Department of Thoracic and Cardiovascular Surgery, Mie University Graduate School of Medicine, Tsu, Mie, Japan.
Department of Pediatrics, Mie University Graduate School of Medicine, Tsu, Mie, Japan.
JAMA Cardiol. 2020 Apr 1;5(4):449-457. doi: 10.1001/jamacardio.2019.5620.
Chest radiography is a useful noninvasive modality to evaluate pulmonary blood flow status in patients with congenital heart disease. However, the predictive value of chest radiography is limited by the subjective and qualitive nature of the interpretation. Recently, deep learning has been used to analyze various images, but it has not been applied to analyzing chest radiographs in such patients.
To develop and validate a quantitative method to predict the pulmonary to systemic flow ratio from chest radiographs using deep learning.
DESIGN, SETTING, AND PARTICIPANTS: This retrospective observational study included 1031 cardiac catheterizations performed for 657 patients from January 1, 2005, to April 30, 2019, at a tertiary center. Catheterizations without the Fick-derived pulmonary to systemic flow ratio or chest radiography performed within 1 month before catheterization were excluded. Seventy-eight patients (100 catheterizations) were randomly assigned for evaluation. A deep learning model that predicts the pulmonary to systemic flow ratio from chest radiographs was developed using the method of transfer learning.
Whether the model can predict the pulmonary to systemic flow ratio from chest radiographs was evaluated using the intraclass correlation coefficient and Bland-Altman analysis. The diagnostic concordance rate was compared with 3 certified pediatric cardiologists. The diagnostic performance for a high pulmonary to systemic flow ratio of 2.0 or more was evaluated using cross tabulation and a receiver operating characteristic curve.
The study included 1031 catheterizations in 657 patients (522 males [51%]; median age, 3.4 years [interquartile range, 1.2-8.6 years]), in whom the mean (SD) Fick-derived pulmonary to systemic flow ratio was 1.43 (0.95). Diagnosis included congenital heart disease in 1008 catheterizations (98%). The intraclass correlation coefficient for the Fick-derived and deep learning-derived pulmonary to systemic flow ratio was 0.68, the log-transformed bias was 0.02, and the log-transformed precision was 0.12. The diagnostic concordance rate of the deep learning model was significantly higher than that of the experts (correctly classified 64 of 100 vs 49 of 100 chest radiographs; P = .02 [McNemar test]). For detecting a high pulmonary to systemic flow ratio, the sensitivity of the deep learning model was 0.47, the specificity was 0.95, and the area under the receiver operating curve was 0.88.
The present investigation demonstrated that deep learning-based analysis of chest radiographs predicted the pulmonary to systemic flow ratio in patients with congenital heart disease. These findings suggest that the deep learning-based approach may confer an objective and quantitative evaluation of chest radiographs in the congenital heart disease clinic.
胸部 X 线摄影是一种有用的非侵入性方法，可用于评估先天性心脏病患者的肺血流状态。然而，由于解释的主观性和定性性质，胸部 X 线摄影的预测价值有限。最近，深度学习已被用于分析各种图像，但尚未应用于分析此类患者的胸部 X 光片。
开发和验证一种使用深度学习从胸部 X 光片中预测肺至全身血流量比的定量方法。
设计、设置和参与者：这是一项回顾性观察研究，纳入了 2005 年 1 月 1 日至 2019 年 4 月 30 日在一家三级中心进行的 657 例患者的 1031 次心导管检查。排除无 Fick 衍生的肺至全身血流比或心导管检查前 1 个月内进行的胸部 X 光检查的患者。78 例患者（100 次心导管检查）被随机分配进行评估。使用迁移学习方法开发了一种从胸部 X 光片中预测肺至全身血流量比的深度学习模型。
使用组内相关系数和 Bland-Altman 分析评估模型是否可以从胸部 X 光片中预测肺至全身血流量比。将诊断一致性率与 3 位认证的儿科心脏病专家进行比较。使用交叉表和受试者工作特征曲线评估高肺至全身血流量比（2.0 或更高）的诊断性能。
该研究纳入了 657 例患者（522 例男性[51%]；中位年龄 3.4 岁[四分位间距 1.2-8.6 岁]）的 1031 次心导管检查，其中 Fick 衍生的肺至全身血流比平均（SD）为 1.43（0.95）。诊断包括 1008 次心导管检查中的先天性心脏病（98%）。Fick 衍生和深度学习衍生的肺至全身血流量比的组内相关系数为 0.68，对数偏倚为 0.02，对数精度为 0.12。深度学习模型的诊断一致性率明显高于专家（正确分类 100 个中的 64 个与 100 个中的 49 个胸部 X 光片；P = .02 [McNemar 检验]）。对于检测高肺至全身血流量比，深度学习模型的灵敏度为 0.47，特异性为 0.95，受试者工作特征曲线下面积为 0.88。
本研究表明，基于深度学习的胸部 X 线分析可预测先天性心脏病患者的肺至全身血流量比。这些发现表明，基于深度学习的方法可能为先天性心脏病临床提供对胸部 X 光片的客观和定量评估。
