Automated segmentation of thoracic aortic lumen and vessel wall on three-dimensional bright- and black-blood magnetic resonance imaging using nnU-Net

ABSTRACT: Background: Magnetic resonance angiography (MRA) is an important tool for aortic assessment in several cardiovascular diseases. Assessment of MRA images relies on manual segmentation, a time-intensive process that is subject to operator variability. We aimed to optimize and validate two d...

Full description

Saved in:
Bibliographic Details
Main Authors: Matteo Cesario, Simon J. Littlewood, James Nadel, Thomas J. Fletcher, Anastasia Fotaki, Carlos Castillo-Passi, Reza Hajhosseiny, Jim Pouliopoulos, Andrew Jabbour, Ruperto Olivero, Jose Rodríguez-Palomares, M. Eline Kooi, Claudia Prieto, René M. Botnar
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Journal of Cardiovascular Magnetic Resonance
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1097664725000857
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850100498156224512
author Matteo Cesario
Simon J. Littlewood
James Nadel
Thomas J. Fletcher
Anastasia Fotaki
Carlos Castillo-Passi
Reza Hajhosseiny
Jim Pouliopoulos
Andrew Jabbour
Ruperto Olivero
Jose Rodríguez-Palomares
M. Eline Kooi
Claudia Prieto
René M. Botnar
author_facet Matteo Cesario
Simon J. Littlewood
James Nadel
Thomas J. Fletcher
Anastasia Fotaki
Carlos Castillo-Passi
Reza Hajhosseiny
Jim Pouliopoulos
Andrew Jabbour
Ruperto Olivero
Jose Rodríguez-Palomares
M. Eline Kooi
Claudia Prieto
René M. Botnar
author_sort Matteo Cesario
collection DOAJ
description ABSTRACT: Background: Magnetic resonance angiography (MRA) is an important tool for aortic assessment in several cardiovascular diseases. Assessment of MRA images relies on manual segmentation, a time-intensive process that is subject to operator variability. We aimed to optimize and validate two deep-learning models for automatic segmentation of the aortic lumen and vessel wall in high-resolution electrocardiogram-triggered free-breathing respiratory motion-corrected three-dimensional (3D) bright- and black-blood MRA images. Methods: Manual segmentation, serving as the ground truth, was performed on 25 bright-blood and 15 black-blood 3D MRA image sets acquired with the iT2PrepIR-BOOST sequence (1.5T) in thoracic aortopathy patients. The training was performed with no new U-Net (nnUNet) for bright-blood (lumen) and black-blood image sets (lumen and vessel wall). Training consisted of a 70:20:10% (17/25:5/25:3/25 datasets) training:validation:testing split. Inference was run on datasets (single vendor) from different centers (UK, Spain, and Australia), sequences (iT2PrepIR-BOOST, T2 prepared coronary magnetic resonance angiography [CMRA], and time-resolved angiography with interleaved stochastic trajectories [TWIST] MRA), acquired resolutions (from 0.9–3 mm3), and field strengths (0.55T, 1.5T, and 3T). Predictive measurements comprised Dice similarity coefficient (DSC) and Intersection over Union (IoU). Postprocessing (3D slicer) included centreline extraction, diameter measurement, and curved planar reformatting (CPR). Results: The optimal configuration was the 3D U-Net. Bright-blood segmentation at 1.5T on iT2PrepIR-BOOST datasets (1.3 and 1.8 mm3) and 3D CMRA datasets (0.9 mm3) resulted in DSC ≥ 0.96 and IoU ≥ 0.92. For bright-blood segmentation on 3D CMRA at 0.55T, the nnUNet achieved DSC and IoU scores of 0.93 and 0.88 at 1.5 mm³, and 0.68 and 0.52 at 3.0 mm³, respectively. DSC and IoU scores of 0.89 and 0.82 were obtained for CMRA image sets (1 mm3) at 1.5T (Barcelona dataset). DSC and IoU scores of the BRnnUNet model were 0.90 and 0.82, respectively, for the contrast-enhanced dataset (TWIST MRA). Lumen segmentation on black-blood 1.5T iT2PrepIR-BOOST image sets achieved DSC ≥ 0.95 and IoU ≥ 0.90, and vessel wall segmentation resulted in DSC ≥ 0.80 and IoU ≥ 0.67. Automated centreline tracking, diameter measurement, and CPR were successfully implemented in all subjects. Conclusion: Automated aortic lumen and wall segmentation on 3D bright- and black-blood image sets demonstrated excellent agreement with ground truth. This technique demonstrates a fast and comprehensive assessment of aortic morphology with great potential for future clinical application in various cardiovascular diseases.
format Article
id doaj-art-0f948d87ddc843118d3ad23e2890069f
institution DOAJ
issn 1097-6647
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Journal of Cardiovascular Magnetic Resonance
spelling doaj-art-0f948d87ddc843118d3ad23e2890069f2025-08-20T02:40:17ZengElsevierJournal of Cardiovascular Magnetic Resonance1097-66472025-01-0127210192310.1016/j.jocmr.2025.101923Automated segmentation of thoracic aortic lumen and vessel wall on three-dimensional bright- and black-blood magnetic resonance imaging using nnU-NetMatteo Cesario0Simon J. Littlewood1James Nadel2Thomas J. Fletcher3Anastasia Fotaki4Carlos Castillo-Passi5Reza Hajhosseiny6Jim Pouliopoulos7Andrew Jabbour8Ruperto Olivero9Jose Rodríguez-Palomares10M. Eline Kooi11Claudia Prieto12René M. Botnar13School of Biomedical Engineering and Imaging Sciences, King’s College London, London, United Kingdom; Department of Radiology and Nuclear Medicine, Maastricht University Medical Centre, Maastricht, the Netherlands; Cardiovascular Research Institute Maastricht (CARIM), Maastricht University, Maastricht, the NetherlandsSchool of Biomedical Engineering and Imaging Sciences, King’s College London, London, United KingdomSchool of Biomedical Engineering and Imaging Sciences, King’s College London, London, United Kingdom; Clinical Research Group, Heart Research Institute, Newtown, Australia; Cardiology Department, St. Vincent’s Hospital, Darlinghurst, AustraliaSchool of Biomedical Engineering and Imaging Sciences, King’s College London, London, United KingdomSchool of Biomedical Engineering and Imaging Sciences, King’s College London, London, United KingdomSchool of Biomedical Engineering and Imaging Sciences, King’s College London, London, United Kingdom; Institute of Biological and Medical Engineering, Pontificia Universidad Católica de Chile, Santiago, ChileSchool of Biomedical Engineering and Imaging Sciences, King’s College London, London, United Kingdom; Department of Cardiology, Chelsea and Westminster Hospital NHS Foundation Trust, London, United KingdomCardiology Department, St. Vincent’s Hospital, Darlinghurst, Australia; Victor Chang Cardiac Research Institute, Sydney, AustraliaCardiology Department, St. Vincent’s Hospital, Darlinghurst, Australia; Victor Chang Cardiac Research Institute, Sydney, AustraliaDepartment of Cardiology, Vall d′Hebron Hospital Universitari, Vall d′Hebron Barcelona Hospital Campus, Barcelona, Spain; Department of Medicine, Universitat Autònoma de Barcelona, Bellaterra, Spain; Cardiovascular Diseases, Vall d′Hebron Institut de Recerca (VHIR), Vall d′Hebron Barcelona Hospital Campus, Universitat Autònoma de Barcelona, Bellaterra, Spain; CIBER de Enfermedades Cardiovasculares, Instituto de Salud Carlos III, Madrid, SpainDepartment of Cardiology, Vall d′Hebron Hospital Universitari, Vall d′Hebron Barcelona Hospital Campus, Barcelona, Spain; Department of Medicine, Universitat Autònoma de Barcelona, Bellaterra, Spain; Cardiovascular Diseases, Vall d′Hebron Institut de Recerca (VHIR), Vall d′Hebron Barcelona Hospital Campus, Universitat Autònoma de Barcelona, Bellaterra, Spain; CIBER de Enfermedades Cardiovasculares, Instituto de Salud Carlos III, Madrid, SpainDepartment of Radiology and Nuclear Medicine, Maastricht University Medical Centre, Maastricht, the Netherlands; Cardiovascular Research Institute Maastricht (CARIM), Maastricht University, Maastricht, the NetherlandsSchool of Biomedical Engineering and Imaging Sciences, King’s College London, London, United Kingdom; School of Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile; Millennium Institute for Intelligent Healthcare Engineering, Santiago, ChileSchool of Biomedical Engineering and Imaging Sciences, King’s College London, London, United Kingdom; Institute of Biological and Medical Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile; School of Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile; Millennium Institute for Intelligent Healthcare Engineering, Santiago, Chile; Institute for Advanced Study, Technical University of Munich, Garching, Germany; Corresponding author.ABSTRACT: Background: Magnetic resonance angiography (MRA) is an important tool for aortic assessment in several cardiovascular diseases. Assessment of MRA images relies on manual segmentation, a time-intensive process that is subject to operator variability. We aimed to optimize and validate two deep-learning models for automatic segmentation of the aortic lumen and vessel wall in high-resolution electrocardiogram-triggered free-breathing respiratory motion-corrected three-dimensional (3D) bright- and black-blood MRA images. Methods: Manual segmentation, serving as the ground truth, was performed on 25 bright-blood and 15 black-blood 3D MRA image sets acquired with the iT2PrepIR-BOOST sequence (1.5T) in thoracic aortopathy patients. The training was performed with no new U-Net (nnUNet) for bright-blood (lumen) and black-blood image sets (lumen and vessel wall). Training consisted of a 70:20:10% (17/25:5/25:3/25 datasets) training:validation:testing split. Inference was run on datasets (single vendor) from different centers (UK, Spain, and Australia), sequences (iT2PrepIR-BOOST, T2 prepared coronary magnetic resonance angiography [CMRA], and time-resolved angiography with interleaved stochastic trajectories [TWIST] MRA), acquired resolutions (from 0.9–3 mm3), and field strengths (0.55T, 1.5T, and 3T). Predictive measurements comprised Dice similarity coefficient (DSC) and Intersection over Union (IoU). Postprocessing (3D slicer) included centreline extraction, diameter measurement, and curved planar reformatting (CPR). Results: The optimal configuration was the 3D U-Net. Bright-blood segmentation at 1.5T on iT2PrepIR-BOOST datasets (1.3 and 1.8 mm3) and 3D CMRA datasets (0.9 mm3) resulted in DSC ≥ 0.96 and IoU ≥ 0.92. For bright-blood segmentation on 3D CMRA at 0.55T, the nnUNet achieved DSC and IoU scores of 0.93 and 0.88 at 1.5 mm³, and 0.68 and 0.52 at 3.0 mm³, respectively. DSC and IoU scores of 0.89 and 0.82 were obtained for CMRA image sets (1 mm3) at 1.5T (Barcelona dataset). DSC and IoU scores of the BRnnUNet model were 0.90 and 0.82, respectively, for the contrast-enhanced dataset (TWIST MRA). Lumen segmentation on black-blood 1.5T iT2PrepIR-BOOST image sets achieved DSC ≥ 0.95 and IoU ≥ 0.90, and vessel wall segmentation resulted in DSC ≥ 0.80 and IoU ≥ 0.67. Automated centreline tracking, diameter measurement, and CPR were successfully implemented in all subjects. Conclusion: Automated aortic lumen and wall segmentation on 3D bright- and black-blood image sets demonstrated excellent agreement with ground truth. This technique demonstrates a fast and comprehensive assessment of aortic morphology with great potential for future clinical application in various cardiovascular diseases.http://www.sciencedirect.com/science/article/pii/S1097664725000857AortaAortic diseaseMagnetic resonance angiographySegmentationDeep-learningnnUNet
spellingShingle Matteo Cesario
Simon J. Littlewood
James Nadel
Thomas J. Fletcher
Anastasia Fotaki
Carlos Castillo-Passi
Reza Hajhosseiny
Jim Pouliopoulos
Andrew Jabbour
Ruperto Olivero
Jose Rodríguez-Palomares
M. Eline Kooi
Claudia Prieto
René M. Botnar
Automated segmentation of thoracic aortic lumen and vessel wall on three-dimensional bright- and black-blood magnetic resonance imaging using nnU-Net
Journal of Cardiovascular Magnetic Resonance
Aorta
Aortic disease
Magnetic resonance angiography
Segmentation
Deep-learning
nnUNet
title Automated segmentation of thoracic aortic lumen and vessel wall on three-dimensional bright- and black-blood magnetic resonance imaging using nnU-Net
title_full Automated segmentation of thoracic aortic lumen and vessel wall on three-dimensional bright- and black-blood magnetic resonance imaging using nnU-Net
title_fullStr Automated segmentation of thoracic aortic lumen and vessel wall on three-dimensional bright- and black-blood magnetic resonance imaging using nnU-Net
title_full_unstemmed Automated segmentation of thoracic aortic lumen and vessel wall on three-dimensional bright- and black-blood magnetic resonance imaging using nnU-Net
title_short Automated segmentation of thoracic aortic lumen and vessel wall on three-dimensional bright- and black-blood magnetic resonance imaging using nnU-Net
title_sort automated segmentation of thoracic aortic lumen and vessel wall on three dimensional bright and black blood magnetic resonance imaging using nnu net
topic Aorta
Aortic disease
Magnetic resonance angiography
Segmentation
Deep-learning
nnUNet
url http://www.sciencedirect.com/science/article/pii/S1097664725000857
work_keys_str_mv AT matteocesario automatedsegmentationofthoracicaorticlumenandvesselwallonthreedimensionalbrightandblackbloodmagneticresonanceimagingusingnnunet
AT simonjlittlewood automatedsegmentationofthoracicaorticlumenandvesselwallonthreedimensionalbrightandblackbloodmagneticresonanceimagingusingnnunet
AT jamesnadel automatedsegmentationofthoracicaorticlumenandvesselwallonthreedimensionalbrightandblackbloodmagneticresonanceimagingusingnnunet
AT thomasjfletcher automatedsegmentationofthoracicaorticlumenandvesselwallonthreedimensionalbrightandblackbloodmagneticresonanceimagingusingnnunet
AT anastasiafotaki automatedsegmentationofthoracicaorticlumenandvesselwallonthreedimensionalbrightandblackbloodmagneticresonanceimagingusingnnunet
AT carloscastillopassi automatedsegmentationofthoracicaorticlumenandvesselwallonthreedimensionalbrightandblackbloodmagneticresonanceimagingusingnnunet
AT rezahajhosseiny automatedsegmentationofthoracicaorticlumenandvesselwallonthreedimensionalbrightandblackbloodmagneticresonanceimagingusingnnunet
AT jimpouliopoulos automatedsegmentationofthoracicaorticlumenandvesselwallonthreedimensionalbrightandblackbloodmagneticresonanceimagingusingnnunet
AT andrewjabbour automatedsegmentationofthoracicaorticlumenandvesselwallonthreedimensionalbrightandblackbloodmagneticresonanceimagingusingnnunet
AT rupertoolivero automatedsegmentationofthoracicaorticlumenandvesselwallonthreedimensionalbrightandblackbloodmagneticresonanceimagingusingnnunet
AT joserodriguezpalomares automatedsegmentationofthoracicaorticlumenandvesselwallonthreedimensionalbrightandblackbloodmagneticresonanceimagingusingnnunet
AT melinekooi automatedsegmentationofthoracicaorticlumenandvesselwallonthreedimensionalbrightandblackbloodmagneticresonanceimagingusingnnunet
AT claudiaprieto automatedsegmentationofthoracicaorticlumenandvesselwallonthreedimensionalbrightandblackbloodmagneticresonanceimagingusingnnunet
AT renembotnar automatedsegmentationofthoracicaorticlumenandvesselwallonthreedimensionalbrightandblackbloodmagneticresonanceimagingusingnnunet