Association between Fetal Heart Rate Monitoring during Labor and Neonatal Acidosis in Full-Term Newborns: A Retrospective Multicenter Cohort Study

Introduction: Fetal heart rate monitoring during labor is used to study fetal well-being and predict neonatal acidosis of newborn. Fetal heart rate monitoring is analyzed by the obstetrical team and categorized according to the FIGO guidelines. An important limitation of this diagnostic tool is an inter- and intra-observer variability, leading to subjective cardiotocography interpretation and classification. Our objective was to study the association between the categories of fetal heart rate analysis (according to FIGO classification) and neonatal acidosis of full-term newborns. Study design: This is a multicenter retrospective cohort study conducted between 2014 and 2018 in the Grand-Est region. We searched and included retrospectively children hospitalized in a pediatric intensive care unit in one of the participating hospitals with an ICD-10 coding type “P91.6” corresponding to “Hypoxic Ischemic Encephalopathy”. Maternal, pregnancy, delivery, and newborn characteristics were collected and compared by univariate logistic regression with multiple imputation. Odds Ratio and 95% confidence intervals (CI) were calculated using the model and presented. Multiple imputation with m = 100 imputations was tested, using Rubin rules to combine the results. Results: 55 patients were included in the study. Fetal heart rate tracings classified in Category 3 as “pathological” according to FIGO guidelines were significantly associated with an increased risk of severe neonatal acidosis. Late decelerations and bradycardia during labor were associated with severe neonatal acidosis. Conclusion: Severe neonatal acidosis may be suspected by interpretation of fetal heart rate during labor. Fetal bradycardia and late decelerations are predictive of the severity of neonatal acidosis. This study emphasizes the need to screen severe neonatal acidosis and allows the identification of populations most at risk. Repeated team training and upgrading of fetal heart rate study would further reduce the incidence of neonatal acidosis.

An Effective Machine-Learning Based Feature Extraction/Recognition Model for Fetal Heart Defect Detection from 2D Ultrasonic Imageries

Congenital heart defect,accounting for about 30%of congenital defects,is the most common one.Data shows that congenital heart defects have seriously affected the birth rate of healthy newborns.In Fetal andNeonatal Cardiology,medical imaging technology(2D ultrasonic,MRI)has been proved to be helpful to detect congenital defects of the fetal heart and assists sonographers in prenatal diagnosis.It is a highly complex task to recognize 2D fetal heart ultrasonic standard plane(FHUSP)manually.Compared withmanual identification,automatic identification through artificial intelligence can save a lot of time,ensure the efficiency of diagnosis,and improve the accuracy of diagnosis.In this study,a feature extraction method based on texture features(Local Binary Pattern LBP and Histogram of Oriented Gradient HOG)and combined with Bag of Words(BOW)model is carried out,and then feature fusion is performed.Finally,it adopts Support VectorMachine(SVM)to realize automatic recognition and classification of FHUSP.The data includes 788 standard plane data sets and 448 normal and abnormal plane data sets.Compared with some other methods and the single method model,the classification accuracy of our model has been obviously improved,with the highest accuracy reaching 87.35%.Similarly,we also verify the performance of the model in normal and abnormal planes,and the average accuracy in classifying abnormal and normal planes is 84.92%.The experimental results show that thismethod can effectively classify and predict different FHUSP and can provide certain assistance for sonographers to diagnose fetal congenital heart disease.

The Signal Extraction of Fetal Heart Rate Based on Wavelet Transform and BP Neural Network

This paper briefly introduces the collection and recognition of bio-medical sig nals, designs the method to collect FM signals. A detailed discussion on the sys tem hardware, structure and functions is also given. Under LabWindows/CVI,the ha rdware and the driver do compatible, the hardware equipment work properly active ly. The paper adopts multi threading technology for real-time analysis and make s use of latency time of CPU effectively, expedites program reflect speed, impro ve s the program to perform efficiency. One threading is collecting data; the other threading is analyzing data. Using the method, it is broaden to analyze the sig nal in real-time. Wavelet transform to remove the main interference in the FM a nd by adding time-window to recognize with BP network; Finally the results of c ollecting signals and BP networks are discussed.8 pregnant women’s signals of F M were collected successfully by using the sensor. The correct of BP network rec ognition is about 83.3% by using the above measure.

The Impacts of Maternal Gestational Diabetes Mellitus (GDM) on Fetal Hearts

Objective To evaluate the fetal cardiac function in gestational diabetes mellitus （GDM） pregnancies under different maternal glycemic controls. Methods Forty four GDM mothers received 78 fetal echocardiographic evaluations at three gestational periods （〈28, 28-34 and ≥34 weeks） and were divided into poorly-（DM1） and well-（DM2） controlled groups according to their glycemic control at examination. Seventy uncomplicated mothers were selected as controls. Parameters of fetal cardiac anatomy and function were measured and analyzed. Results GDM fetuses＇ cardiac ventricular walls were thicker than controls＇, and the differences between DM1 and DM2 were not significant except for end-diastolic left ventricular walls. In both GDM groups, the aortic flow velocities increased earlier than pulmonary artery and DM1 fetuses changed earlier than DM2 ones. GDM fetuses＇ left atrial shortening fraction was smaller than the controls＇ in the period of ≥34 weeks and negatively correlated with thicknesses of left ventricular walls and interventricular septum in DM1 fetuses （r=-0.438 and -0.506）. The right ventricular diastolic function in DM1 and DM2 fetuses decreased after the period of 28-34 weeks and in the period of ≥34 weeks respectively. Tel index of both left and right ventricles increased in DM1 group after the period of 〈28 weeks and in DM2 group only in the period of ≥ 34 weeks, with no significant differences between DM1 and DM2 groups in this period. Conclusion Fetuses of GDM mothers showed cardiac function impairments. Good maternal glycemic control may delay the impairments, but cannot reduce the degree. Some cardiac changes in GDM fetuses were similar to those in pregestational diabetic pregnancies except for several parameters and their changing time.

Critical evaluation of American categorization of fetal heart rate (FHR) decelerations and three tier classification—Shortcomings, contradictions, remedies and need for debate

Fetal heart rate (FHR) decelerations are the commonest aberrant feature on cardiotocograph (CTG) thus having a major influence on classification ofFHRpatterns into the three tier system. The unexplained paradox of early decelerations (head compression—an invariable phenomenon in labor) being extremely rare [1] should prompt a debate about scientific validity of current categorization. This paper demonstrates that there appear to be major fallacies in the pathophysiological hypothesis (cord compression—baroreceptor mechanism) underpinning of vast majority of (variable?) decelerations. Rapid decelerations during contractions with nadir matching peak of contractions are consistent with “pure” vagal reflex (head compression) rather than result of fetal blood pressure or oxygenation changes from cord compression. Hence, many American authors have reported that the abrupt FHR decelerations attributed to cord compression are actually due to head compression [2-6]. The paper debates if there are major fundamental fallacies in current categorization of FHR decelerations based concomitantly on rate of descent (reflecting putative aetiology?) and time relationship to contractions. Decelerations with consistently early timing (constituting majority) seem to get classed as “variable” because of rapid descent. A distorted unscientific categorization of FHR decelerations could lead to clinically unhelpful three tier classification system. Hence, the current unphysiological classification needs a fresh debate with consideration of alternative models and re-evaluation of clinical studies to test these. Open debate improves patient care and safety. The clue to benign reflex versus hypoxic nature of decelerations seems to be in the timing rather than the rate of descent. Although the likelihood of fetal hypxemia is related to depth and duration ofFHRdecelerations, the cut-offs are likely to be different for early/late/variable decelerations and it seems to be of paramount importance to get this discrimination right for useful visual or computerized system of CTG interpretation.

The Diagnostic Accuracy of Automated Fetal Heart Echocardiography by Five Dimensional Compared to Two-Dimensional Ultrasound in the Second Trimester of Pregnancy

Objective: To compare the diagnostic accuracy of Fetal Intelligent Navigation Echocardiography (FINE) method by Five-Dimensional Ultrasound in automated fetal heart examination to conventional fetal heart examination by Two-Dimensional ultrasound in second trimester pregnancy. Methods: 90 normal singleton pregnancies at the second trimester were enrolled in this prospective study. Fetal heart was examined by Two-Dimensional Ultrasound (2D US) and Five-Dimensional Ultrasound (FINE). Paired numerical data were compared using the paired samples t test. Inter-method agreement for the rating of the quality of cardiac views by 2D US or 5D US was assessed by calculation of the prevalence-adjusted and bias-adjusted kappa coefficient (PABAK). Results: There was no statistical significant difference between fetal heart echocardiography assessment using 2DUS or 5DUS(FINE) (p-value > 0.05). The overall inter-method agreement between 2D US and 5D US was 0.92. The difference in % of satisfactory views between 2D and 5D US was 1.73%, (95% CI - 0.5% to 3.33%) (P-value = 0.144). Conclusion: Our findings indicate the accuracy of 5DUS (FINE) echocardiography in evaluation of normal heart in the second trimester of pregnancy.

Interpretation of British experts’ illustrations of fetal heart rate (FHR) decelerations by Consultant Obstetricians, registrars and midwives: A prospective study—Reasons for major disagreement with experts and implications for clinical practice

Objective: To test the reproducibility of British experts’ (eFM, K2MS, Gibb and Arulkumaran) [1-3] illustrations of fetal heart rate (FHR) decelerations by trained British Obstetricians and midwives. To analyze reasons for any discrepancies by examining factors relating to the participants, British experts’ descriptions and NICE guidelines [4]. Design: Prospective observational study. Setting: National Health Service (NHS) Hospitals. Participants: 38 Obstetric Consultants, 49 registrars and 45 midwives. Methods: Printed questionnaire. Statistical Analysis: Fisher’s Exact test. Results: This largest study of its kind showed almost unbelievably high disconnect between CTG interpretation by experts and participants. 98% - 100% midwives, 80% - 100% Registrars and 74% - 100% Consultants categorized FHR decelerations differently from the five experts’ illustrations/interpretations (p < 0.0001). Remarkably, the three experts’ illustrations of early (supposedly most benign) decelerations were classed as atypical variable by 56% Consultants, 78% Registrars and 99% midwives and the CTGs as pathological by 85% of the participants. Conclusions: The high degree of disagreement with the experts’ illustrations (p < 0.0001) did not appear to be due to participant factors. The immediate reasons seemed to be the conflicting illustrations and heterogeneity of experts’ descriptions. But most importantly, these appeared to stem from non-standardized ambiguous definitions of FHR decelerations and many intrinsic systemic flaws in the current NICE guidelines [4]. The NICE concept of “true uniform” (identical) early and late decelerations seems biologically implausible (a myth) and no examples can be found. Another myth seems to be that early and late decelerations should be gradual. Only very shallow decelerations will look “gradual” on the British CTG. These systemic flaws lead to dysfunctional CTG interpretation increasing intervention as well as impairing diagnosis of fetal hypoxemia. This is because the vast majority of FHR decelerations fall in a single heterogeneous “variable” group with many further classed as “atypical” (pathological) based on disproven and discredited criteria [5-7]. There is increasing evidence in USA that a system with variable decelerations as the majority is clinically unhelpful because of loss of information [5-9]. In the interest of patient care and safety, open debate is necessary regarding a better way forward. Classification of FHR decelerations based primarily and solely on time relationship to contractions appears more scientific and clinically useful.

Assessing Coarctation of the Aorta With Fetal Heart Quantification Technology

Objective:To use fetal heart quantification(fetal HQ)technology to compare the coarctation of the aorta(CoA)and normal fetal heart structure and systolic function and to assess whether there are abnormalities in the fetal heart structure and systolic function associated with CoA.Methods:This prospective cohort study was conducted from May 2020 to December 2022 and involved 18–40-week-old singleton pregnancies and 30 fetuses diagnosed with CoA using fetal echocardiography at the General Hospital of Ningxia Medical University and Peking University First Hospital Ningxia Women’s andChildren’s Hospital,China.The control group contained 60 normal fetuses.The following parameters were recorded and analyzed statistically:four-chamber view(4CV)end-diastolic long diameter,4CV epicardial–contralateral epicardial transverse maximum diameter,4CV global sphericity index(GSI),left ventricular(LV)and right ventricular(RV)24-segment end-diastolic diameter(EDD),24-segment sphericity index(SI),LV-fractional area change(LV-FAC),LV-longitudinal strain(LV-LS),RV-fractional area change(RV-FAC),RV-longitudinal strain(RV-LS),and LV and RV 24-segment transverse fractional shortening(FS).Measurement data were compared between the two groups using an independent sample t test,with P<0.05 indicating statistically significant differences.Moreover,the correlation between gestational age and GSI,LV-FAC,LV-LS,RV-FAC,and RV-LS was assessed.Results:Within and between observer comparisons of the parameters associated with major cardiac function revealed an intragroup correlation coefficient of>0.9,indicating high consistency,and a coefficient of variable of<1%,indicating low variability.Correlation analysis revealed no obvious correlation between gestational age and GSI,LV-FAC,LV-LS,RV-FAC,and RV-LS.A comparison of the fourchamber morphological structural parameters of the hearts in the two groups revealed that when compared with the control group,the 4CV end-diastolic long diameter was shortened in fetuses in the CoA group and the epicardial–contralateral epicardial transverse maximum diameter was wider,while the GSI was lower(P<0.05).A comparison of the LV and RV morphological structure parameters between the two groups revealed that when compared with the control group,the LV’s 24-segment EDD was smaller in the CoA group,the RV’s 24-segment EDD was greater in the control group,the SI of the LV’s segments 16–24 was greater than in the control group,and the SI of the RV’s segments 7–24 was less than in the control group(all P<0.05).When comparedwith fetuses in the control group,the LV’s segments16–24 were greater in the CoA group,whereas the RV’s segment 6–24 was smaller(P<0.05).When comparedwith the control group,LV-FAC,RV-FAC,and LS were lower in the CoA group(P<0.05).The FS of the LV segments 1–24 and the FS of the RV segments 1–16 were smaller in the CoA group than in the normal group(P<0.05).Conclusion:Fetal HQ,a new simple technique that offers rapid analysis and high repeatability,can quantitatively evaluate structural and systolic function changes in fetuses with CoA.

CTGNet: Automatic Analysis of Fetal Heart Rate from Cardiotocograph Using Artificial Intelligence

Objective:This study investigates the efficacy of analyzing fetal heart rate(FHR)signals based on Artificial Intelligence to obtain a baseline calculation and identify accelerations/decelerations in the FHR through electronic fetal monitoring during labor.Methods:A total of 43,888 cardiotocograph(CTG)records of female patients in labor from January 2012 to December 2020 were collected from the NanFang Hospital of Southern Medical University.After filtering the data,2341 FHR records were used for the study.The ObVue fetal monitoring system,manufactured by Lian-Med Technology Co.Ltd.,was used to monitor the FHR signals for these pregnant women from the beginning of the first stage of labor to the end of delivery.Two obstetric experts together annotated the FHR signals in the system to determine the baseline as well as accelerations/decelerations of the FHR.Our cardiotocograph network(CTGNet)as well as traditional methods were then used to automatically analyze the baseline and acceleration/deceleration of the FHR signals.The results of calculations were compared with the annotations provided by the obstetric experts,and ten-fold cross-validation was applied to evaluate them.The root-mean-square difference(RMSD)between the baselines,acceleration F-measure(Acc.F-measure),deceleration F-measure(Dec.F-measure),coefficient of synthetic inconsistency(SI)and the morphological analysis discordance index(MADI)were used as evaluation metrics.The data were analyzed by using a pairedt-test.Results:The proposed CTGNet was superior to the best traditional method,proposed by Mantel,in terms of the RMSD.BL(1.7935±0.8099vs.2.0293±0.9267,t=-3.55,P=0.004),Acc.F-measure(86.8562±10.9422vs.72.2367±14.2096,t=12.43,P<0.001),Dec.F-measure(72.1038±33.2592vs.58.5040±38.0276,t=4.10,P<0.001),SI(34.8277±20.9595vs.54.8049±25.0265,t=-9.39,P<0.001),and MADI(3.1741±1.9901vs.3.7289±2.7253,t=-2.74,P=0.012).The proposed CTGNet thus had significant advantages over the best traditional method on all evaluation metrics.Conclusion:The proposed Artificial Intelligence-based method CTGNet delivers good performance in terms of the automatic analysis of FHR based on cardiotocograph data.It promises to be a key component of smart obstetrics systems of the future.

Right heart modified myocardial performance index and ductus venosus spectrum parameters in pre-eclampsia fetuses for predicting adverse pregnancy outcomes

Objective To observe the values of changes of right heart modified myocardial performance index(Mod-MPI)and ductus venosus(DV)spectrum parameters in pre-eclampsia fetuses for predicting adverse pregnancy outcomes.Methods Eighty-one pregnant women diagnosed as pre-eclampsia were prospectively enrolled and divided into severe pre-eclampsia(SPE)group(n=39)and mild pre-eclampsia(MPE)group(n=42),while 85 healthy pregnant women were taken as controls(control group).Fetal right heart function parameters,including right ventricular isovolumetric relaxation time(IRT),isovolumetric contraction time(ICT),ejection time(ET),total spent time(TST),Mod-MPI,tricuspid valve peak flow velocity ratio in early and late diastole(TV-E/A),as well as blood flow velocities in each waveform of DV spectrum(S,V,D,and A wave)were obtained,and the pulsatility index(PI)and the ratio of blood flow velocities in each waveform of the DV(S/V,S/D,S/A,V/D,V/A,D/A)were calculated.Intrauterine fetal distress,preterm delivery,neonatal asphyxia and newborn with low weight were considered as adverse pregnancy outcomes.The correlations of right heart Mod-MPI and TV-E/A with DV parameters in pre-eclampsia fetuses were assessed,and their predictive efficacies for adverse pregnancy outcomes were evaluated for right heart Mod-MPI and DV using the receiver operating characteristics(ROC)and the area under the curves(AUC).Results Compared with control group and MPE group,fetal right heart IRT,ICT and Mod-MPI increased and ET decreased in SPE group(all P<0.05).No significant differences of right heart TST and TV-E/A among 3 groups(both P>0.05).Fetal DV A-wave velocity and V/D values progressively decreased but PI progressively increased in control,MPE and SPE groups(all P<0.05).Fetal right heart Mod-MPI in pre-eclampsia was moderately positively correlated with DV PI(r=0.637,P=0.016),while TV-E/A was weakly negatively correlated with DV V/D(r=-0.355,P=0.043).Adverse pregnancy outcomes were noticed in 59 pre-eclampsia cases.The AUC of fetal right heart Mod-MPI and DV PI for predicting adverse pregnancy outcomes in pre-eclampsia cases was 0.897 and 0.848,respectively,without significant difference(Z=0.460,P=0.400).Conclusion Changes of right heart Mod-MPI and DV spectrum parameters in pre-eclampsia fetuses had high value for predicting adverse pregnancy outcomes.

Unexplained fetal tachycardia:A case report

BACKGROUND This study aimed to explore the possible etiology and treatment of severe fetal tachycardia in the absence of organic disease and provide a reference for clinical management of severe fetal tachycardia.CASE SUMMARY A 29-year-old pregnant woman,with a gravidity 1 parity 0,presented with a fetal heart rate(FHR)of 243 beats per minute during a routine antenatal examination at 31+2 wk of gestation.Before termination of pregnancy at 38 wk of gestation,the FHR repeatedly showed serious abnormalities,lasting more than 30 min.However,the pregnant woman and the fetus had no clinical symptoms,and repeated examination revealed no organic lesions.The mother and the baby were regularly followed up.CONCLUSION This was a case of severe fetal tachycardia with no organic lesions and management based on clinical experience.

Valvuloplasty of fetal pulmonary atresia with intact ventricular septum and hypoplastic right heart: Mid-term follow-up results

Objective:This study aimed to analyze and evaluate the results of mid-term follow-up after fetal pulmonary valvuloplasty(FPV)in fetuses with pulmonary atresia with intact ventricular septum(PA/IVS).Methods:From August 31,2018,to May 31,2019,seven fetuses with PA/IVS and hypoplastic right heart were included in this study.All underwent echocardiography by the same specialist and were operated on by the same team.Intervention and echocardiography data were collected,and changes in the associated indices noted during follow-up were analyzed.Results:All seven fetuses successfully underwent FPV.The median gestational age at FPV was 27.54 weeks.The average FPV procedural time was 6 min.Persistent bradycardia requiring treatment occurred in 4/7 procedures.Finally,five pregnancies were successfully delivered,and the other two were aborted.Compared to data before fetal cardiac interventions(FCI),tricuspid valve annulus diameter/mitral valve annulus diameter(TV/MV)and right ventricle diameter/left ventricle diameter(RV/LV)of all fetuses had progressively improved.The maximum tricuspid regurgitation velocity decreased from 4.60 m/s to 3.64 m/s.The average follow-up time was 30.40±2.05 months.During the follow-up period,the diameter of the tricuspid valve ring in five children continued to improve,and the development rate of the tricuspid valve was relatively obvious from 6 months to 1 year after birth.However,the development of the right ventricle after birth was relatively slow.It was discovered that there were individual variations in the development of the right ventricle during follow-up.Conclusion:The findings support the potential for the development of the right ventricle and tricuspid valve in fetuses with PA/IVS who underwent FCI.Development of the right ventricle and tricuspid valve does not occur synchronously during pregnancy.The right ventricle develops rapidly in utero,but the development of tricuspid valve is more apparent after birth than in utero.

The Efficacy of In-Phase and Quadrature Demodulation in Electronic Fetal Heart Rate Monitoring During Labor

Objective:To investigate the efficacy of in-phase and quadrature(IQ)demodulation in electronic fetal heart rate monitoring(EFM)to reduce false reports of fetal heart rate(FHR)doubling or halving.Methods:This is a prospective cohort study.A total of 263 full-term pregnant women who delivered at Peking University Shenzhen Hospital between August 2019 and July 2020 were prospectively enrolled in the study.FHR monitoring began when the cervix was dilated to 2-3 cm and continued until delivery.Raw fetal Doppler audio signals and internal and external cardiotocography curves from internal electrode monitoring,EFM with conventional demodulation(external),and EFM with IQ demodulation(external)were acquired to compare FHR doubling and halving time.In cohort 1,FHR was compared between IQ demodulation and conventional demodulation.In cohort 2,FHR was compared between IQ demodulation,conventional demodulation,and internal FHR monitoring.Count data were statistically analyzed using the Chi-squared test,and measurement data were statistically analyzed usingt-test for correlation coefficients,and Bland-Altman analysis for concordance ranges.Results:To compare IQ demodulation and conventional demodulation,225 pregnant women were monitored for a total of 835,870 seconds.The beat-to-beat interval of FHRs in raw fetal Doppler audio signals was used as the reference.The results showed a doubling time of 3401 seconds(0.407%,3401/835,870)and a halving time of 2918 seconds(0.349%,2918/835,870)with conventional demodulation,compared to 241 seconds(0.029%,241/835,870)and 589 seconds(0.070%,589/835,870),respectively,with IQ demodulation.IQ demodulation reduced FHR doubling by approximately 93%(3160/3401)and FHR halving by approximately 80%(2329/2918)compared to conventional demodulation(P<0.01).Conclusion:EFM with IQ demodulation significantly reduces false FHR doubling and halving,with an efficacy similar to that of internal FHR monitoring.

应用深度学习模型分类正常胎儿心脏超声切面

目的观察4种深度学习(DL)模型分类正常胎儿7类心脏超声切面的价值。方法回顾性纳入200名于孕周18~24+6周接受胎儿心脏超声检查的正常胎儿,按7∶3比例分为训练集(n=140)和测试集(n=60)。收集三血管气管(3VT)切面、心尖四腔心(A4C)切面、主动脉弓长轴切面、双腔静脉切面、左心室流出道(LVOT)切面、三血管(three-vessel,3V)切面及右心室流出道(right ventricular outflow tract,RVOT)切面二维声像图,经过图像预处理后,采用4种DL模型Vision Transformer(ViT)、Data-efficient Image Transformer(DeiT)、Vision-long short term memory(ViL)及Multi-axis Vision Transformer(MaxViT)分别提取图像特征并构建正常胎儿心脏超声切面模型,以准确率、精确率、召回率及F1分数评估各模型于测试集中分类效能,并以梯度加权类激活映射(Grad-CAM)获取激活特征的热力图可视化图像中最具识别特征的区域。结果ViT、DeiT、ViL及MaxViT模型分类测试集中正常胎儿心脏超声切面的效能均表现优秀,其中MaxViT为最优模型,准确率、精确率、召回率及F1分数分别为98.93%、98.93%、98.95%及98.93%。Grad-CAM可视化结果显示,以DL模型分类正常胎儿心脏超声7类切面时,心脏、血管所在区域红色最深,对于分类的贡献最大,模型关注度最高。结论所获4种DL模型分类正常胎儿心脏超声切面均表现优越,尤以MaxViT模型效能最佳,且分类结果的可解释性获得Grad-CAM验证。

Ultrasonographic Segmentation of Fetal Lung with Deep Learning

The morbidity and mortality of the fetus is related closely with the neonatal respiratory morbidity, which was caused by the immaturity of the fetal lung primarily. The amniocentesis has been used in clinics to evaluate the maturity of the fetal lung, which is invasive, expensive and time-consuming. Ultrasonography has been developed to examine the fetal lung quantitatively in the past decades as a non-invasive method. However, the contour of the fetal lung required by existing studies was delineated in manual. An automated segmentation approach could not only improve the objectiveness of those studies, but also offer a quantitative way to monitor the development of the fetal lung in terms of morphological parameters based on the segmentation. In view of this, we proposed a deep learning model for automated fetal lung segmentation and measurement. The model was constructed based on the U-Net. It was trained by 3500 data sets augmented from 250 ultrasound images with both the fetal lung and heart manually delineated, and then tested on 50 ultrasound data sets. With the proposed method, the fetal lung and cardiac area were automatically segmented with the accuracy, average IoU, sensitivity and precision being 0.98, 0.79, 0.881 and 0.886, respectively.

电子胎心监护相关指标及产妇临床特征对新生儿不良结局的预测价值

目的探究电子胎心监护相关指标联合产妇临床特征对新生儿不良结局的预测价值。方法收集濮阳市妇幼保健院2019年1月至2022年7月产科收治的237例产妇临床资料。观察电子胎心监护相关指标、产妇临床特征等。结果将237例患者按照不同结局分为良好组(165例)与不良组(72例)。两组胎龄、体重指数、新生儿性别、受教育程度、分娩方式比较,差异无统计学意义(P>0.05)。良好组30 min减速区面积高于不良组,年龄低于不良组,妊娠糖尿病、羊水污染、妊娠高血压、胎心率图形异常例数低于不良组(P<0.05)。二元逻辑回归分析显示,结果显示,30 min减速区面积、年龄、妊娠糖尿病、羊水污染、妊娠高血压、胎心率图形异常均是新生儿不良结局的危险因素。电子胎心监护相关指标及产妇临床特征对新生儿不良结局的预测效能较高,曲线下面积(AUC)为0.877。结论电子胎心监护相关指标联合临床特征对于新生儿不良结局有良好的预测价值,可作为临床上预测新生儿不良结局的参照指标。

Imperative for improvements and international convergence of intrapartum fetal monitoring: A bird's eye view

Intrapartum fetal monitoring has been criticized for the lack of evidence of improvement in fetal outcome despite causing increased operative intervention. Paradoxically, cardiotocography （CTG） has been a major driver for litigation for neonatal neurological injury. This analytical review tries to explore why extensive clinical studies and trials over 50 years have failed to demonstrate or bring about signifcant improvement in intrapartum fetal monitoring. There seems a need for significant reform. International congruence on most aspects of CTG interpretation [defnitions of fetal heart rate （FHR） parameters, CTG recording speed, 3-tier systems, etc .] is highly desirable to facilitate future meaningful clinical studies, evaluation and progress in this field. The FHR changes are non-specific and poor surrogate for fetal well-being. As a compromise for maintaining low false-negative results for fetal acidemia, a high false-positive value may have to be accepted. The need for redefning the place of adjuvant tests of fetal well-being like fetal blood sampling or fetal electrocardiography （ECG） is discussed. The FHR decelerations are often deterministic （center-stage） in CTG interpretation and 3-tier categorization. It is discussed if their scientifc and physiological classifcation （avoiding framing and confirmation biases） may be best based on time relationship to uterine contractions alone. This may provide a more sound foundation which could improve the reliability and further evolution of 3-tier systems. Results of several trials of fetal ECG （STAN） have been inconclusive and a need for a fresh approach or strategy is considered. It is hoped that the long anticipated Computer-aided analysis of CTG will be more objective and reliable （overcome human factors） and will offer valuable support or may eventually replace visual CTG interpretation. In any case, the recording and archiving all CTGs digitally and testing cord blood gases routinely in every delivery would be highly desirable for future research. This would facilitate well designed retrospective studies which can be very informative especially when prospective randomised controlled trials are often diffcult and resource-intensive.

基于多模态超声建构胎儿先天性心脏病决策树模型及其应用价值

目的:分析基于多模态超声建构胎儿先天性心脏病决策树模型及其应用价值。方法:随机选取2021年4月-2023年7月在本院产前超声检查孕中期孕妇300例,常规产科超声检查确定胎儿生长程度,核实孕周,采用超声多断面模式方法对胎儿心脏进行多断面检测,包括四腔心断面、三血管断面、主动脉弓断面、左室流出道断面、右室流出道断面。对正常分娩的新生儿进行心脏多断面超声检测。对300例胎儿进行多断面模式超声检测,分析胎儿是否伴有先天性心脏畸形,对比超声检查与随访结果符合情况。结果:超声检出21例先天性心脏畸形胎儿,8例选择引产,余13例正常分娩。超声诊断与随访结果对比,卵圆孔直径增大、法洛四联症、完全型心内膜垫缺损、二尖瓣闭锁、右室发育不良综合征、左室发育不良综合征、大动脉转位、永存动脉干、单心室、三尖瓣下移符合率均为100%,超声诊断室间隔缺损7例,随访发现室间隔诊断5例,诊断符合率71.4%。279例超声诊断无先天性心脏畸形胎儿出生后经超声诊断发现有1例卵圆孔未闭、3例室间隔缺损,共4例漏诊患儿,漏诊率0.54%。四腔心断面、三血管断面、主动脉弓断面、左室流出道断面、右室流出道断面诊断胎儿畸形率分别为3.95%、0.63%、2.76%、3.27%、3.25%。由决策树模型可得,产前超声检查发现胎儿心脏可疑异常、高龄孕妇、孕妇接受药物治疗或射线暴露、孕妇有先天性心脏病家族史是胎儿存在先天性心脏病的独立危险因素,其中产前超声检查发现胎儿心脏可疑异常的影响最为显著。结论:孕中期胎儿产前超声多断面模式筛查胎儿先天性心脏病,能够对多数胎儿先天性心脏病进行诊断。

Interaction between ozone and paternal smoking on fetal congenital heart defects among pregnant women at high risk a multicenter maternal-fetal medicine study

Background Evidence remains limited on the association between maternal ozone(O,)exposure and congenital heart defects(CHDs)in offspring,and few studies have investigated the interaction and modification of paternal smoking on this association.Methods Using a sample including pregnant women at high risk of fetal CHD(with metabolic disease,first-trimester viral infection,family history of CHD,etc.)from a maternal-fetal medicine study covering 1313 referral hospitals in China during 2013-2021,we examined the associations between maternal O_(3)exposure during 3-8 weeks of gestational age and fetal CHD in offspring and investigated the interaction and modification of paternal smoking on this association.CHD was diagnosed by fetal echocardiograms,maximum daily 8-hour average O,exposure data at a 10 km×10 km spatial resolution came from the Tracking Air Pollution in China dataset,and paternal smoking was collected using questionnaires.Logistic regression models were used to estimate adjusted odds ratios(ORs)and 95%confidence intervals(CIs).Results Among 27,834 pregnant women at high risk of fetal CHD,17.4%of fetuses were diagnosed with CHD.Each 10μg/m^(3)increase in maternal O_(3)exposure was associated with a 17%increased risk of CHD in offspring(OR=1.17,95%CI=1.14-1.20).Compared with paternal nonsmoking and maternal low O_(3)exposure,the ORs(95%CI)of CHD for smoking and low O_(3)exposure,nonsmoking and high O_(3)exposure,and smoking and high O_(3)exposure were 1.25(1.08-1.45),1.81(1.56-2.08),and 2.23(1.84-2.71),respectively.Paternal smoking cessation seemingly mitigated the increased risk of CHD.Conclusions Maternal O_(3)exposure and paternal smoking were interactively associated with an increased risk of fetal CHD in offspring,which calls for effective measures to decrease maternal exposure to O_(3)pollution and secondhand smoke for CHDprevention.