Automated Segmentation of Thoracic Aortic Lumen and Vessel Wall on 3D Bright- and Black-Blood MRI using nnU-Net

Simple item page
dc.catalogadoraba
dc.contributor.authorCesario, Matteo
dc.contributor.authorLittlewood, Simon J.
dc.contributor.authorNadel, James
dc.contributor.authorFletcher, Thomas J.
dc.contributor.authorFotaki, Anastasia
dc.contributor.authorCastillo Passi, Carlos
dc.contributor.authorHajhosseiny, Reza
dc.contributor.authorPouliopoulos, Jim
dc.contributor.authorJabbour, Andrew
dc.contributor.authorOlivero, Ruperto
dc.contributor.authorRodríguez Palomares, José
dc.contributor.authorKooi, M. Eline
dc.contributor.authorPrieto Vásquez, Claudia
dc.contributor.authorBotnar, René Michael
dc.date.accessioned2025-06-25T20:49:15Z
dc.date.available2025-06-25T20:49:15Z
dc.date.issued2025
dc.description.abstractBACKGROUND: 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 ECG-triggered free-breathing respiratory motion-corrected 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 nnU-Net for bright-blood (lumen) and black-blood image sets (lumen and vessel wall). Training consisted of a 70:20:10% training: validation: testing split. Inference was run on datasets (single vendor) from different centres (UK, Spain, and Australia), sequences (iT2PrepIR-BOOST, T2 prepared CMRA, and TWIST MRA), acquired resolutions (from 0.9 mm 3 to 3 mm 3), 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 mm 3) and 3D CMRA datasets (0.9 mm 3) 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 mm 3) at 1.5T (Barcelona dataset). DSC and IoU score 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.
dc.description.funderKing’s BHF Centre for Award Excellence; Folio: RE/24/130035, RG/20/1/34802
dc.description.funderEPSRC; Folio: EP/V044087/1
dc.description.funderWellcome EPSRC Centre for Medical Engineering; Folio: NS/A000049/1
dc.description.funderMillennium Institute for Intelligent Healthcare Engineering; Folio: ICN2021_004
dc.description.funderFONDECYT; Folios: 1210637, 1210638
dc.description.funderIMPACT, Center of Interventional Medicine for Precision and Advanced Cellular Therapy/ANID—Basal funding for Scientific and Technological Center of Excellence; Folio: FB210024
dc.description.funderDepartment of Health through the National Institute for Health Research (NIHR)/ comprehensive Biomedical Research Centre award
dc.description.funderNIHR Cardiovascular MedTech Co-operative
dc.description.funderTechnical University of Munich – Institute for Advanced Study
dc.fechaingreso.objetodigital2025-06-26
dc.fuente.origenORCID
dc.identifier.doi10.1016/j.jocmr.2025.101923
dc.identifier.eissn1532-429X
dc.identifier.issn1097-6647
dc.identifier.urihttps://doi.org/10.1016/j.jocmr.2025.101923
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/104758
dc.information.autorucInstituto de Ingeniería Biológica y Médica; Castillo Passi, Carlos; 0000-0001-6227-0477; 204150
dc.information.autorucInstituto de Ingeniería Biológica y Médica; Botnar, René Michael; 0000-0003-2811-2509; 1015313
dc.information.autorucEscuela de Ingeniería; Prieto Vásquez, Claudia; 0000-0003-4602-2523; 14195
dc.language.isoen
dc.nota.accesocontenido completo
dc.revistaJournal of Cardiovascular Magnetic Resonance
dc.rightsacceso abierto
dc.rights.licenseAttribution 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectAorta
dc.subjectAortic Disease
dc.subjectMagnetic Resonance Angiography
dc.subjectSegmentation
dc.subjectDeep-Learningnn
dc.subjectU-Net
dc.subject.ddc610
dc.subject.deweyMedicina y saludes_ES
dc.subject.ods03 Good health and well-being
dc.subject.odspa03 Salud y bienestar
dc.titleAutomated Segmentation of Thoracic Aortic Lumen and Vessel Wall on 3D Bright- and Black-Blood MRI using nnU-Net
dc.typepreprint
sipa.codpersvinculados204150
sipa.codpersvinculados1015313
sipa.codpersvinculados14195
sipa.trazabilidadORCID;2025-06-23
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
S1097664725000857.htm
Size:
213.19 KB
Format:
Hypertext Markup Language
Description:
Download
Collections
Artículos de revistas