Ultrasound-based radiomics for the evaluation of fetal rat lung maturity: A noninvasive assessment method (Ultrasound-based radiomics in fetal rat lung).

OBJECTIVE: To establish a classification model for the evaluation of rat fetal lung maturity (FLM) using radiomics technology. METHOD: A total of 430 high-throughput features were extracted per fetal lung image from 134 fetal lung ultrasound images (four-cardiac-chamber views) of 67 Sprague-Dawley (SD) fetal rats with a gestational age of 16-21 days. The detection of fetal lung tissues included histopathological staining and the expression of surface proteins SP-A, SP-B, and SP-C. A machine learning classification model was established using a support vector machine based on histopathological results to analyze the relationship between fetal lung texture characteristics and FLM. RESULTS: The rat fetal lungs were divided into two groups: terminal sac period (SD1) and canalicular period (SD2). The mRNA transcription and protein expression level of SP-C protein were significantly higher in the SD1 group than in the SD2 group (p < 0.05). The diagnostic performance of the rat FLM classification model was measured as follows: area under the receiver operating characteristic curve (AUC), 0.93 (training set) and 0.89 (validation set); sensitivity, 89.26% (training set) and 87.10% (validation set); specificity, 85.87% (training set) and 79.17% (validation set); and accuracy, 87.79% (training set) and 83.64% (validation set). CONCLUSION: Ultrasound-based radiomics technology can be used to evaluate the FLM of rats, which lays a foundation for further research on this technology in human fetal lungs.

Prenatal prediction of neonatal respiratory morbidity: a radiomics method based on imbalanced few-shot fetal lung ultrasound images.

BACKGROUND: To develop a non-invasive method for the prenatal prediction of neonatal respiratory morbidity (NRM) by a novel radiomics method based on imbalanced few-shot fetal lung ultrasound images. METHODS: A total of 210 fetal lung ultrasound images were enrolled in this study, including 159 normal newborns and 51 NRM newborns. Fetal lungs were delineated as the region of interest (ROI), where radiomics features were designed and extracted. Integrating radiomics features selected and two clinical features, including gestational age and gestational diabetes mellitus, the prediction model was developed and evaluated. The modelling methods used were data augmentation, cost-sensitive learning, and ensemble learning. Furthermore, two methods, which embed data balancing into ensemble learning, were employed to address the problems of imbalance and few-shot simultaneously. RESULTS: Our model achieved sensitivity values of 0.82, specificity values of 0.84, balanced accuracy values of 0.83 and area under the curve values of 0.87 in the test set. The radiomics features extracted from the ROIs at different locations within the lung region achieved similar classification performance outcomes. CONCLUSION: The feature set we designed can efficiently and robustly describe fetal lungs for NRM prediction. RUSBoost shows excellent performance compared to state-of-the-art classifiers on the imbalanced few-shot dataset. The diagnostic efficacy of the model we developed is similar to that of several previous reports of amniocentesis and can serve as a non-invasive, precise evaluation tool for NRM prediction.

Model application to quantitatively evaluate placental features from ultrasound images with gestational diabetes.

PURPOSE: The goal of this study was to introduce PFCnet (placental features classification network), an multimodel model for evaluating and classifying placental features in gestational diabetes mellitus (GDM) and normal late pregnancy. Deep learning algorithms could be utilized to fully automate the examination of alterations in the placenta caused by hyperglycemia. METHODS: A total of 718 placental ultrasound images, including 139 cases of GDM, were collected, including gray-scale images (GSIs) and microflow images (MFIs). Ultrasonic assessment parameters and perinatal features were recorded. We divided gestational age into two categories for analysis (37 weeks and 37 weeks) based on the cut-off value level of placental maturity. The PFCnet model was introduced for identifying placental characteristics from normal and GDM pregnancies after extensive training and optimization. The model was scored using metrics such as sensitivity, specificity, accuracy, and the area under the curve (AUC). RESULTS: In view of multimodal fusion (GSIs and MFIs) and deep network optimization training, the overall diagnostic performance of the PFCnet model depending on the region of interest (ROI) was excellent (AUC: 93%), with a sensitivity of 89%, a specificity of 92%, and an accuracy of 92% in the independent test set. The fusion features of GSIs and MFIs in the placenta showed a higher discriminative power than single-mode features (accuracy: Fusion 92% vs. GSIs 84% vs. MFIs 82%). The independent test set at 37 weeks exhibited a better specificity (75% vs. 69%) but a lower sensitivity(95% vs. 100%). CONCLUSIONS: With its dual channel identification of placental parenchymal and vascular lesions in obstetric complications, the PFCnet classification model has the potential to be a useful tool for detecting placental tissue abnormalities caused by hyperglycemia.

Abnormal placental perfusion and the risk of stillbirth: a hospital-based retrospective cohort study.

BACKGROUND: A lack of information on specific and interventional factors for stillbirth has made designing preventive strategies difficult, and the stillbirth rate has declined more slowly than the neonatal death rate. We compared the prevalence of stillbirth among the offspring of women with or without abnormal placental perfusion (APP). METHODS: We conducted a hospital-based retrospective cohort study involving women with a singleton pregnancy between 2012 and 2016 (N = 41,632). Multivariate analysis was performed to compare the prevalence of stillbirth in infants exposed to APP (defined as any abnormality in right or left uterine artery pulsatility index or resistance index [UtA-PI, -RI] [e.g., > 95th percentile] or presence of early diastolic notching) with that in those not exposed to APP. RESULTS: Stillbirths were more common among women with APP than among those with normal placental perfusion (stillbirth rate, 4.3 ‰ vs 0.9 ‰; odds ratio (OR), 4.2; 95% confidence interval (CI), 2.2 to 8.0). The association strengths were consistent across groups of infants exposed to APP that separately defined by abnormality in right or left UtA-PI or -RI (OR ranged from 3.2 to 5.3; all P ≤ 0.008). The associations were slightly stronger for the unexplained stillbirths. Most of the unexplained stillbirth risk was attributed to APP (59.0%), while a foetal sex disparity existed (94.5% for males and 58.0% for females). Women with normal placental perfusion and a male foetus had higher credibility (e.g., higher specificities) in excluding stillbirths than those with APP and a female foetus at any given false negative rate from 1 to 10% (93.4% ~ 94.1% vs. 12.3% ~ 14.0%). CONCLUSIONS: APP is associated with and accounts for most of the unexplained stillbirth risk. Different mechanisms exist between the sexes. The performance of screening for stillbirth may be improved by stratification according to sex and placental perfusion.

High maternal blood lipid levels during early pregnancy are associated with increased risk of congenital heart disease in offspring.

INTRODUCTION: This study aimed to investigate whether maternal blood lipid levels during early pregnancy are associated with the occurrence of congenital heart disease (CHD) in their offspring. MATERIAL AND METHODS: In this single-center case-control study, mothers of offspring with CHD (n = 230) and without CHD (n = 381) were included. Maternal lipid levels were determined on fasting blood samples taken in the first trimester. Relevant demographic and clinical data were extracted from the medical records. Maternal lipid profile was compared between the two groups, and regression analysis was performed to evaluate the association between lipid profile and CHD risk in offspring. RESULTS: Compared with the control group, levels of triglyceride, apolipoprotein-A1, and apolipoprotein-B in early pregnancy were significantly higher in the CHD group. Multivariate analyses showed that triglyceride (odds ratio [OR] 2.46, 95% CI 1.62-3.73, p < 0.01), total/high-density lipoprotein cholesterol (OR 2.10, 95% CI 1.07-4.13, p = 0.03), and apolipoprotein-A1 (OR 2.73, 95% CI 1.16-6.40, p = 0.02) were positively associated with CHD risk in offspring. CONCLUSIONS: Elevated maternal lipid profile was associated with increased risk of CHD in offspring.

Three-dimensional power Doppler ultrasonography indicates that increased placental blood perfusion during the third trimester is associated with the risk of macrosomia at birth.

PURPOSE: To investigate the association between placental blood perfusion and the occurrence of macrosomia at birth. METHODS: This was a prospective cohort study including women with singleton pregnancies that aimed to measure placental blood perfusion using three-dimensional (3D) power Doppler ultrasonography in the second and third trimester. We acquired three indices of placental blood flow, including vascularization index (VI), flow index (FI), vascularization flow index (VFI), along with routine two-dimensional (2D) biometric measurements, including abdominal circumference (AC) and estimated fetal weight (EFW). Pregnancy outcomes were divided into two groups: newborns with a normal birth weight and those with macrosomia. We then compared all of the recorded variables between these two groups. We also determined the predictive efficiency of each variable using receiver-operating characteristic (ROC) curves. RESULTS: The placental 3D power Doppler indices, including VI and FI, were significantly higher in the third trimester of pregnancies developing macrosomia, but not during the second trimester, as compared to those with a normal birth weight. ROC curves analysis for third-trimester VI and FI suggested a slight ability to predict macrosomia; this was also the case for AC and EFW. Interestingly, VI showed high sensitivity and low specificity, while FI showed low sensitivity and high specificity; this was also the case for AC and EFW. CONCLUSIONS: Three-dimensional power Doppler ultrasound indices were significantly higher during the third-trimester for pregnancies developing macrosomia. However, these indices had only moderate ability to predict macrosomia.

Association of abnormal placental perfusion with the risk of male hypospadias: a hospital-based retrospective cohort study.

BACKGROUND: The effect and extent of abnormal placental perfusion (APP) on the risk of male hypospadias are poorly understood. We compared the prevalence of male hypospadias in the offspring of women with APP and quantify the extent of the APP effect on the anomaly. METHODS: A hospital-based retrospective analysis of births from 2012 to 2016 was conducted in 2018. Women of singleton pregnancy and male infants born to them were included (N = 21,447). A multivariate analysis was performed to compare the prevalence of male hypospadias in infants exposed to APP with those that were not exposed to APP. RESULTS: Compared with the infants of women without APP, infants of women with APP showed an increased risk of male hypospadias (odds ratio, 2.40; 95% confidence interval, 1.09-5.29). The male hypospadias cumulative risk increased with the severity of APP. Infants exposed to severe APP had a significantly higher risk of male hypospadias than those without APP exposure (9.2 versus 1.7 per 1000 infants, P < 0.001). A path analysis indicated that 28.18-46.61% of the risk of hypospadias may be attributed to the effect of APP. CONCLUSIONS: Male hypospadias risk was associated with APP and increased with APP severity, as measured in the second trimester. APP had an important role in the development of the anomaly.

Ultrasonographic Findings of Uterine Carcinosarcoma.

AIMS: The aim of this study was to investigate the clinical features and ultrasonographic findings of uterine carcinosarcoma (UCS). METHODS: Seventy-five patients (mean age, 58.6 years) with pathologically proven UCS who were treated at our hospital from January 2003 to December 2015 were retrospectively recruited. The clinical features and preoperative findings on transvaginal sonography (TVS) were investigated. RESULTS: Eighty percent of the patients were postmenopausal. The primary symptoms were postmenopausal abnormal uterine bleeding (57.3%), irregular menstruation (18.7%), vaginal discharge (10.7%) and the presence of a uterine mass or others (13.3%). The tumor marker CA125 was evaluated in 43 women and was found to be elevated in 15 (34.9%); in 60% of those women (9/15), the CA125 level was lower than 200U/ml. According to the frequency of the different types of lesions observed by ultrasonic imaging, we decided to categorize the lesions into 3 different groups as follows: Group I, intrauterine tumors (73.33%); group II, intra-myometrial tumors (13.33%); and group III, intra-endometrial tumors (13.33 %). CONCLUSION: Combined with the clinical features, the characteristics demonstrated by TVS provide evidence for an indication of the presence of UCS and could contribute to clinical decision-making.

Absent fetal nasal bone in the second trimester and risk of abnormal karyotype in a prescreened population of Chinese women.

INTRODUCTION: The aim of this study was to evaluate the value of absent fetal nasal bone in the prediction of fetal chromosomal abnormalities, according to whether it was associated with other soft markers or structural abnormalities in a prescreened population of Chinese pregnant women. MATERIAL AND METHODS: In this retrospective cohort study, women whose fetuses had absent nasal bone detected during the second trimester ultrasound scan were followed. Fetal karyotyping was performed and pregnancy outcomes were recorded. The association between absent fetal nasal bone with abnormal karyotype was evaluated according to whether soft markers or structural abnormalities were also observed. RESULTS: Fetal nasal bone was assessed in 56 707 singleton pregnancies. After exclusion of unqualified cases, 71 (71/56 707, 0.13%) fetuses were included in the final analyses, of which 16 (16/71, 22.54%) were detected to have chromosomal abnormalities, including 12 cases of trisomy-21, three of trisomy-18, and one of micro-deletion (in 7q). Among the 42 cases with isolated absence of nasal bone, two had trisomy-21 and one had a micro-deletion. Absence of nasal bone in association with other structural abnormalities had a higher rate of abnormal karyotypes compared with isolated absence of nasal bone [83.33% (10/12) vs. 7.14% (3/42), Fisher's exact test χ2  = 25.620, p < 0.001]. CONCLUSION: Absent fetal nasal bone is a highly specific ultrasonographic soft marker that should be included in the routine second trimester ultrasound scan.

Prenatal diagnosis of congenital heart diseases by fetal echocardiography in second trimester: a Chinese multicenter study.

INTRODUCTION: The objective of our study was to evaluate the performance of detailed fetal echocardiography by skilled obstetric physician sonologists in the diagnosis of congenital heart disease (CHD) in a Chinese population. MATERIAL AND METHODS: This investigation included a multicenter prospective cohort of 10 259 pregnant women attending 10 regional tertiary hospitals in China. The inclusion criteria were singleton pregnancy and gestational age from 18 to ≤28 weeks. Women with multiple pregnancies were excluded. A detailed fetal echocardiography was performed by trained physicians with at least 3 years of experience. The primary outcome measures included sensitivity, specificity, and positive and negative likelihood ratios of detailed fetal echocardiography in prenatal detection of CHD. RESULTS: The sensitivity and specificity of fetal echocardiography in detecting any CHD were 33.9 and 99.8%, respectively, in the low-risk population, and 68.8 and 99.4%, respectively, in the high-risk population. For detecting major CHDs, fetal echocardiography had a high sensitivity and specificity, and satisfactory positive and negative likelihood ratios in both the low-risk population (88.2, 100%, 6947.7, and 0.118, respectively) and high-risk population (100, 99.9%, 833.3, and <0.0001, respectively). The sensitivity and likelihood ratios were substantially lower for detecting minor CHDs in both populations. CONCLUSIONS: Detailed fetal echocardiography performed by skilled physicians had high detection rate for major CHD in both low-risk and high-risk populations. However, its value for detecting minor CHD was limited. The incorporation of fetal echocardiography with multiple cardiac views into routine ultrasound screening may improve the detection rate of fetal major CHD and facilitate appropriate parental counseling.

Prospective prenatal cell-free DNA screening for genetic conditions of heterogenous etiologies.

Prenatal cell-free DNA (cfDNA) screening uses extracellular fetal DNA circulating in the peripheral blood of pregnant women to detect prevalent fetal chromosomal anomalies. However, numerous severe conditions with underlying single-gene defects are not included in current prenatal cfDNA screening. In this prospective, multicenter and observational study, pregnant women at elevated risk for fetal genetic conditions were enrolled for a cfDNA screening test based on coordinative allele-aware target enrichment sequencing. This test encompasses the following three of the most frequent pathogenic genetic variations: aneuploidies, microdeletions and monogenic variants. The cfDNA screening results were compared to invasive prenatal or postnatal diagnostic test results for 1,090 qualified participants. The comprehensive cfDNA screening detected a genetic alteration in 135 pregnancies with 98.5% sensitivity and 99.3% specificity relative to standard diagnostics. Of 876 fetuses with suspected structural anomalies on ultrasound examination, comprehensive cfDNA screening identified 55 (56.1%) aneuploidies, 6 (6.1%) microdeletions and 37 (37.8%) single-gene pathogenic variants. The inclusion of targeted monogenic conditions alongside chromosomal aberrations led to a 60.7% increase (from 61 to 98) in the detection rate. Overall, these data provide preliminary evidence that a comprehensive cfDNA screening test can accurately identify fetal pathogenic variants at both the chromosome and single-gene levels in high-risk pregnancies through a noninvasive approach, which has the potential to improve prenatal evaluation of fetal risks for severe genetic conditions arising from heterogenous molecular etiologies. ClinicalTrials.gov registration: ChiCTR2100045739 .

Laparoscopic-assisted uterovaginal anastomosis for uterine cervix atresia with vaginal aplasia using a silicone stent lined with acellular porcine small intestinal submucosa graft inserted using a 16F Foley catheter.

Herein is reported a novel technique for cervical reconstruction of congenital cervicovaginal atresia. The patient was a 16-year-old girl with congenital atresia of the cervix and vagina, didelphic uterus, and right hematosalpinx. At laparoscopic-assisted creation of a neocervix, a silicone stent was inserted using a 16F Foley catheter and lined with an acellular porcine small intestinal submucosa graft under ultrasound guidance. At 3-month clinical follow-up after placement of the stent, the patient had regular menstrual flow. The neocervix was completely mucosalized on the inner surface at 4 months after surgery. There were no complications related to the silicone stent or the cervical stent. Cervical reconstruction using a vaginal mucosa-lined silicone stent is accessible and effective, and provides an alternative option to preserve reproductive potential in patients with cervicovaginal atresia.

Potential role of strain elastography for detection of the extent of large-scar endometriosis.

OBJECTIVES: The purpose of this study was to evaluate the clinical value of strain elastography for detection of the lesion extent of large-scar endometriosis and compare it to conventional sonography and magnetic resonance imaging (MRI). METHODS: Eight patients suspected of having large-scar endometriosis underwent transabdominal sonography, strain elastography, and MRI. The mass was located and assessed for its size, imaging appearance, and, especially, widest boundary and vertical extent. After wide surgical excision and pathologic diagnosis, lesions in the central area shown on conventional sonography and the extended area shown on strain elastography underwent immunohistochemical examination. RESULTS: Nodules were always deep in the subcutaneous plane, in contact with the fascia or muscle. Horizontally, the mean lesion size shown on conventional sonography was mainly consistent with the size on MRI in all cases, but it was obviously smaller on sonography than on strain elastography in 7 cases. Vertically, the lesion depth was mainly consistent with the depth on MRI in 7 cases, but it was more infiltrative on strain elastography in 6 cases. The vertical and horizontal infiltration scales of the postoperative specimens were consistent with strain elastography in all cases. All 8 patients showed strong collagen type I expression in the central area of the lesions; 6 patients showed strong collagen type I expression and the other 2 showed moderate expression in the extended area. CONCLUSIONS: Strain elastography can elevate the diagnostic accuracy of large-scar endometriosis, the extent of which may be evaluated insufficiently by transabdominal sonography and MRI.

Multimodal fusion model for classifying placenta ultrasound imaging in pregnancies with hypertension disorders.

BACKGROUND: A multimodal fusion model was proposed to assist the traditional visual diagnosis in evaluating the placental features of hypertension disorders of pregnancy (HDP). OBJECTIVE: The aim of this study was to analyse and compare the placental features between normal and HDP pregnancies and propose a multimodal fusion deep learning model for differentiating and characterizing the placental features from HDP to normal pregnancy. METHODS: This observational prospective study included 654 pregnant women, including 75 with HDPs. Grayscale ultrasound images (GSIs) and Microflow images (MFIs) of the placentas were collected from all patients during routine obstetric examinations. On the basis of intelligent extraction and features fusion, after quantities of training and optimization, the classification model named GMNet (the intelligent network based on GSIs and MFIs) was introduced for differentiating the placental features of normal and HDP pregnancies. The distributions of placental features extracted by the deep convolutional neural networks (DCNNs) were visualized by Uniform Manifold Approximation and Projection for Dimension Reduction (UMAP). Metrics including sensitivity, specificity, accuracy, and the area under the curve (AUC) were used to score the model. Finally, placental tissue samples were randomly selected for microscopic analyses to prove the interpretability and effectiveness of the GMNet model. RESULTS: Compared with the Normal group in ultrasonic images, the light spots were rougher and the parts with focal cystic or hypoechogenic lesions were increased in the HDP groups. The overall diagnostic performance of the GMNet model depending on the region of interest (ROI) was excellent (AUC: 97%), with a sensitivity of 90.0%, a specificity of 93.5%, and an accuracy of 93.1%. The fusion features of GSIs and MFIs in the placenta showed a higher discriminative power than single-mode features (fusion features vs GSI features vs MFI features, 97.0% vs 91.2% vs 94.8%). Furthermore, according to the microscopic analysis, unevenly distributed villi, increased syncyte nodules and aggregated intervillous cellulose deposition were particularly frequent in the HDP cases. CONCLUSIONS: The GMNet model could sensitively identify abnormal changes in the placental microstructure in pregnancies with HDP.

GMRLNet: A Graph-Based Manifold Regularization Learning Framework for Placental Insufficiency Diagnosis on Incomplete Multimodal Ultrasound Data.

Multimodal analysis of placental ultrasound (US) and microflow imaging (MFI) could greatly aid in the early diagnosis and interventional treatment of placental insufficiency (PI), ensuring a normal pregnancy. Existing multimodal analysis methods have weaknesses in multimodal feature representation and modal knowledge definitions and fail on incomplete datasets with unpaired multimodal samples. To address these challenges and efficiently leverage the incomplete multimodal dataset for accurate PI diagnosis, we propose a novel graph-based manifold regularization learning (MRL) framework named GMRLNet. It takes US and MFI images as input and exploits their modality-shared and modality-specific information for optimal multimodal feature representation. Specifically, a graph convolutional-based shared and specific transfer network (GSSTN) is designed to explore intra-modal feature associations, thus decoupling each modal input into interpretable shared and specific spaces. For unimodal knowledge definitions, graph-based manifold knowledge is introduced to describe the sample-level feature representation, local inter-sample relations, and global data distribution of each modality. Then, an MRL paradigm is designed for inter-modal manifold knowledge transfer to obtain effective cross-modal feature representations. Furthermore, MRL transfers the knowledge between both paired and unpaired data for robust learning on incomplete datasets. Experiments were conducted on two clinical datasets to validate the PI classification performance and generalization of GMRLNet. State-of-the-art comparisons show the higher accuracy of GMRLNet on incomplete datasets. Our method achieves 0.913 AUC and 0.904 balanced accuracy (bACC) for paired US and MFI images, as well as 0.906 AUC and 0.888 bACC for unimodal US images, illustrating its application potential in PI CAD systems.

Comparison of the left and right ventricular size and systolic function of low-risk fetuses in the third trimester: Which is more dominant?

Objective: To quantify fetal cardiovascular parameters utilizing fetal-specific 2D speckle tracking technique and to explore the differences in size and systolic function of the left and right ventricles in low-risk pregnancy. Methods: A prospective cohort study was performed in 453 low-risk single fetuses (28+0-39+6 weeks) to evaluate ventricular size [i.e., end-diastolic length (EDL), end-systolic length (ESL), end-diastolic diameter (ED), end-systolic diameter (ES), end-diastolic area, end-systolic area, end-diastolic volume (EDV), and end-systolic volume (ESV)] and systolic function [i.e., ejection fraction (EF), stroke volume (SV), cardiac output (CO), cardiac output per kilogram (CO/KG), and stroke volume per kilogram (SV/KG)]. Results: This study showed that (1) the reproducibility of the interobserver and intraobserver measurements was good to excellent (ICC 0.626-0.936); (2) with advancing gestation, fetal ventricular size and systolic function increased, whereas right ventricular (RV) EF decreased and left ventricular (LV) EF was not significantly changed; (3) LV length was longer than RV length in diastole (2.24 vs. 1.96 cm, P < 0.001) and systole (1.72 vs. 1.52 cm, P < 0.001); (4) LV ED-S1 and ES-S1 were shorter than the RV ED-S1 and ES-S1 (12.87 vs. 13.43 mm, P < 0.001; 5.09 vs. 5.61 mm, P < 0.001); (5) there were no differences between the LV and RV in EDA or EDV; (6) the mean EDV ratio of right-to-left ventricle was 1.076 (95% CI, 1.038-1.114), and the mean ESV ratio was 1.628 (95% CI, 1.555-1.701); (7) the EF, CO and SV of the LV were greater than the RV (EF: 62.69% vs. 46.09%, P < 0.001; CO: 167.85 vs. 128.69 ml, P < 0.001; SV: 1.18 vs. 0.88 ml, P < 0.001); (8) SV and CO increased with ED-S1 and EDL, but EF was not significantly changed. Conclusion: Low-risk fetal cardiovascular physiology is characterized by a larger RV volume (especially after 32 weeks) and greater LV outputs (EF, CO, SV, SV/KG and CO/KG).

Association between abnormal uterine artery pulsatility index and the risk of fetal congenital heart defects: a hospital-based cohort study.

To explore the associations between high uterine artery pulsatility index (UtA-PI) values and congenital heart disease (CHD) risk and whether they differed between singleton and multiple pregnancies. This hospital-based cohort study involving 52,047 pregnant women who underwent prenatal examinations from 2012 to 2016. Infants born to the included pregnant women were followed until 42 days after birth to identify those with CHDs. Generalized estimating equations were used to estimate the associations of high right UtA-PI (> 95th percentile) values with maternal preeclampsia and fetal CHDs. Logistic regression analyses were conducted using path analysis models to quantify the effect of high right UtA-PI values on fetal CHD risk. A total of 42,552 women and 43,470 infants (147 with CHDs) were included. Preeclampsia risk was associated with a high right UtA-PI in singleton-pregnant women (adjusted PR, 3.01; 95% CI 2.57-3.52). CHD risk was marginally associated with a high right UtA-PI in singleton-pregnant women (adjusted PR, 2.26, 95% CI 1.03-4.95). Considering only two factors, 96.0% of the fetal CHD risk was mediated by preeclampsia in singleton-pregnant women, while 93.8% of the risk was related to a high right UtA-PI in multiple-pregnant women. A high right UtA-PI was marginally associated with an increased fetal CHD risk in singleton-pregnant women and might play an important role in multiple-pregnant women. Further studies are warranted to confirm these findings given the high loss to follow-up rate.

Fetal tissue Doppler imaging in pregnancies complicated with preeclampsia with or without intrauterine growth restriction.

OBJECTIVES: This study's aim was to evaluate the effect of preeclampsia and intrauterine growth restriction (IUGR) on fetal cardiac function, and the relationship of the latter with adverse pregnancy outcomes. MATERIAL AND METHODS: We did a cross-sectional study of 132 women with uncomplicated singleton pregnancies, 34 with preeclampsia without IUGR, and 12 with preeclampsia and IUGR. Fetal cardiac structure and function were evaluated using fetal two-dimension ultrasound, pulsed wave Doppler and tissue Doppler imaging (TDI). Data were analyzed by t-tests, ANOVA, Chi-square tests, or Wilcoxon rank-sum test. RESULTS: Compared with the normal pregnancy group, mitral/tricuspid early systolic peak velocity of annulus/late diastolic peak velocity of annulus (Sa) and left ventricular (LV)/right ventricular (RV) early diastolic peak velocity at the annulus (Ea) in TDI decreased in preeclampsia with or without IUGR (P < 0.05). LV/RV Ea underwent a gestational decrease in preeclampsia with or without IUGR (P < 0.05). The changes in mitral/tricuspid Sa and LV Sa associated with preeclampsia were even more pronounced with preterm delivery at less than 34 gestational weeks and stillbirth (P < 0.05). CONCLUSIONS: Intrauterine growth restriction influences fetal cardiac function in the presence of preeclampsia, and TDI may be a sensitive and preferable method to detect such changes. Fetal LV/RV Ea is a potential marker for early fetal cardiac diastolic impairment, and mitral/tricuspid Sa and LV Sa may be predictors for adverse pregnancy outcomes.

Correlation between cerebroplacental doppler ratio and neonatal respiratory disorders: A reference marker of fetal lung maturation.

AIM: The aim of this study was to investigate the role of cerebroplacental ratio (CPR) in the final prenatal care for neonatal respiratory diseases and to analyze the risk of relevant factors associated with neonatal respiratory disorders. METHODS: A prospective cohort study of 795 singleton pregnancies was conducted. The pulsatility indices (PI) of the umbilical artery (UA) and the middle cerebral artery (MCA) were measured, and the MCA to UA ratio (CPR) was determined. The severity of the case is determined by whether or not the newborn has respiratory problems. Compare the CPR correlation between the two groups and examine the illness prediction factors through a binary logistic regression method. RESULTS: Of the 801 participants, 114 had neonatal respiratory disorders. The mean values of CPR between neonatal respiratory diseases group and control group were 1.78±0.6, 1.97±0.9, respectively (P <  0.001). Maternal age, abortion history, cesarean section history, placental thickness, placental maturity, and amniotic fluid index (AFI) were determined to have no significant link between the two groups after comparison analysis (P >  0.05). It could be found that compared with the control group, CPR MoM indicators of neonatal respiratory distress syndrome, neonatal pneumonia and wet lung disease all show significant decreases. In binary logistic regression analysis, among the variables included in the model, CPR (OR:2.90, P = 0.015), fetal heart monitoring (OR:5.26, P <  0.001), delivery mode (OR:2.86, P <  0.001) and gestational age of delivery (OR:0.92, P <  0.001) were statistically significant in both groups. CONCLUSION: The findings of this study showed that infant respiratory problems were substantially related to CPR value. The correlation indicates that CPR was a powerful reference marker for respiratory disorders.

Ultrasound-based radiomics technology in fetal lung texture analysis prediction of neonatal respiratory morbidity.

To develop a novel method for predicting neonatal respiratory morbidity (NRM) by ultrasound-based radiomics technology. In this retrospective study, 430 high-throughput features per fetal-lung image were extracted from 295 fetal lung ultrasound images (four-chamber view) in 295 single pregnancies. Images had been obtained between 28+3 and 37+6 weeks of gestation within 72 h before delivery. A machine-learning model built by RUSBoost (Random under-sampling with AdaBoost) architecture was created using 20 radiomics features extracted from the images and 2 clinical features (gestational age and pregnancy complications) to predict the possibility of NRM. Of the 295 standard fetal lung ultrasound images included, 210 in the training set and 85 in the testing set. The overall performance of the neonatal respiratory morbidity prediction model achieved AUC of 0.88 (95% CI 0.83-0.92) in the training set and 0.83 (95% CI 0.79-0.97) in the testing set, sensitivity of 84.31% (95% CI 79.06-89.44%) in the training set and 77.78% (95% CI 68.30-87.43%) in the testing set, specificity of 81.13% (95% CI 78.16-84.07%) in the training set and 82.09% (95% CI 77.65-86.62%) in the testing set, and accuracy of 81.90% (95% CI 79.34-84.41%) in the training set and 81.18% (95% CI 77.33-85.12%) in the testing set. Ultrasound-based radiomics technology can be used to predict NRM. The results of this study may provide a novel method for non-invasive approaches for the prenatal prediction of NRM.