基于人工智能的左心房后空间比诊断胎儿完全性肺静脉异位连接。
Diagnosis of fetal total anomalous pulmonary venous connection based on the post-left atrium space ratio using artificial intelligence.
机构信息
Echocardiography Medical Center, Beijing Anzhen Hospital, Capital Medical University, Beijing, China.
Maternal-Fetal Medicine Center in Fetal Heart Disease, Beijing Anzhen Hospital, Beijing, China.
出版信息
Prenat Diagn. 2022 Sep;42(10):1323-1331. doi: 10.1002/pd.6220. Epub 2022 Aug 19.
OBJECTIVE
To explore whether the post-left atrium space (PLAS) ratio would be useful for prenatal diagnosis of total anomalous pulmonary venous connection (TAPVC) using echocardiography and artificial intelligence.
METHODS
We retrospectively included 642 frames of four-chamber views from 319 fetuses (32 with TAPVC and 287 without TAPVC) in end-systolic and end-diastolic periods with multiple apex directions. The average gestational age was 25.6 ± 2.7 weeks. No other cardiac or extracardiac malformations were observed. The dataset was divided into a training set (n = 540; 48 with TAPVC and 492 without TAPVC) and test set (n = 102; 20 with TAPVC and 82 without TAPVC). The PLAS ratio was defined as the ratio of the epicardium-descending aortic distance to the center of the heart-descending aortic distance. Supervised learning was used in DeepLabv3+, FastFCN, PSPNet, and DenseASPP segmentation models. The area under the curve (AUC) was used on the test set.
RESULTS
Expert annotations showed that this ratio was not related to the period or apex direction. It was higher in the TAPVC group than in the control group detected by the expert and the four models. The AUC of expert annotations, DeepLabv3+, FastFCN, PSPNet, and DenseASPP were 0.977, 0.941, 0.925, 0.856, and 0.887, respectively.
CONCLUSION
Segmentation models achieve good diagnostic accuracy for TAPVC based on the PLAS ratio.
目的
探讨利用超声心动图和人工智能技术，通过测量左心房后空间（PLAS）比率，能否有助于产前诊断完全性肺静脉异位连接（TAPVC）。
方法
我们回顾性纳入了 319 例胎儿（TAPVC 组 32 例，无 TAPVC 组 287 例）共 642 帧四腔心切面的收缩末期和舒张末期图像，且这些图像具有多种心尖方向。平均孕龄为 25.6±2.7 周。未观察到其他心脏或心脏外畸形。数据集分为训练集（n=540；TAPVC 组 48 例，无 TAPVC 组 492 例）和测试集（n=102；TAPVC 组 20 例，无 TAPVC 组 82 例）。PLAS 比率定义为心外膜至降主动脉距离与心脏中心至降主动脉距离的比值。在 DeepLabv3+、FastFCN、PSPNet 和 DenseASPP 分割模型中使用有监督学习。在测试集上使用曲线下面积（AUC）。
结果
专家标注结果显示，该比值与心动周期或心尖方向无关。专家和四个模型均检测到 TAPVC 组的比值高于对照组。专家标注、DeepLabv3+、FastFCN、PSPNet 和 DenseASPP 的 AUC 分别为 0.977、0.941、0.925、0.856 和 0.887。
结论
基于 PLAS 比率，分割模型对 TAPVC 的诊断准确性较好。
Zotero 插件