简介：AbstractBackground:Prenatal evaluation of fetal lung maturity (FLM) is a challenge, and an effective non-invasive method for prenatal assessment of FLM is needed. The study aimed to establish a normal fetal lung gestational age (GA) grading model based on deep learning (DL) algorithms, validate the effectiveness of the model, and explore the potential value of DL algorithms in assessing FLM.Methods:A total of 7013 ultrasound images obtained from 1023 normal pregnancies between 20 and 41 + 6 weeks were analyzed in this study. There were no pregnancy-related complications that affected fetal lung development, and all infants were born without neonatal respiratory diseases. The images were divided into three classes based on the gestational week: class I: 20 to 29 + 6 weeks, class II: 30 to 36 + 6 weeks, and class III: 37 to 41 + 6 weeks. There were 3323, 2142, and 1548 images in each class, respectively. First, we performed a pre-processing algorithm to remove irrelevant information from each image. Then, a convolutional neural network was designed to identify different categories of fetal lung ultrasound images. Finally, we used ten-fold cross-validation to validate the performance of our model. This new machine learning algorithm automatically extracted and classified lung ultrasound image information related to GA. This was used to establish a grading model. The performance of the grading model was assessed using accuracy, sensitivity, specificity, and receiver operating characteristic curves.Results:A normal fetal lung GA grading model was established and validated. The sensitivity of each class in the independent test set was 91.7%, 69.8%, and 86.4%, respectively. The specificity of each class in the independent test set was 76.8%, 90.0%, and 83.1%, respectively. The total accuracy was 83.8%. The area under the curve (AUC) of each class was 0.982, 0.907, and 0.960, respectively. The micro-average AUC was 0.957, and the macro-average AUC was 0.949.Conclusions:The normal fetal lung GA grading model could accurately identify ultrasound images of the fetal lung at different GAs, which can be used to identify cases of abnormal lung development due to gestational diseases and evaluate lung maturity after antenatal corticosteroid therapy. The results indicate that DL algorithms can be used as a non-invasive method to predict FLM.

简介：AbstractBackground:Fetal weight is an important parameter to ensure maternal and child safety. The purpose of this study was to use three-dimensional (3D) limb volume ultrasound combined with fetal abdominal circumference (AC) measurement to establish a model to predict fetal weight and evaluate its efficiency.Methods:A total of 211 participants with single pregnancy (28-42 weeks) were selected between September 2017 and December 2018 in the Beijing Obstetrics and Gynecology Hospital of Capital Medical University. The upper arm (AVol)/thigh volume (TVol) of fetuses was measured by the 3D limb volume technique. Fetal AC was measured by two-dimensional ultrasound. Nine cases were excluded due to incomplete information or the interval between examination and delivery >7 days. The enrolled 202 participants were divided into a model group (134 cases, 70%) and a verification group (68 cases, 30%) by mechanical sampling method. The linear relationship between limb volume and fetal weight was evaluated using Pearson Chi-squared test. The prediction model formula was established by multivariate regression with data from the model group. Accuracy of the model formula was evaluated with verification group data and compared with traditional formulas (Hadlock, Lee2009, and INTERGROWTH-21st) by paired t-test and residual analysis. Receiver operating characteristic curves were generated to predict macrosomia.Results:AC, AVol, and TVol were linearly related to fetal weight. Pearson correlation coefficient was 0.866, 0.862, and 0.910, respectively. The prediction model based on AVol/TVol and AC was established as follows: Y=-481.965+ 12.194TVol + 15.358AVol + 67.998AC, R2adj = 0.868. The scatter plot showed that when birth weight fluctuated by 5% (i.e., 95% to 105%), the difference between the predicted fetal weight by the model and the actual weight was small. A paired t-test showed that there was no significant difference between the predicted fetal weight and the actual birth weight (t= -1.015, P = 0.314). Moreover, the residual analysis showed that the model formula’s prediction efficiency was better than the traditional formulas with a mean residual of 35,360.170. The combined model of AVol/TVol and AC was superior to the Lee2009 and INTERGROWTH-21st formulas in the diagnosis of macrosomia. Its predictive sensitivity and specificity were 87.5% and 91.7%, respectively.Conclusion:Fetal weight prediction model established by semi-automatic 3D limb volume combined with AC is of high accuracy, sensitivity, and specificity. The prediction model formula shows higher predictive efficiency, especially for the diagnosis of macrosomia.Trial Registration:ClinicalTrials.gov, NCT03002246; https://clinicaltrials.gov/ct2/show/NCT03002246?recrs=e&cond=fetal& draw=8&rank=67.