IEEE Trans Med Imaging. 2020 Apr;39(4):1206-1222. doi: 10.1109/TMI.2019.2946059. Epub 2019 Oct 7.
Fetal congenital heart disease (FHD) is a common and serious congenital malformation in children. In Asia, FHD birth defect rates have reached as high as 9.3%. For the early detection of birth defects and mortality, echocardiography remains the most effective method for screening fetal heart malformations. However, standard echocardiograms of the fetal heart, especially four-chamber view images, are difficult to obtain. In addition, the pathophysiological changes in fetal hearts during different pregnancy periods lead to ever-changing two-dimensional fetal heart structures and hemodynamics, and it requires extensive professional knowledge to recognize and judge disease development. Thus, research on the automatic screening for FHD is necessary. In this paper, we proposed a new model named DGACNN that shows the best performance in recognizing FHD, achieving a rate of 85%. The motivation for this network is to deal with the problem that there are insufficient training datasets to train a robust model. There are many unlabeled video slices, but they are tough and time-consuming to annotate. Thus, how to use these un-annotated video slices to improve the DGACNN capability for recognizing FHD, in terms of both recognition accuracy and robustness, is very meaningful for FHD screening. The architecture of DGACNN comprises two parts, that is, DANomaly and GACNN (Wgan-GP and CNN). DANomaly, similar to the ALOCC network, but incorporates cycle adversarial learning to train an end-to-end one-class classification (OCC) network that is more robust and has a higher accuracy than ALOCC in screening video slices. For the GACNN architecture, we use FCH (four chamber heart) video slices at around the end-systole, as screened by DANomaly, to train a WGAN-GP for the purpose of obtaining ideal low-level features that can robustly improve the FHD recognition accuracy. A few annotated video slices, as screened by DANomaly, can also be used for data augmentation so as to improve the FHD recognition further. The experiments show that the DGACNN outperforms other state-of-the-art networks by 1%-20% in recognizing FHD. A comparison experiment shows that the proposed network already outperforms the performance of expert cardiologists in recognizing FHD, reaching 84% in a test. Thus, the proposed architecture has high potential for helping cardiologists complete early FHD screenings.
胎儿先天性心脏病（FHD）是儿童中常见且严重的先天性畸形。在亚洲，FHD 出生缺陷率高达 9.3%。为了早期发现出生缺陷和死亡，超声心动图仍然是筛查胎儿心脏畸形最有效的方法。然而，胎儿心脏的标准超声心动图，特别是四腔心视图图像，很难获得。此外，胎儿心脏在不同妊娠时期的生理变化导致二维胎儿心脏结构和血液动力学不断变化，需要广泛的专业知识来识别和判断疾病的发展。因此，对 FHD 的自动筛查的研究是必要的。在本文中，我们提出了一种名为 DGACNN 的新模型，该模型在识别 FHD 方面表现出最佳性能，准确率达到 85%。该网络的动机是解决训练一个健壮模型的训练数据集不足的问题。有许多未标记的视频切片，但对它们进行注释既困难又耗时。因此，如何利用这些未标记的视频切片来提高 DGACNN 识别 FHD 的能力，无论是在识别准确率还是鲁棒性方面，对于 FHD 的筛查都非常有意义。DGACNN 的架构包括两部分，即 DANomaly 和 GACNN（Wgan-GP 和 CNN）。DANomaly 类似于 ALOCC 网络，但结合了循环对抗学习来训练一个端到端的一类分类（OCC）网络，该网络在筛查视频切片时比 ALOCC 更健壮，准确率更高。对于 GACNN 架构，我们使用 DANomaly 筛选出的 FCH（四腔心）视频切片在收缩末期左右，训练一个 WGAN-GP，目的是获得理想的低水平特征，能够稳健地提高 FHD 识别准确率。DANomaly 筛选出的少量标记视频切片也可用于数据扩充，以进一步提高 FHD 识别率。实验表明，DGACNN 在识别 FHD 方面的性能优于其他最先进的网络 1%-20%。对比实验表明，所提出的网络在识别 FHD 方面已经优于专家心脏病学家的表现，在测试中达到了 84%。因此，所提出的架构在帮助心脏病学家完成早期 FHD 筛查方面具有很高的潜力。
