Feasibility and Reproducibility of Fetal Lung Texture Analysis by Automatic Quantitative Ultrasound Analysis and Correlation with Gestational Age

Abstract

Objective: To evaluate the feasibility and reproducibility of fetal lung texture analysis using a novel automatic quantitative ultrasound analysis and to assess its correlation with gestational age. Methods: Prospective cross-sectional observational study. To evaluate texture features, 957 left and right lung images in a 2D four-cardiac-chamber view plane were previously delineated from fetuses between 20 and 41 weeks of gestation. Quantification of lung texture was performed by the Automatic Quantitative Ultrasound Analysis (AQUA) software to extract image features. A standard learning approach composed of feature transformation and a regression model was used to evaluate the association between texture features and gestational age. Results: The association between weeks of gestation and fetal lung texture quantified by the AQUA software presented a Pearson correlation of 0.97. The association was not influenced by delineation parameters such as region of interest (ROI) localization, ROI size, right/left lung selected or sonographic parameters such as ultrasound equipment or transducer used. Conclusions: Fetal lung texture analysis measured by the AQUA software demonstrated a strong correlation with gestational age. This supports further research to explore the use of this technology to the noninvasive prediction of fetal lung maturity.

Prediction of neonatal respiratory morbidity by quantitative ultrasound lung texture analysis: a multicenter study

“…The method used herein is based on the combination of texture extraction with machine learning methods, allowing the identification of texture patterns in the ultrasound image that correlate with the clinical outcome. This approach has been shown to be reliable and robust to small variations in the conditions of the image acquisition, including depth and changes in the gain of the image, and does not need other tissues with which to be compared (placenta, fetal liver…) [20]. Additionally, a previous pilot study reported on the ability of this non-invasive technology to predict NRM [22].…”

“…Quantitative texture analysis is a powerful technique that can be used to extract information from medical images and to quantify tissue changes not visible to the human eye, allowing the training of computer programs that may predict clinical events [18, 19]. Earlier studies reported that texture analysis can be applied to fetal lung ultrasound images and to correlate with both gestational age [20] and the results of fetal lung maturity testing of the amniotic fluid [21]. In a recent single-center study, we tested software based on quantitative texture analysis of the fetal lung (quantusFLM) trained to predict NRM.…”

Quantitative Analysis of the Cervical Texture by Ultrasound and Correlation with Gestational Age

“…Texture analysis by ultrasound or magnetic resonance has also been investigated in the field of foetal and perinatal medicine [13,14] . Recently, quantitative texture analysis of foetal lung ultrasound images has proven to be a predictor of neonatal respiratory morbidity [15][16][17] . The aim of this study was to evaluate the feasibility of quantitative analysis of cervical ultrasound images to evaluate cervical tissue changes throughout pregnancy.…”

Fetal Brain MRI Texture Analysis Identifies Different Microstructural Patterns in Adequate and Small for Gestational Age Fetuses at Term

“…We have reported our experience using a TA software that was initially applied on ultrasound images showing the ability to predict white matter damage in subclinical stages on preterm neonatal brain scans with a high accuracy [35]. In addition, the software has demonstrated a strong correlation between fetal lung ultrasound texture features and gestational age (GA) [36]. We hypothesized that TA could also be used to detect different patterns in fetal brain MR images.…”