Chong Jun Hua, Abdulkareem Musa, Petersen Steffen E, Khanji Mohammed Y
National Heart Centre Singapore, Singapore; Cardiovascular Sciences Academic Clinical Programme, Duke-National University of Singapore Medical School, Singapore.
Barts Heart Centre, Barts Health National Health Service Trust, London, UK; National Institute for Health Research Barts Biomedical Research Centre, William Harvey Research Institute, Queen Mary University of London, London, UK; Health Data Research UK, London, UK.
Curr Probl Cardiol. 2022 Dec;47(12):101330. doi: 10.1016/j.cpcardiol.2022.101330. Epub 2022 Jul 21.
Cardiovascular magnetic resonance (CMR) is an important cardiac imaging tool for assessing the prognostic extent of myocardial injury after myocardial infarction (MI). Within the context of clinical trials, CMR is also useful for assessing the efficacy of potential cardioprotective therapies in reducing MI size and preventing adverse left ventricular (LV) remodelling in reperfused MI. However, manual contouring and analysis can be time-consuming with interobserver and intra-observer variability, which can in turn lead to reduction in accuracy and precision of analysis. There is thus a need to automate CMR scan analysis in MI patients to save time, increase accuracy, increase reproducibility and increase precision. In this regard, automated imaging analysis techniques based on artificial intelligence (AI) that are developed with machine learning (ML), and more specifically deep learning (DL) strategies, can enable efficient, robust, accurate and clinician-friendly tools to be built so as to try and improve both clinician productivity and quality of patient care. In this review, we discuss basic concepts of ML in CMR, important prognostic CMR imaging biomarkers in MI and the utility of current ML applications in their analysis as assessed in research studies. We highlight potential barriers to the mainstream implementation of these automated strategies and discuss related governance and quality control issues. Lastly, we discuss the future role of ML applications in clinical trials and the need for global collaboration in growing this field.
心血管磁共振成像（CMR）是评估心肌梗死（MI）后心肌损伤预后范围的重要心脏成像工具。在临床试验中，CMR对于评估潜在心脏保护疗法在减少MI面积和预防再灌注MI中左心室（LV）不良重塑方面的疗效也很有用。然而，手动勾勒轮廓和分析可能很耗时，且存在观察者间和观察者内的变异性，这进而可能导致分析的准确性和精确性降低。因此，需要对MI患者的CMR扫描分析进行自动化，以节省时间、提高准确性、增加可重复性和提高精确性。在这方面，基于人工智能（AI）开发的、采用机器学习（ML），更具体地说是深度学习（DL）策略的自动成像分析技术，可以构建高效、强大、准确且对临床医生友好的工具，以提高临床医生的工作效率和患者护理质量。在本综述中，我们讨论了CMR中ML的基本概念、MI中重要的预后CMR成像生物标志物以及研究中评估的当前ML应用在其分析中的效用。我们强调了这些自动化策略在主流实施方面的潜在障碍，并讨论了相关的管理和质量控制问题。最后，我们讨论了ML应用在临床试验中的未来作用以及在该领域发展中进行全球合作的必要性。
