION: The described CNN was capable of cardiac perfusion mapping and integrated an automated inline implementation on the MR scanner, enabling one-click analysis and reporting in a manner comparable to manual assessment. Published under a CC BY 4.0 license. Supplemental material is available for this article. Radiological Society of North America 2020-10-21 /pmc/articles/PMC7706884/ /pubmed/33330849 http://dx.doi.org/10.1148/ryai.2020200009 Text en 2020 by the Radiological Society of North America, Inc. https://creativecommons.org/licenses/by/4.0/Published under a (https://creativecommons.org/licenses/by/4.0/) CC BY 4.0 license.
spellingShingle Technical Development
Xue, Hui
Davies, Rhodri H.
Brown, Louise A. E.
Knott, Kristopher D.
Kotecha, Tushar
Fontana, Marianna
Plein, Sven
Moon, James C.
Kellman, Peter
Automated Inline Analysis of Myocardial Perfusion MRI with Deep Learning
title Automated Inline Analysis of Myocardial Perfusion MRI with Deep Learning
title_full Automated Inline Analysis of Myocardial Perfusion MRI with Deep Learning
title_fullStr Automated Inline Analysis of Myocardial Perfusion MRI with Deep Learning
title_full_unstemmed Automated Inline Analysis of Myocardial Perfusion MRI with Deep Learning
title_short Automated Inline Analysis of Myocardial Perfusion MRI with Deep Learning
title_sort automated inline analysis of myocardial perfusion mri with deep learning
topic Technical Development
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7706884/
https://www.ncbi.nlm.nih.gov/pubmed/33330849
http://dx.doi.org/10.1148/ryai.2020200009
work_keys_str_mv AT xuehui automatedinlineanalysisofmyocardialperfusionmriwithdeeplearning
AT daviesrhodrih automatedinlineanalysisofmyocardialperfusionmriwithdeeplearning
AT brownlouiseae automatedinlineanalysisofmyocardialperfusionmriwithdeeplearning
AT knottkristopherd automatedinlineanalysisofmyocardialperfusionmriwithdeeplearning
AT kotechatushar automatedinlineanalysisofmyocardialperfusionmriwithdeeplearning
AT fontanamarianna automatedinlineanalysisofmyocardialperfusionmriwithdeeplearning
AT pleinsven automatedinlineanalysisofmyocardialperfusionmriwithdeeplearning
AT moonjamesc automatedinlineanalysisofmyocardialperfusionmriwithdeeplearning
AT kellmanpeter automatedinlineanalysisofmyocardialperfusionmriwithdeeplearning