Automated Segmentation of Thoracic Aortic Lumen and Vessel Wall on 3D Bright- and Black-Blood MRI using nnU-Net.
Authors
Affiliations (10)
Affiliations (10)
- School of Biomedical Engineering and Imaging Sciences, King's College 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 Netherlands.
- School of Biomedical Engineering and Imaging Sciences, King's College London, United Kingdom.
- School of Biomedical Engineering and Imaging Sciences, King's College London, United Kingdom; Clinical Research Group, Heart Research Institute, Newtown, Australia; Cardiology Department, St. Vincent's Hospital, Darlinghurst, Australia.
- School of Biomedical Engineering and Imaging Sciences, King's College London, United Kingdom; Institute of Biological and Medical Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile.
- School of Biomedical Engineering and Imaging Sciences, King's College London, United Kingdom; Department of Cardiology, Chelsea and Westminster Hospital NHS Foundation Trust.
- Cardiology Department, St. Vincent's Hospital, Darlinghurst, Australia; Victor Chang Cardiac Research Institute, Sydney, Australia.
- Department of Cardiology, Vall d'Hebron Hospital Universitari, Vall d'Hebron Barcelona Hospital Campus, Barcelona, Spain; Cardiovascular Diseases, Vall d'Hebron Institut de Recerca (VHIR), Vall d'Hebron Barcelona Hospital Campus, Barcelona, Spain; Department of Medicine, Universitat Autònoma de Barcelona, Bellaterra, Spain; CIBER de Enfermedades Cardiovasculares, Instituto de Salud Carlos III, Madrid, Spain.
- Department of Radiology and Nuclear Medicine, Maastricht University Medical Centre, Maastricht, the Netherlands; Cardiovascular Research Institute Maastricht (CARIM), Maastricht University, Maastricht, the Netherlands.
- School of Biomedical Engineering and Imaging Sciences, King's College London, United Kingdom; School of Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile; Millennium Institute for Intelligent Healthcare Engineering, Santiago, Chile.
- School of Biomedical Engineering and Imaging Sciences, King's College 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. Electronic address: [email protected].
Abstract
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. 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<sup>3</sup> to 3 mm<sup>3</sup>), 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). The optimal configuration was the 3D U-Net. Bright blood segmentation at 1.5T on iT2PrepIR-BOOST datasets (1.3 and 1.8 mm<sup>3</sup>) and 3D CMRA datasets (0.9 mm<sup>3</sup>) 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<sup>3</sup>) 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. 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.