Mariscal-Harana Jorge, Asher Clint, Vergani Vittoria, Rizvi Maleeha, Keehn Louise, Kim Raymond J, Judd Robert M, Petersen Steffen E, Razavi Reza, King Andrew P, Ruijsink Bram, Puyol-Antón Esther
School of Biomedical Engineering & Imaging Sciences Rayne Institute, 4th Floor, Lambeth Wing St. Thomas' Hospital Westminster Bridge Road London SE1 7EH.
Department of Adult and Paediatric Cardiology, Guy's and St Thomas' NHS Foundation Trust, Westminster Bridge Road, London SE1 7EH, London, UK.
Eur Heart J Digit Health. 2023 Jul 13;4(5):370-383. doi: 10.1093/ehjdh/ztad044. eCollection 2023 Oct.
Artificial intelligence (AI) techniques have been proposed for automating analysis of short-axis (SAX) cine cardiac magnetic resonance (CMR), but no CMR analysis tool exists to automatically analyse large (unstructured) clinical CMR datasets. We develop and validate a robust AI tool for start-to-end automatic quantification of cardiac function from SAX cine CMR in large clinical databases.
Our pipeline for processing and analysing CMR databases includes automated steps to identify the correct data, robust image pre-processing, an AI algorithm for biventricular segmentation of SAX CMR and estimation of functional biomarkers, and automated post-analysis quality control to detect and correct errors. The segmentation algorithm was trained on 2793 CMR scans from two NHS hospitals and validated on additional cases from this dataset ( = 414) and five external datasets ( = 6888), including scans of patients with a range of diseases acquired at 12 different centres using CMR scanners from all major vendors. Median absolute errors in cardiac biomarkers were within the range of inter-observer variability: <8.4 mL (left ventricle volume), <9.2 mL (right ventricle volume), <13.3 g (left ventricular mass), and <5.9% (ejection fraction) across all datasets. Stratification of cases according to phenotypes of cardiac disease and scanner vendors showed good performance across all groups.
We show that our proposed tool, which combines image pre-processing steps, a domain-generalizable AI algorithm trained on a large-scale multi-domain CMR dataset and quality control steps, allows robust analysis of (clinical or research) databases from multiple centres, vendors, and cardiac diseases. This enables translation of our tool for use in fully automated processing of large multi-centre databases.
已有人提出使用人工智能（AI）技术实现短轴（SAX）心脏磁共振成像（CMR）电影的自动化分析，但目前尚无用于自动分析大型（非结构化）临床CMR数据集的CMR分析工具。我们开发并验证了一种强大的AI工具，用于在大型临床数据库中对SAX心脏磁共振成像进行心脏功能的端到端自动定量分析。
我们用于处理和分析CMR数据库的流程包括自动识别正确数据、强大的图像预处理、用于SAX CMR双心室分割和功能生物标志物估计的AI算法，以及用于检测和纠正错误的自动分析后质量控制。分割算法在来自两家英国国家医疗服务体系（NHS）医院的2793次CMR扫描上进行训练，并在该数据集的其他病例（n = 414）和五个外部数据集（n = 6888）上进行验证，包括使用所有主要供应商的CMR扫描仪在12个不同中心获取的一系列疾病患者的扫描数据。所有数据集中，心脏生物标志物的中位数绝对误差在观察者间变异性范围内：左心室容积<8.4 mL，右心室容积<9.2 mL，左心室质量<13.3 g，射血分数<5.9%。根据心脏病表型和扫描仪供应商对病例进行分层，结果显示所有组的性能均良好。
我们表明，我们提出的工具结合了图像预处理步骤、在大规模多域CMR数据集上训练的通用AI算法和质量控制步骤，能够对来自多个中心、供应商和心脏病的（临床或研究）数据库进行可靠分析。这使得我们的工具能够转化用于大型多中心数据库的全自动处理。
