Tang Jiajie, Liang Yongen, Jiang Yuxuan, Liu Jinrong, Zhang Rui, Huang Danping, Pang Chengcheng, Huang Chen, Luo Dongni, Zhou Xue, Li Ruizhuo, Zhang Kanghui, Xie Bingbing, Hu Lianting, Zhu Fanfan, Xia Huimin, Lu Long, Wang Hongying
Department of Medical Ultrasonics/Institute of Pediatrics, Guangzhou Women and Children's Medical Center, Guangzhou Medical University, Guangzhou, China.
School of Information Management, Wuhan University, Wuhan, China.
NPJ Digit Med. 2023 Aug 12;6(1):143. doi: 10.1038/s41746-023-00883-y.
Duct-dependent congenital heart diseases (CHDs) are a serious form of CHD with a low detection rate, especially in underdeveloped countries and areas. Although existing studies have developed models for fetal heart structure identification, there is a lack of comprehensive evaluation of the long axis of the aorta. In this study, a total of 6698 images and 48 videos are collected to develop and test a two-stage deep transfer learning model named DDCHD-DenseNet for screening critical duct-dependent CHDs. The model achieves a sensitivity of 0.973, 0.843, 0.769, and 0.759, and a specificity of 0.985, 0.967, 0.956, and 0.759, respectively, on the four multicenter test sets. It is expected to be employed as a potential automatic screening tool for hierarchical care and computer-aided diagnosis. Our two-stage strategy effectively improves the robustness of the model and can be extended to screen for other fetal heart development defects.
依赖导管的先天性心脏病（CHD）是一种严重的CHD形式，检出率较低，尤其是在不发达国家和地区。尽管现有研究已经开发出用于胎儿心脏结构识别的模型，但缺乏对主动脉长轴的全面评估。在本研究中，共收集了6698张图像和48段视频，以开发和测试一种名为DDCHD-DenseNet的两阶段深度迁移学习模型，用于筛查严重的依赖导管的CHD。该模型在四个多中心测试集上的灵敏度分别为0.973、0.843、0.769和0.759，特异性分别为0.985、0.967、0.956和0.759。有望作为一种潜在的自动筛查工具，用于分级护理和计算机辅助诊断。我们的两阶段策略有效地提高了模型的鲁棒性，并且可以扩展到筛查其他胎儿心脏发育缺陷。
