Gonzales Ricardo A, Ibáñez Daniel H, Hann Evan, Popescu Iulia A, Burrage Matthew K, Lee Yung P, Altun İbrahim, Weintraub William S, Kwong Raymond Y, Kramer Christopher M, Neubauer Stefan, Ferreira Vanessa M, Zhang Qiang, Piechnik Stefan K
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.
Front Cardiovasc Med. 2023 Sep 11;10:1213290. doi: 10.3389/fcvm.2023.1213290. eCollection 2023.
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.
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).
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: ; VNE: ; ). 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 (, ) emphasising the accuracy of the quality control-driven strategy in predicting segmentation quality in clinical settings. Overall, no statistical difference () was found when comparing the LGE and VNE test sets across all experiments.
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.
延迟钆增强（LGE）心血管磁共振（CMR）成像是非侵入性心肌组织特征分析的金标准。然而，由于训练数据有限且缺乏质量控制，左心室（LV）心肌的准确分割仍然是一个挑战。本研究通过利用生成对抗网络（GAN）生成的虚拟原生增强（VNE）图像来扩展训练集，并纳入一个自动质量控制驱动（QCD）框架来提高分割的可靠性，从而解决这些问题。
使用一个包含4716幅LGE图像（来自1363例肥厚型心肌病和心肌梗死患者）的数据集进行开发。为了生成更多经过临床验证的数据，使用基于GAN的生成器对LGE数据进行增强，以生成VNE图像。临床观察者在这些图像上手动勾勒出LV轮廓。为了创建多样化的候选分割，QCD框架涉及多个U-Net，这些U-Net使用统计秩滤波器进行组合。该框架预测每个候选分割的骰子相似系数（DSC），预测DSC最高的表示最准确和可靠的结果。在LGE和VNE测试数据集（来自103例患者的309幅LGE/VNE图像）上评估QCD集成框架的性能，评估分割准确性（DSC）和质量预测（平均绝对误差（MAE）和二元分类准确性）。
QCD框架在LGE和VNE图像上均能有效且快速地分割LV心肌（每张图像<1秒），在两个测试数据集上均表现出稳健的性能，平均DSC相似（LGE： ；VNE： ； ）。将GAN生成的VNE数据纳入训练过程始终能提高单个模型和整体框架的性能。质量控制机制产生了高性能（ ， ），强调了质量控制驱动策略在临床环境中预测分割质量的准确性。总体而言，在所有实验中比较LGE和VNE测试集时未发现统计学差异（ ）。
利用GAN生成的VNE数据和自动质量控制机制的QCD集成框架显著提高了LGE分割的准确性和可靠性，为常规临床应用中增强和可问责的诊断成像铺平了道路。
