欢迎来到《四川大学学报(医学版)》
师轲, 李颖, 张天静, 等. 基于未增强T1 mapping的深度学习模型早期评价肥厚型心肌病心肌纤维化的初步研究[J]. 四川大学学报(医学版), 2021, 52(5): 819-824. DOI: 10.12182/20210960506
引用本文: 师轲, 李颖, 张天静, 等. 基于未增强T1 mapping的深度学习模型早期评价肥厚型心肌病心肌纤维化的初步研究[J]. 四川大学学报(医学版), 2021, 52(5): 819-824. DOI: 10.12182/20210960506
SHI Ke, LI Ying, ZHANG Tian-jing, et al. Early Assessment of Myocardial Fibrosis of Hypertrophic Cardiomyopathy with Native-T1-Mapping-Based Deep Learning: A Preliminary Study[J]. Journal of Sichuan University (Medical Sciences), 2021, 52(5): 819-824. DOI: 10.12182/20210960506
Citation: SHI Ke, LI Ying, ZHANG Tian-jing, et al. Early Assessment of Myocardial Fibrosis of Hypertrophic Cardiomyopathy with Native-T1-Mapping-Based Deep Learning: A Preliminary Study[J]. Journal of Sichuan University (Medical Sciences), 2021, 52(5): 819-824. DOI: 10.12182/20210960506

基于未增强T1 mapping的深度学习模型早期评价肥厚型心肌病心肌纤维化的初步研究

Early Assessment of Myocardial Fibrosis of Hypertrophic Cardiomyopathy with Native-T1-Mapping-Based Deep Learning: A Preliminary Study

  • 摘要:
      目的   通过深度学习(deep learning, DL)模型分析心脏磁共振检查中不伴有心肌延迟强化(late gadolinium enhancement, LGE)的肥厚型心肌病(hypertrophic cardiomyopathy, HCM)未增强T1 mapping图像,探讨其早期识别心肌间质性纤维化的能力。
      方法   纳入接受心脏磁共振检查的60例HCM患者及44例正常对照者,以有无LGE判断并标记对应的未增强T1 mapping图像,将其与正常对照者的未增强T1 mapping图像经过预处理后作为矩阵形式输入SE-ResNext-50模型进行训练、验证及测试。
      结果   总共241幅未增强T1 mapping图像输入SE-ResNext-50模型,该模型识别测试集中LGE(−)未增强T1 mapping图像的特异性0.87,敏感性0.79,曲线下面积0.83(P<0.05)。
      结论   基于SE-ResNext-50的DL模型可较准确地识别LGE(−)未增强T1 mapping图像,可在不依赖对比剂的情况下早期发现HCM心肌纤维化。

     

    Abstract:
      Objective  To explore the diagnostic performance of deep learning (DL) model in early detection of the interstitial myocardial fibrosis using native T1 maps of hypertrophic cardiomyopathy (HCM) without late gadolinium enhancement (LGE).
      Methods  Sixty HCM patients and 44 healthy volunteers who underwent cardiac magnetic resonance were enrolled in this study. Each native T1 map was labeled according to its LGE status. Then, native T1 maps of LGE (−) and those of the controls were preprocessed and entered in the SE-ResNext-50 model as the matrix for the DL model for training, validation and testing.
      Results  A total of 241 native T1 maps were entered in the SE-ResNext-50 model. The model achieved a specificity of 0.87, sensitivity of 0.79, and area under curve (AUC) of 0.83 (P<0.05) in distinguishing native T1 maps of LGE (−) from those of the controls in the testing set.
      Conclusion  The DL model based on SE-ResNext-50 could be used for identifying native T1 maps of LGE (−) with relatively high accuracy. It is a promising approach for early detection of myocardial fibrosis in HCM without the use of contrast agent.

     

© 2021 《四川大学学报(医学版)》编辑部 版权所有 cc

开放获取 本文遵循知识共享署名—非商业性使用4.0国际许可协议(CC BY-NC 4.0),允许第三方对本刊发表的论文自由共享(即在任何媒介以任何形式复制、发行原文)、演绎(即修改、转换或以原文为基础进行创作),必须给出适当的署名,提供指向本文许可协议的链接,同时标明是否对原文作了修改;不得将本文用于商业目的。CC BY-NC 4.0许可协议详情请访问 https://creativecommons.org/licenses/by-nc/4.0

/

返回文章
返回