Vergani Vittoria, Razavi Reza, Puyol-Antón Esther, Ruijsink Bram
School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom.
Department of Adult and Paediatric Cardiology, Guy's and St. Thomas' NHS Foundation Trust, London, United Kingdom.
Front Cardiovasc Med. 2021 Oct 14;8:742640. doi: 10.3389/fcvm.2021.742640. eCollection 2021.
Deep learning demonstrates great promise for automated analysis of CMR. However, existing limitations, such as insufficient quality control and selection of target acquisitions from the full CMR exam, are holding back the introduction of deep learning tools in the clinical environment. This study aimed to develop a framework for automated detection and quality-controlled selection of standard cine sequences images from clinical CMR exams, prior to analysis of cardiac function. Retrospective study of 3,827 subjects that underwent CMR imaging. We used a total of 119,285 CMR acquisitions, acquired with scanners of different magnetic field strengths and from different vendors (1.5T Siemens and 1.5T and 3.0T Phillips). We developed a framework to select one good acquisition for each conventional cine class. The framework consisted of a first pre-processing step to exclude still acquisitions; two sequential convolutional neural networks (CNN), the first (CNN) to classify acquisitions in standard cine views (2/3/4-chamber and short axis), the second (CNN) to classify acquisitions according to image quality and orientation; a final algorithm to select one good acquisition of each class. For each CNN component, 7 state-of-the-art architectures were trained for 200 epochs, with cross entropy loss and data augmentation. Data were divided into 80% for training, 10% for validation, and 10% for testing. CNN selected cine CMR acquisitions with accuracy ranging from 0.989 to 0.998. Accuracy of CNN reached 0.861 for 2-chamber, 0.806 for 3-chamber, and 0.859 for 4-chamber. The complete framework was presented with 379 new full CMR studies, not used for CNN training/validation/testing, and selected one good 2-, 3-, and 4-chamber acquisition from each study with sensitivity to detect erroneous cases of 89.7, 93.2, and 93.9%, respectively. We developed an accurate quality-controlled framework for automated selection of cine acquisitions prior to image analysis. This framework is robust and generalizable as it was developed on multivendor data and could be used at the beginning of a pipeline for automated cine CMR analysis to obtain full automatization from scanner to report.
深度学习在心脏磁共振成像（CMR）的自动分析方面展现出巨大潜力。然而，诸如质量控制不足以及从完整的CMR检查中选择目标采集数据等现有局限性，阻碍了深度学习工具在临床环境中的应用。本研究旨在开发一个框架，用于在分析心脏功能之前，从临床CMR检查中自动检测并通过质量控制选择标准电影序列图像。对3827名接受CMR成像的受试者进行回顾性研究。我们总共使用了119285次CMR采集数据，这些数据由不同磁场强度的扫描仪以及不同供应商（1.5T西门子和1.5T及3.0T飞利浦）采集。我们开发了一个框架，为每个传统电影序列类别选择一个优质采集数据。该框架包括第一步预处理，以排除静止的采集数据；两个连续的卷积神经网络（CNN），第一个（CNN）对标准电影序列视图（二腔、三腔、四腔和短轴）中的采集数据进行分类，第二个（CNN）根据图像质量和方向对采集数据进行分类；最后一个算法，为每个类别选择一个优质采集数据。对于每个CNN组件，使用7种最先进的架构训练200个轮次，采用交叉熵损失和数据增强。数据分为80%用于训练，10%用于验证，10%用于测试。CNN选择电影CMR采集数据的准确率在0.989至0.998之间。二腔视图的CNN准确率达到0.861，三腔视图为0.806，四腔视图为0.859。该完整框架应用于379项新的完整CMR研究（未用于CNN训练/验证/测试），并从每项研究中选择一个优质的二腔、三腔和四腔采集数据，检测错误病例的灵敏度分别为89.7%、93.2%和93.9%。我们开发了一个准确的、经过质量控制的框架，用于在图像分析之前自动选择电影序列采集数据。该框架具有鲁棒性且可推广，因为它是基于多供应商数据开发的，可用于自动电影CMR分析流程的开始阶段，以实现从扫描仪到报告的完全自动化。
