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

MedStar author(s):
Citation: Frontiers in Cardiovascular Medicine. 10:1213290, 2023.PMID: 37753166Institution: MedStar Health Research InstituteForm of publication: Journal ArticleMedline article type(s): Journal ArticleSubject headings: IN PROCESS -- NOT YET INDEXED | Year: 2023ISSN:
  • 2297-055X
Name of journal: Frontiers in cardiovascular medicineAbstract: Background: Late 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.Conclusions: The 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. Copyright © 2023 Gonzales, Ibanez, Hann, Popescu, Burrage, Lee, Altun, Weintraub, Kwong, Kramer, Neubauer, Ferreira, Zhang and Piechnik.Methods: A 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).Results: The 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.All authors: Gonzales RA, Ibanez DH, Hann E, Popescu IA, Burrage MK, Lee YP, Altun I, Weintraub WS, Kwong RY, Kramer CM, Neubauer S, Ferreira VM, Zhang Q, Piechnik SKFiscal year: FY2024Digital Object Identifier: Date added to catalog: 2023-12-20
Holdings
Item type Current library Collection Call number Status Date due Barcode
Journal Article MedStar Authors Catalog Article 37753166 Available 37753166

Background: Late 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.

Conclusions: The 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. Copyright © 2023 Gonzales, Ibanez, Hann, Popescu, Burrage, Lee, Altun, Weintraub, Kwong, Kramer, Neubauer, Ferreira, Zhang and Piechnik.

Methods: A 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).

Results: The 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.

English

Powered by Koha