Skip to main content
QUICK REVIEW

[论文解读] Deep-learning models improve on community-level diagnosis for common congenital heart disease lesions

Rima Arnaout, Lara Curran|arXiv (Cornell University)|Sep 19, 2018
Congenital Heart Disease Studies参考文献 23被引用 25
一句话总结

本研究开发并评估了用于胎儿超声心动图中常见先天性心脏病——法洛四联症(TOF)和左心发育不良综合征(HLHS)——自动化产前诊断的深度学习模型。这些模型在识别关键心脏切面(F1分数:0.95)、检测TOF(敏感性75%,特异性76%)和HLHS(敏感性100%,特异性90%)方面表现出高准确率,显著优于社区层面的诊断水平。

ABSTRACT

Prenatal diagnosis of tetralogy of Fallot (TOF) and hypoplastic left heart syndrome (HLHS), two serious congenital heart defects, improves outcomes and can in some cases facilitate in utero interventions. In practice, however, the fetal diagnosis rate for these lesions is only 30-50 percent in community settings. Improving fetal diagnosis of congenital heart disease is therefore critical. Deep learning is a cutting-edge machine learning technique for finding patterns in images but has not yet been applied to prenatal diagnosis of congenital heart disease. Using 685 retrospectively collected echocardiograms from fetuses 18-24 weeks of gestational age from 2000-2018, we trained convolutional and fully-convolutional deep learning models in a supervised manner to (i) identify the five canonical screening views of the fetal heart and (ii) segment cardiac structures to calculate fetal cardiac biometrics. We then trained models to distinguish by view between normal hearts, TOF, and HLHS. In a holdout test set of images, F-score for identification of the five most important fetal cardiac views was 0.95. Binary classification of unannotated cardiac views of normal heart vs. TOF reached an overall sensitivity of 75% and a specificity of 76%, while normal vs. HLHS reached a sensitivity of 100% and specificity of 90%, both well above average diagnostic rates for these lesions. Furthermore, segmentation-based measurements for cardiothoracic ratio (CTR), cardiac axis (CA), and ventricular fractional area change (FAC) were compatible with clinically measured metrics for normal, TOF, and HLHS hearts. Thus, using guideline-recommended imaging, deep learning models can significantly improve detection of fetal congenital heart disease compared to the common standard of care.

研究动机与目标

  • 提高对严重先天性心脏病(如TOF和HLHS)的产前检出率,因为目前在社区环境中仅30–50%的病例能被确诊。
  • 开发深度学习模型,通过监督训练自动从超声心动图中识别标准胎儿心脏切面。
  • 评估这些模型在基于分类和基于分割的生物测量值(如心胸比CTR、心脏轴向CA、心室面积变化分数FAC)区分正常心脏与TOF和HLHS心脏方面的性能。
  • 评估深度学习是否能在常规社区级临床环境中,使诊断准确率超越当前临床实践。

提出的方法

  • 对2000年至2018年间收集的685例18–24周妊娠胎儿超声心动图进行回顾性分析。
  • 训练卷积神经网络和全卷积神经网络以检测五种标准胎儿心脏筛查切面。
  • 采用监督学习方法,将未标注的心脏切面分类为正常、TOF或HLHS。
  • 实施语义分割以测量关键生物测量指标:心胸比(CTR)、心脏轴向(CA)和心室面积变化分数(FAC)。
  • 在保留测试集上进行验证,以评估视图检测的F1分数、病变检测的敏感性和特异性。
  • 将模型生成的生物测量值与临床测量值进行比较,以评估其兼容性。

实验结果

研究问题

  • RQ1深度学习模型能否准确从超声心动图图像中识别出五种标准胎儿心脏切面?
  • RQ2深度学习模型在区分正常心脏与TOF或HLHS心脏方面的诊断表现如何?
  • RQ3基于分割的生物测量值(CTR、CA、FAC)与临床测量值相比表现如何?
  • RQ4深度学习模型在TOF和HLHS检测中的敏感性和特异性是否高于当前社区水平的诊断率?
  • RQ5深度学习在常规临床实践中对先天性心脏病的早期检测能提升到何种程度?

主要发现

  • 深度学习模型在从超声心动图中识别五种最重要胎儿心脏切面方面取得了0.95的F1分数。
  • 正常与TOF的二分类检测达到75%的敏感性和76%的特异性,优于典型社区级诊断表现。
  • 正常与HLHS的分类检测达到100%的敏感性和90%的特异性,显示出卓越的检测能力。
  • 基于分割的CTR、CA和FAC测量值与临床测量值在正常、TOF和HLHS心脏中具有良好的兼容性。
  • 该模型在HLHS检测方面表现尤为出色,敏感性达到完美,显示出极高的早期干预潜力。
  • 总体而言,深度学习方法在常见先天性心脏病病变的诊断中显著优于标准社区级诊断水平。

更好的研究,从现在开始

从论文设计到论文写作,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。