Large-scale, multi-vendor, multi-protocol, quality-controlled analysis of clinical cine CMR using artificial intelligence
Large-scale, multi-vendor, multi-protocol, quality-controlled analysis of clinical cine CMR using artificial intelligence
复制标题
使用人工智能对临床电影 CMR 进行大规模、多供应商、多协议、质量控制分析
DOI：
10.1093/ehjci/jeab090.046
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Mariscal Harana J
中科院分区：
文献类型：
--
作者：
Mariscal Harana J
资助确认资金来源类型：公共拨款(S)-仅限国家预算。主要资金来源(S)：伦敦国王学院EPSRC Impact Acceleration帐户的高级Impact奖励计划背景人工智能(AI)具有促进生物标志物提取的CMR分析自动化的潜力。然而，大多数人工智能算法都是在特定的输入域(例如，扫描仪供应商或医院定制的成像协议)上进行训练的，当应用于来自其他输入域的CMR数据时，缺乏健壮性来优化执行。目的开发和验证用于自动分割和心功能分析的健壮CMR分析工具，该工具能够获得最先进的多供应商短轴电影CMR图像的性能。方法本工作是我们之前发表的基于质量控制的基于AI的电影CMR分析工具的扩展[1]。我们部署了一种人工智能算法，该算法配备了自动处理不同图像大小和域的‘NNU-Net’框架[2]，并使用英国生物库队列人群(n = 4,872)和从两家国民保健系统医院获得的临床CMR研究的大型数据库(n = 3,406)重新训练了我们的工具。NHS医院的数据来自三种不同的扫描仪类型：西门子AERA 1.5T(n = 1,419)，飞利浦Achieva 1.5T和3T(n = 1,160)，以及飞利浦雌驼龙1.5T(n = 827)。用‘NNU-Net’分割脑室和心肌。所提出的方法是在随机选择的测试集上进行评估的，这些测试集来自英国国民健康保险制度(n = 488)和英国国民健康保险制度(n = 331)，以及在飞利浦、西门子、通用电气(GE)和佳能CMR扫描仪上获得的两个外部公开可用的临床CMR数据库-ACDC(n = 100)[3]和M&MS(n = 321)[4]。结果表1显示NHS、ACDC和M&MS扫描的Dice分数与高度受控、单一供应商和单场强UKBB扫描中获得的Dice分数相似。尽管我们的基于AI的工具仅针对两个供应商(飞利浦和西门子)的CMR扫描进行了培训，但它在看不见的供应商(GE和佳能)中的表现类似。此外，它在在线分段挑战中实现了最先进的性能，而不需要在这些数据库上进行专门的培训。表1还显示了手动和自动临床测量射血分数和心室容量和质量之间的良好一致性。结论我们表明，我们提出的基于人工智能的工具，将大规模多域CMR数据库上的训练与最先进的人工智能算法相结合，使我们能够稳健地处理来自多个中心、供应商和领域优势的常规临床数据。这是AI算法临床翻译的根本一步。此外，我们的方法在不增加计算成本的情况下产生了一系列额外的心脏功能指标(充盈和射血率、节段性室壁运动和应变)。
Funding AcknowledgementsType of funding sources: Public grant(s) – National budget only. Main funding source(s): Advancing Impact Award scheme of the EPSRC Impact Acceleration Account at King’s College LondonBackgroundArtificial intelligence (AI) has the potential to facilitate the automation of CMR analysis for biomarker extraction. However, most AI algorithms are trained on a specific input domain (e.g., scanner vendor or hospital-tailored imaging protocol) and lack the robustness to perform optimally when applied to CMR data from other input domains.PurposeTo develop and validate a robust CMR analysis tool for automatic segmentation and cardiac function analysis which achieves state-of-the-art performance for multi-vendor short-axis cine CMR images.MethodsThe current work is an extension of our previously published quality-controlled AI-based tool for cine CMR analysis [1]. We deployed an AI algorithm that is equipped to handle different image sizes and domains automatically - the ‘nnU-Net’ framework [2] - and retrained our tool using the UK Biobank (UKBB) cohort population (n = 4,872) and a large database of clinical CMR studies obtained from two NHS hospitals (n = 3,406). The NHS hospital data came from three different scanner types: Siemens Aera 1.5T (n = 1,419), Philips Achieva 1.5T and 3T (n = 1,160), and Philips Ingenia 1.5T (n = 827). The ‘nnU-net’ was used to segment both ventricles and the myocardium. The proposed method was evaluated on randomly selected test sets from UKBB (n = 488) and NHS (n = 331) and on two external publicly available databases of clinical CMRs acquired on Philips, Siemens, General Electric (GE), and Canon CMR scanners – ACDC (n = 100) [3] and M&Ms (n = 321) [4]. We calculated the Dice scores - which measure the overlap between manual and automatic segmentations - and compared manual vs AI-based measures of biventricular volumes and function.ResultsTable 1 shows that the Dice scores for the NHS, ACDC, and M&Ms scans are similar to those obtained in the highly controlled, single vendor and single field strength UKBB scans. Although our AI-based tool was only trained on CMR scans from two vendors (Philips and Siemens), it performs similarly in unseen vendors (GE and Canon). Furthermore, it achieves state-of-the-art performance in online segmentation challenges, without being specifically trained on these databases. Table 1 also shows good agreement between manual and automated clinical measures of ejection fraction and ventricular volume and mass.ConclusionsWe show that our proposed AI-based tool, which combines training on a large-scale multi-domain CMR database with a state-of-the-art AI algorithm, allows us to robustly deal with routine clinical data from multiple centres, vendors, and field strengths. This is a fundamental step for the clinical translation of AI algorithms. Moreover, our method yields a range of additional metrics of cardiac function (filling and ejection rates, regional wall motion, and strain) at no extra computational cost.Abstract Table 1