Quality control-driven deep ensemble for accountable automated segmentation of cardiac magnetic resonance LGE and VNE images

Frontiers in Cardiovascular Medicine

Cardiovascular Medicine

Raymond Y. Kwong¹  Christopher M. Kramer²  William S. Weintraub³  Vanessa M. Ferreira⁴  İbrahim Altun⁴  Evan Hann⁴  Yung P. Lee⁴  Qiang Zhang⁴  Iulia A. Popescu⁴  Stefan Neubauer⁴  Stefan K. Piechnik⁴  Ricardo A. Gonzales⁴  Daniel H. Ibáñez⁵  Matthew K. Burrage⁶ 

[1] Cardiovascular Division, Department of Medicine, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States;Department of Medicine, University of Virginia Health System, Charlottesville, VA, United States;MedStar Health Research Institute, Georgetown University, Washington, DC, United States;Oxford Centre for Clinical Magnetic Resonance Research (OCMR), Division of Cardiovascular Medicine, Radcliffe Department of Medicine, John Radcliffe Hospital, University of Oxford, Oxford, United Kingdom;Oxford Centre for Clinical Magnetic Resonance Research (OCMR), Division of Cardiovascular Medicine, Radcliffe Department of Medicine, John Radcliffe Hospital, University of Oxford, Oxford, United Kingdom;Artificio, Cambridge, MA, United States;Oxford Centre for Clinical Magnetic Resonance Research (OCMR), Division of Cardiovascular Medicine, Radcliffe Department of Medicine, John Radcliffe Hospital, University of Oxford, Oxford, United Kingdom;Faculty of Medicine, University of Queensland, Brisbane, QLD, Australia;

关键词: data augmentation;    generative adversarial networks;    quality control;    segmentation;    late gadolinium enhancement;    virtual native enhancement;    cardiovascular magnetic resonance;   

DOI  :  10.3389/fcvm.2023.1213290

 received in 2023-04-27, accepted in 2023-08-16,  发布年份 2023

来源: Frontiers

【 摘 要 】

BackgroundLate gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) imaging is the gold standard for non-invasive myocardial tissue characterisation. However, accurate segmentation of the left ventricular (LV) myocardium remains a challenge due to limited training data and lack of quality control. This study addresses these issues by leveraging generative adversarial networks (GAN)-generated virtual native enhancement (VNE) images to expand the training set and incorporating an automated quality control-driven (QCD) framework to improve segmentation reliability.MethodsA dataset comprising 4,716 LGE images (from 1,363 patients with hypertrophic cardiomyopathy and myocardial infarction) was used for development. To generate additional clinically validated data, LGE data were augmented with a GAN-based generator to produce VNE images. LV was contoured on these images manually by clinical observers. To create diverse candidate segmentations, the QCD framework involved multiple U-Nets, which were combined using statistical rank filters. The framework predicted the Dice Similarity Coefficient (DSC) for each candidate segmentation, with the highest predicted DSC indicating the most accurate and reliable result. The performance of the QCD ensemble framework was evaluated on both LGE and VNE test datasets (309 LGE/VNE images from 103 patients), assessing segmentation accuracy (DSC) and quality prediction (mean absolute error (MAE) and binary classification accuracy).ResultsThe QCD framework effectively and rapidly segmented the LV myocardium (<1 s per image) on both LGE and VNE images, demonstrating robust performance on both test datasets with similar mean DSC (LGE: 0.845±0.075; VNE: 0.845±0.071; p=ns). Incorporating GAN-generated VNE data into the training process consistently led to enhanced performance for both individual models and the overall framework. The quality control mechanism yielded a high performance (MAE=0.043, accuracy=0.951) emphasising the accuracy of the quality control-driven strategy in predicting segmentation quality in clinical settings. Overall, no statistical difference (p=ns) was found when comparing the LGE and VNE test sets across all experiments.ConclusionsThe QCD ensemble framework, leveraging GAN-generated VNE data and an automated quality control mechanism, significantly improved the accuracy and reliability of LGE segmentation, paving the way for enhanced and accountable diagnostic imaging in routine clinical use.

【 授权许可】

Unknown   
© 2023 Gonzales, Ibáñez, Hann, Popescu, Burrage, Lee, Altun, Weintraub, Kwong, Kramer, Neubauer, Ferreira, Zhang and Piechnik.