Cargando…

An Improved 3D Deep Learning-Based Segmentation of Left Ventricular Myocardial Diseases from Delayed-Enhancement MRI with Inclusion and Classification Prior Information U-Net (ICPIU-Net)

Accurate segmentation of the myocardial scar may supply relevant advancements in predicting and controlling deadly ventricular arrhythmias in subjects with cardiovascular disease. In this paper, we propose the architecture of inclusion and classification of prior information U-Net (ICPIU-Net) to eff...

Descripción completa

Detalles Bibliográficos
Autores principales: Brahim, Khawla, Arega, Tewodros Weldebirhan, Boucher, Arnaud, Bricq, Stephanie, Sakly, Anis, Meriaudeau, Fabrice
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8954140/
https://www.ncbi.nlm.nih.gov/pubmed/35336258
http://dx.doi.org/10.3390/s22062084
_version_ 1784676021459484672
author Brahim, Khawla
Arega, Tewodros Weldebirhan
Boucher, Arnaud
Bricq, Stephanie
Sakly, Anis
Meriaudeau, Fabrice
author_facet Brahim, Khawla
Arega, Tewodros Weldebirhan
Boucher, Arnaud
Bricq, Stephanie
Sakly, Anis
Meriaudeau, Fabrice
author_sort Brahim, Khawla
collection PubMed
description Accurate segmentation of the myocardial scar may supply relevant advancements in predicting and controlling deadly ventricular arrhythmias in subjects with cardiovascular disease. In this paper, we propose the architecture of inclusion and classification of prior information U-Net (ICPIU-Net) to efficiently segment the left ventricle (LV) myocardium, myocardial infarction (MI), and microvascular-obstructed (MVO) tissues from late gadolinium enhancement magnetic resonance (LGE-MR) images. Our approach was developed using two subnets cascaded to first segment the LV cavity and myocardium. Then, we used inclusion and classification constraint networks to improve the resulting segmentation of the diseased regions within the pre-segmented LV myocardium. This network incorporates the inclusion and classification information of the LGE-MRI to maintain topological constraints of pathological areas. In the testing stage, the outputs of each segmentation network obtained with specific estimated parameters from training were fused using the majority voting technique for the final label prediction of each voxel in the LGE-MR image. The proposed method was validated by comparing its results to manual drawings by experts from 50 LGE-MR images. Importantly, compared to various deep learning-based methods participating in the EMIDEC challenge, the results of our approach have a more significant agreement with manual contouring in segmenting myocardial diseases.
format Online
Article
Text
id pubmed-8954140
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-89541402022-03-26 An Improved 3D Deep Learning-Based Segmentation of Left Ventricular Myocardial Diseases from Delayed-Enhancement MRI with Inclusion and Classification Prior Information U-Net (ICPIU-Net) Brahim, Khawla Arega, Tewodros Weldebirhan Boucher, Arnaud Bricq, Stephanie Sakly, Anis Meriaudeau, Fabrice Sensors (Basel) Article Accurate segmentation of the myocardial scar may supply relevant advancements in predicting and controlling deadly ventricular arrhythmias in subjects with cardiovascular disease. In this paper, we propose the architecture of inclusion and classification of prior information U-Net (ICPIU-Net) to efficiently segment the left ventricle (LV) myocardium, myocardial infarction (MI), and microvascular-obstructed (MVO) tissues from late gadolinium enhancement magnetic resonance (LGE-MR) images. Our approach was developed using two subnets cascaded to first segment the LV cavity and myocardium. Then, we used inclusion and classification constraint networks to improve the resulting segmentation of the diseased regions within the pre-segmented LV myocardium. This network incorporates the inclusion and classification information of the LGE-MRI to maintain topological constraints of pathological areas. In the testing stage, the outputs of each segmentation network obtained with specific estimated parameters from training were fused using the majority voting technique for the final label prediction of each voxel in the LGE-MR image. The proposed method was validated by comparing its results to manual drawings by experts from 50 LGE-MR images. Importantly, compared to various deep learning-based methods participating in the EMIDEC challenge, the results of our approach have a more significant agreement with manual contouring in segmenting myocardial diseases. MDPI 2022-03-08 /pmc/articles/PMC8954140/ /pubmed/35336258 http://dx.doi.org/10.3390/s22062084 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Brahim, Khawla
Arega, Tewodros Weldebirhan
Boucher, Arnaud
Bricq, Stephanie
Sakly, Anis
Meriaudeau, Fabrice
An Improved 3D Deep Learning-Based Segmentation of Left Ventricular Myocardial Diseases from Delayed-Enhancement MRI with Inclusion and Classification Prior Information U-Net (ICPIU-Net)
title An Improved 3D Deep Learning-Based Segmentation of Left Ventricular Myocardial Diseases from Delayed-Enhancement MRI with Inclusion and Classification Prior Information U-Net (ICPIU-Net)
title_full An Improved 3D Deep Learning-Based Segmentation of Left Ventricular Myocardial Diseases from Delayed-Enhancement MRI with Inclusion and Classification Prior Information U-Net (ICPIU-Net)
title_fullStr An Improved 3D Deep Learning-Based Segmentation of Left Ventricular Myocardial Diseases from Delayed-Enhancement MRI with Inclusion and Classification Prior Information U-Net (ICPIU-Net)
title_full_unstemmed An Improved 3D Deep Learning-Based Segmentation of Left Ventricular Myocardial Diseases from Delayed-Enhancement MRI with Inclusion and Classification Prior Information U-Net (ICPIU-Net)
title_short An Improved 3D Deep Learning-Based Segmentation of Left Ventricular Myocardial Diseases from Delayed-Enhancement MRI with Inclusion and Classification Prior Information U-Net (ICPIU-Net)
title_sort improved 3d deep learning-based segmentation of left ventricular myocardial diseases from delayed-enhancement mri with inclusion and classification prior information u-net (icpiu-net)
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8954140/
https://www.ncbi.nlm.nih.gov/pubmed/35336258
http://dx.doi.org/10.3390/s22062084
work_keys_str_mv AT brahimkhawla animproved3ddeeplearningbasedsegmentationofleftventricularmyocardialdiseasesfromdelayedenhancementmriwithinclusionandclassificationpriorinformationuneticpiunet
AT aregatewodrosweldebirhan animproved3ddeeplearningbasedsegmentationofleftventricularmyocardialdiseasesfromdelayedenhancementmriwithinclusionandclassificationpriorinformationuneticpiunet
AT boucherarnaud animproved3ddeeplearningbasedsegmentationofleftventricularmyocardialdiseasesfromdelayedenhancementmriwithinclusionandclassificationpriorinformationuneticpiunet
AT bricqstephanie animproved3ddeeplearningbasedsegmentationofleftventricularmyocardialdiseasesfromdelayedenhancementmriwithinclusionandclassificationpriorinformationuneticpiunet
AT saklyanis animproved3ddeeplearningbasedsegmentationofleftventricularmyocardialdiseasesfromdelayedenhancementmriwithinclusionandclassificationpriorinformationuneticpiunet
AT meriaudeaufabrice animproved3ddeeplearningbasedsegmentationofleftventricularmyocardialdiseasesfromdelayedenhancementmriwithinclusionandclassificationpriorinformationuneticpiunet
AT brahimkhawla improved3ddeeplearningbasedsegmentationofleftventricularmyocardialdiseasesfromdelayedenhancementmriwithinclusionandclassificationpriorinformationuneticpiunet
AT aregatewodrosweldebirhan improved3ddeeplearningbasedsegmentationofleftventricularmyocardialdiseasesfromdelayedenhancementmriwithinclusionandclassificationpriorinformationuneticpiunet
AT boucherarnaud improved3ddeeplearningbasedsegmentationofleftventricularmyocardialdiseasesfromdelayedenhancementmriwithinclusionandclassificationpriorinformationuneticpiunet
AT bricqstephanie improved3ddeeplearningbasedsegmentationofleftventricularmyocardialdiseasesfromdelayedenhancementmriwithinclusionandclassificationpriorinformationuneticpiunet
AT saklyanis improved3ddeeplearningbasedsegmentationofleftventricularmyocardialdiseasesfromdelayedenhancementmriwithinclusionandclassificationpriorinformationuneticpiunet
AT meriaudeaufabrice improved3ddeeplearningbasedsegmentationofleftventricularmyocardialdiseasesfromdelayedenhancementmriwithinclusionandclassificationpriorinformationuneticpiunet