Quantitative ultrasound texture analysis of fetal lungs to predict neonatal respiratory morbidity

Quantitative ultrasound texture analysis of fetal lungs to predict neonatal respiratory morbidity
复制标题

DOI:
10.1002/uog.13441
复制
发表时间:
2015-04-01
影响因子:
7.1
通讯作者:
Gratacos, E.
Gratacos, E.
中科院分区:
医学1区
文献类型:
--
作者:
Bonet-Carne, E.;Palacio, M.;Gratacos, E.

文献摘要

被引文献

相似文献

目的 开发一种基于超声定量分析胎儿肺部来预测新生儿呼吸道疾病的新方法并评估其性能。方法使用超过 13 000 个非临床图像和 900 个胎儿肺部图像来开发基于纹理分析和机器学习算法的计算机化方法,并训练用于预测胎儿肺部超声图像上的新生儿呼吸道疾病风险。该方法被称为“定量超声胎肺成熟度分析”(quantusFLM (TM)),然后在 144 名妊娠 28 + 0 至 39 + 0 周的新生儿中进行盲法验证。在分娩后 48 小时内获得 DICOM 格式的肺部超声图像,并确定该软件预测新生儿呼吸系统疾病(定义为新生儿呼吸窘迫综合征或短暂性呼吸急促)的能力。 结果 分娩时平均 (SD) 胎龄为 36 + 1 (3 + 3) 周。 144名新生儿中,有29例(20.1%)新生儿呼吸道疾病。定量纹理分析预测新生儿呼吸道疾病的敏感性、特异性、阳性预测值和阴性预测值分别为 86.2%、87.0%、62.5% 和 96.2%。 结论 定量超声胎肺成熟度分析预测新生儿呼吸道疾病的准确性与目前使用羊水的测试相当。版权所有 (C) 2014 ISUOG。由约翰·威利父子有限公司出版
Objective To develop and evaluate the performance of a novel method for predicting neonatal respiratory morbidity based on quantitative analysis of the fetal lung by ultrasound.Methods More than 13 000 non-clinical images and 900 fetal lung images were used to develop a computerized method based on texture analysis and machine learning algorithms, trained to predict neonatal respiratory morbidity risk on fetal lung ultrasound images. The method, termed 'quantitative ultrasound fetal lung maturity analysis' (quantusFLM (TM)), was then validated blindly in 144 neonates, delivered at 28 + 0 to 39 + 0 weeks' gestation. Lung ultrasound images in DICOM format were obtained within 48 h of delivery and the ability of the software to predict neonatal respiratory morbidity, defined as either respiratory distress syndrome or transient tachypnea of the newborn, was determined.Results Mean (SD) gestational age at delivery was 36 + 1 (3 + 3) weeks. Among the 144 neonates, there were 29 (20.1%) cases of neonatal respiratory morbidity. Quantitative texture analysis predicted neonatal respiratory morbidity with a sensitivity, specificity, positive predictive value and negative predictive value of 86.2%, 87.0%, 62.5% and 96.2%, respectively.Conclusions Quantitative ultrasound fetal lung maturity analysis predicted neonatal respiratory morbidity with an accuracy comparable to that of current tests using amniotic fluid. Copyright (C) 2014 ISUOG. Published by John Wiley & Sons Ltd.