Cargando…

Automated analysis of cardiovascular magnetic resonance myocardial native T(1) mapping images using fully convolutional neural networks

BACKGROUND: Cardiovascular magnetic resonance (CMR) myocardial native T(1) mapping allows assessment of interstitial diffuse fibrosis. In this technique, the global and regional T(1) are measured manually by drawing region of interest in motion-corrected T(1) maps. The manual analysis contributes to...

Descripción completa

Detalles Bibliográficos
Autores principales: Fahmy, Ahmed S., El-Rewaidy, Hossam, Nezafat, Maryam, Nakamori, Shiro, Nezafat, Reza
Formato: Online Artículo Texto
Lenguaje:English
Publicado: BioMed Central 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6330747/
https://www.ncbi.nlm.nih.gov/pubmed/30636630
http://dx.doi.org/10.1186/s12968-018-0516-1
_version_ 1783387024667967488
author Fahmy, Ahmed S.
El-Rewaidy, Hossam
Nezafat, Maryam
Nakamori, Shiro
Nezafat, Reza
author_facet Fahmy, Ahmed S.
El-Rewaidy, Hossam
Nezafat, Maryam
Nakamori, Shiro
Nezafat, Reza
author_sort Fahmy, Ahmed S.
collection PubMed
description BACKGROUND: Cardiovascular magnetic resonance (CMR) myocardial native T(1) mapping allows assessment of interstitial diffuse fibrosis. In this technique, the global and regional T(1) are measured manually by drawing region of interest in motion-corrected T(1) maps. The manual analysis contributes to an already lengthy CMR analysis workflow and impacts measurements reproducibility. In this study, we propose an automated method for combined myocardium segmentation, alignment, and T(1) calculation for myocardial T(1) mapping. METHODS: A deep fully convolutional neural network (FCN) was used for myocardium segmentation in T(1) weighted images. The segmented myocardium was then resampled on a polar grid, whose origin is located at the center-of-mass of the segmented myocardium. Myocardium T(1) maps were reconstructed from the resampled T(1) weighted images using curve fitting. The FCN was trained and tested using manually segmented images for 210 patients (5 slices, 11 inversion times per patient). An additional image dataset for 455 patients (5 slices and 11 inversion times per patient), analyzed by an expert reader using a semi-automatic tool, was used to validate the automatically calculated global and regional T(1) values. Bland-Altman analysis, Pearson correlation coefficient, r, and the Dice similarity coefficient (DSC) were used to evaluate the performance of the FCN-based analysis on per-patient and per-slice basis. Inter-observer variability was assessed using intraclass correlation coefficient (ICC) of the T(1) values calculated by the FCN-based automatic method and two readers. RESULTS: The FCN achieved fast segmentation (< 0.3 s/image) with high DSC (0.85 ± 0.07). The automatically and manually calculated T(1) values (1091 ± 59 ms and 1089 ± 59 ms, respectively) were highly correlated in per-patient (r = 0.82; slope = 1.01; p < 0.0001) and per-slice (r = 0.72; slope = 1.01; p < 0.0001) analyses. Bland-Altman analysis showed good agreement between the automated and manual measurements with 95% of measurements within the limits-of-agreement in both per-patient and per-slice analyses. The intraclass correllation of the T(1) calculations by the automatic method vs reader 1 and reader 2 was respectively 0.86/0.56 and 0.74/0.49 in the per-patient/per-slice analyses, which were comparable to that between two expert readers (=0.72/0.58 in per-patient/per-slice analyses). CONCLUSION: The proposed FCN-based image processing platform allows fast and automatic analysis of myocardial native T(1) mapping images mitigating the burden and observer-related variability of manual analysis. ELECTRONIC SUPPLEMENTARY MATERIAL: The online version of this article (10.1186/s12968-018-0516-1) contains supplementary material, which is available to authorized users.
format Online
Article
Text
id pubmed-6330747
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher BioMed Central
record_format MEDLINE/PubMed
spelling pubmed-63307472019-01-16 Automated analysis of cardiovascular magnetic resonance myocardial native T(1) mapping images using fully convolutional neural networks Fahmy, Ahmed S. El-Rewaidy, Hossam Nezafat, Maryam Nakamori, Shiro Nezafat, Reza J Cardiovasc Magn Reson Research BACKGROUND: Cardiovascular magnetic resonance (CMR) myocardial native T(1) mapping allows assessment of interstitial diffuse fibrosis. In this technique, the global and regional T(1) are measured manually by drawing region of interest in motion-corrected T(1) maps. The manual analysis contributes to an already lengthy CMR analysis workflow and impacts measurements reproducibility. In this study, we propose an automated method for combined myocardium segmentation, alignment, and T(1) calculation for myocardial T(1) mapping. METHODS: A deep fully convolutional neural network (FCN) was used for myocardium segmentation in T(1) weighted images. The segmented myocardium was then resampled on a polar grid, whose origin is located at the center-of-mass of the segmented myocardium. Myocardium T(1) maps were reconstructed from the resampled T(1) weighted images using curve fitting. The FCN was trained and tested using manually segmented images for 210 patients (5 slices, 11 inversion times per patient). An additional image dataset for 455 patients (5 slices and 11 inversion times per patient), analyzed by an expert reader using a semi-automatic tool, was used to validate the automatically calculated global and regional T(1) values. Bland-Altman analysis, Pearson correlation coefficient, r, and the Dice similarity coefficient (DSC) were used to evaluate the performance of the FCN-based analysis on per-patient and per-slice basis. Inter-observer variability was assessed using intraclass correlation coefficient (ICC) of the T(1) values calculated by the FCN-based automatic method and two readers. RESULTS: The FCN achieved fast segmentation (< 0.3 s/image) with high DSC (0.85 ± 0.07). The automatically and manually calculated T(1) values (1091 ± 59 ms and 1089 ± 59 ms, respectively) were highly correlated in per-patient (r = 0.82; slope = 1.01; p < 0.0001) and per-slice (r = 0.72; slope = 1.01; p < 0.0001) analyses. Bland-Altman analysis showed good agreement between the automated and manual measurements with 95% of measurements within the limits-of-agreement in both per-patient and per-slice analyses. The intraclass correllation of the T(1) calculations by the automatic method vs reader 1 and reader 2 was respectively 0.86/0.56 and 0.74/0.49 in the per-patient/per-slice analyses, which were comparable to that between two expert readers (=0.72/0.58 in per-patient/per-slice analyses). CONCLUSION: The proposed FCN-based image processing platform allows fast and automatic analysis of myocardial native T(1) mapping images mitigating the burden and observer-related variability of manual analysis. ELECTRONIC SUPPLEMENTARY MATERIAL: The online version of this article (10.1186/s12968-018-0516-1) contains supplementary material, which is available to authorized users. BioMed Central 2019-01-14 /pmc/articles/PMC6330747/ /pubmed/30636630 http://dx.doi.org/10.1186/s12968-018-0516-1 Text en © The Author(s). 2019 Open AccessThis article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated.
spellingShingle Research
Fahmy, Ahmed S.
El-Rewaidy, Hossam
Nezafat, Maryam
Nakamori, Shiro
Nezafat, Reza
Automated analysis of cardiovascular magnetic resonance myocardial native T(1) mapping images using fully convolutional neural networks
title Automated analysis of cardiovascular magnetic resonance myocardial native T(1) mapping images using fully convolutional neural networks
title_full Automated analysis of cardiovascular magnetic resonance myocardial native T(1) mapping images using fully convolutional neural networks
title_fullStr Automated analysis of cardiovascular magnetic resonance myocardial native T(1) mapping images using fully convolutional neural networks
title_full_unstemmed Automated analysis of cardiovascular magnetic resonance myocardial native T(1) mapping images using fully convolutional neural networks
title_short Automated analysis of cardiovascular magnetic resonance myocardial native T(1) mapping images using fully convolutional neural networks
title_sort automated analysis of cardiovascular magnetic resonance myocardial native t(1) mapping images using fully convolutional neural networks
topic Research
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6330747/
https://www.ncbi.nlm.nih.gov/pubmed/30636630
http://dx.doi.org/10.1186/s12968-018-0516-1
work_keys_str_mv AT fahmyahmeds automatedanalysisofcardiovascularmagneticresonancemyocardialnativet1mappingimagesusingfullyconvolutionalneuralnetworks
AT elrewaidyhossam automatedanalysisofcardiovascularmagneticresonancemyocardialnativet1mappingimagesusingfullyconvolutionalneuralnetworks
AT nezafatmaryam automatedanalysisofcardiovascularmagneticresonancemyocardialnativet1mappingimagesusingfullyconvolutionalneuralnetworks
AT nakamorishiro automatedanalysisofcardiovascularmagneticresonancemyocardialnativet1mappingimagesusingfullyconvolutionalneuralnetworks
AT nezafatreza automatedanalysisofcardiovascularmagneticresonancemyocardialnativet1mappingimagesusingfullyconvolutionalneuralnetworks