Automated Techniques for the Interpretation of Fetal Abnormalities: A Review.

Context: Pregnant women in India are often unable to recall the last menstruation period (LMP) and also present in the late trimester. In India, to determine the fetal age by ultrasonography (USG), Western nomogram is being used, but the racial and ethnic variation might lead to variation in estimation of fetal parameter. Aim: The aim of this study was to estimate the value of different fetal biometric parameters by USG and to compare it with Western nomogram like Hadlock’s. Settings and Design: This was a descriptive cross-sectional study. Subjects and Methods: The study was performed among 150 pregnant women in their second or third trimester following the inclusion and exclusion criteria. Statistical Analysis Used: The data were analyzed with Microsoft Excel and SPSS (Statistical Package for the Social Sciences) version 22.0. Results: 51.33% of participants were in 29–37 weeks of pregnancy. A statistically significant high positive linear correlation within the estimates of different sonological parameters was found. The observed coefficient of correlation for different parameters was as follows: biparietal diameter (r = 0.968), head circumference (r = 0.963), abdominal circumference (r = 0.964), and femur length (r = 0.963). In the same gestational age (GA), Hadlock’s chart reported higher diameter(s)/length, and differences were noted to be statistically significant. GA estimated by Hadlock’s chart was found to be significantly lower than that of the GA determined from LMP. Conclusion: The biometric sonological fetal parameters in the present study were significantly different from the Hadlock’s chart which notes a considerably higher reading for the same GA, indicating that the probability of race, ethnicity, and sample size played a role.

Intrauterine Growth Restriction (IUGR) occurs when a fetus fails to reach its growth potential. Ultrasound plays a key role in diagnosis by assessing fetal biometry, and estimated weight. Umbilical artery Doppler studies evaluate placental function, with abnormal findings like increased resistance or absent/reversed end-diastolic flow. Objective: To detect Intrauterine growth retardation in 2nd and 3rd trimester with fetal parameters and umbilical artery doppler. Methods: This descriptive cross-sectional research took place at Diagnostic centre, Combined Military Hospital, Lahore from September to December 2024. All eligible 130 females in 2nd and 3rd trimester had recruited excluding females with Polyhydromnias. The examination involved the use of a curvilinear transducer (3-5MHz). Non probability convenient technique was employed for data collection. IBM (SPSS) version 26.0 was used for data analysis. For inferential statistics, Chi square test was employed. Statistical p-value <0.05 was considered as a significant value. Results: The study involved 130 pregnant women (mean age 28.82 ± 4.64), with 29.2% in the 2nd and 70.8% in the 3rd trimester. IUGR history (25.4%), gestational hypertension (50.8%), and diabetes (19.2%) were noted. IUGR was diagnosed in 52 cases with 3–6week growth delays. Abnormal PI values in all cases confirmed PI as a reliable marker. Conclusions: In conclusion, fetal biometric parameters (BPD, HC, AC, FL) below the 10th percentile indicated IUGR in over one-third of 2nd and 3rd trimester pregnancies, with growth lags of 15–43 days. Abnormal umbilical artery Doppler PI was present in all IUGR cases, highlighting PI as a consistent and reliable detection marker.

This paper presents an approach of neural modeling for the diagnosis of fetus abnormality using ultrasound (US) images. The proposed algorithm is a hybrid approach wherein image processing methods have been used for preprocessing the image data, and an artificial neural network has been used as a classifier to extract fetus abnormality. Initially, 350 US images were collected in DICOM format directly from the radiologist and were preprocessed to extract the fetal biometric parameters using a morphological operator and a gradient vector flow algorithm. The extracted parameters were labeled as normal and abnormal fetal parameters. The extracted parameters were then applied to a Feed-Forward Back-propagation Neural Network (FFNN) for the training and validation purpose. These neural networks are capable to provide excellent performance in the critical cases especially in the field of pattern recognition. The result found from the proposed FFNNs was in closed confirmation with the real-time results. This modeling will help radiologist to take appropriate decisions in the boundary line cases.

目的在临床超声检查中很难对每例胎儿颈项透明层(nuchal translucency，NT)和头臀径(crown-rump length，CRL)的图像进行质量控制(以下简称“质控”)，但测量的微小差异可能增加假阳性或假阴性诊断的概率，因此，有必要建立胎儿NT检查的质控体系。本研究旨在通过对胎儿NT与CRL测量进行质控，评估超声医师在妊娠早期NT测量中的准确性，并分析增加胎儿结构平面筛查对于染色体异常检出率的影响。方法收集胎儿NT检查质控前和质控后各12个月的病例数据，质控前和质控后病例分别为2 214例及2 538例，分析病例NT中位数的倍数(NT multiple of median，NT-MoM)、log10MoM的标准差[standard deviation (SD) of log10MoM，(SD) log10MoM]、NT基于CRL的回归斜率(the slope of NT on CRL，SNC)3种质控数据。通过个体CRL的 NT-MoM在正常中位数曲线0.9~1.1 MoM范围内的程度来监测NT测量的性能，同时对log10MoM的SD和SNC进行评价。根据超声医师不同工作年限进行分组(<3年组，3~6年组，>6年组)，比较各组间的NT-MoM值，并对质控期内病例NT增厚、结构畸形、染色体异常的数据进行回顾性分析。结果根据美国NTQR项目组的曲线方程，质控前NT-MoM值为0.921 7 MoM，(SD)log10MoM值为0.091 92，SNC值为12.20%；质控后NT-MoM值为0.948 3 MoM，(SD) log10MoM值为0.094 81，SNC值为11.43%；质控前后NT-MoM值比较，差异有统计学意义(P<0.000 1)。质控前及质控后不同工作年限超声医师测量的NT-MoM值比较，差异均有统计学意义(均P<0.000 1)；工作年限3~6年组以及>6年组质控后的NT-MoM值均高于质控前(均P<0.05)，<3年组质控前和质控后比较，差异无统计学意义(P>0.05)。在质控后，胎儿NT增厚不伴明显结构异常占19.05%；NT增厚伴结构异常占47.62%；NT正常但结构异常占33.33%。胎儿合并心脏畸形36例，占总异常率的20.34%，染色体检测阳性率为36%。结论质控后，超声医师对NT的测量会更精确，但测量者之间仍然存在差异；经验丰富的超声医师的测量值更接近预期值，通常小于预期值。对胎儿NT和CRL测量值进行监测，有助于提高测量准确度；增加NT检查的结构筛查，特别是对于胎儿心脏的筛查，有利于提高染色体的异常检出率。

We sought to establish normative data for fetal liver volume (FLV) between 27 and 38 weeks' gestation using three-dimensional ultrasonography. The study design was a longitudinal prospective study involving 53 participants. A total of 250 FLV measurements were obtained, using the multiplanar method with 3.0-mm intervals. Polynomial regressions with adjustments using the determination coefficient ( R2) were used to assess the correlation between FLV and gestational age (GA) and fetal parameters (biparietal diameter, head circumference, abdominal circumference, and estimated fetal weight). The mean, standard deviation, and median, minimum, and maximum values were calculated for each gestational age. The intraclass correlation coefficient (ICC) was used to determine inter- and intraobserver reliability. There was a high correlation between FLV and GA. The mean FLV went from 43.5 +/- 7.6 cm (3) (29.1 to 62.2 cm (3)) to 130.5 +/- 20.1 cm3 (87.5 to 191.1 cm3). There was a high correlation between FLV and all fetal biometric parameters (all P < 0.0001). Intraobserver and interobserver correlations were excellent with an ICC = 0.993 and 0.984, respectively. There was a high correlation between GA and biometric parameters. Reference limits were generated for FLV between 27 and 38 weeks. FLV is highly reproducible.

AIUM Practice Parameter for the Performance of Fetal Echocardiography.

Objective To quantitatively study the correlation of the distance of pulmonary valve to pulmonary artery bifurcation (DPVB) of normal fetuses in second and late trimester with the fetal biometric parameters using fetal echocardiography. Methods The distances of pulmonary valve to pulmonary artery bifurcation in end-systole (DPVBs) and in end-diastole (DPVBd) were measured in a standard short axis view or right ventricular outflow tract view using fetal echocardiography on 419 normal fetuses. The gestation ages ranged from 20 to 35+ weeks. Fetal non-cardiac biometric parameters including biparietal diameter (BPD), femoral length (FL) and gestation age (GA) based on menstrual age, pulmonary valve annulus diameters (PA) at end-systole were measured. The correlation between DPVBs, DPVBd and non-cardiac biometric parameters were analyzed. Results In normal fetuses, the DPVBs was (1.14±0.24)cm with a range of 0.67 to 1.61 cm, the DPVBd was (0.93±0.20)cm with a range of 0.53 to 1.33 cm. The DPVBs and DPVBd were increased with the growth of GA, and were positively correlated with GA, BPD, FL and PA (r=0.827, 0.798, 0.793, 0.769; 0.802, 0.764, 0.773 and 0.771, respectively, all P<0.001). The linear regression equations between DPVBs, DPVBd and GA, BPD, FL, PA were: Y=0.054×GA-0.369, Y=0.184×BPD-0.179, Y=0.217×FL+ 0.011, Y=1.602×PA+ 0.156, Y=0.045×GA-0.330, Y=0.152×BPD-0.157, Y=0.182×FL-0.018, Y=1.380×PA+ 0.080. Conclusions In normal fetuses, the DPVBs and DPVBd increase with the growth of GA, and have good correlation with GA, BPD, FL and PA, respectively. Normal reference ranges of DPVBs and DPVBd have been provided. These normative data may become a new tool for assessment of fetal heart, especially has potential applications in screening of complex congenital heart defects. Key words: Echocardiography; Fetus; Developmental biology; Distance of pulmonary valve to pulmconary artery bifurcation

Counseling for non-invasive prenatal testing (NIPT): what pregnant women may want to know

Reply

Cross-modal Transfer Learning Based on an Improved CycleGAN Model for Accurate Kidney Segmentation in Ultrasound Images

To examine the potential impact of combining maternal age with fetal nuchal translucency thickness and maternal serum free beta-human chorionic gonadotropin (beta-hCG) and pregnancy-associated plasma protein-A (PAPP-A) in screening for trisomy 21 at 10-14 weeks of gestation. Maternal serum free beta-hCG and PAPP-A were measured by Kryptor, a random access immunoassay analyzer using time-resolved amplified cryptate emission, in 210 singleton pregnancies with trisomy 21 and 946 chromosomally normal controls, matched for maternal age, gestation and sample storage time. In all cases the fetal crown-rump length and nuchal translucency thickness had been measured by ultrasonography at 10-14 weeks of gestation and maternal blood had been obtained at the time of the scan. The distributions (in multiples of the median; MoM) of free beta-hCG and PAPP-A (corrected for maternal weight) and fetal nuchal translucency (NT) were determined in the trisomy 21 group and the controls. Likelihood ratios for the various marker combinations were calculated and these were used together with the age-related risk for trisomy 21 in the first trimester to calculate the expected detection rate of affected pregnancies, at a fixed false-positive rate, in a population with the maternal age distribution of pregnancies in England and Wales. In a population with the maternal age distribution of pregnancies in England and Wales, it was estimated that, using the combination of maternal age, fetal nuchal translucency thickness and maternal serum free beta-hCG and PAPP-A, the detection of trisomy 21 pregnancies would be 89% at a fixed false-positive rate of 5%. Alternatively, at a fixed detection rate of 70%, the false-positive rate would be 1%. The inclusion of biochemical parameters added an additional 16% to the detection rate obtained using NT and maternal age alone. Rapid diagnostic technology like Kryptor, which can provide automated reproducible biochemical measurements within 30 min of obtaining a blood sample, will allow the development of interdisciplinary one-stop clinics for early fetal assessment. Such clinics will be able to deliver improved screening sensitivity, rapidly and more efficiently, leading to reduced patient anxiety and stress.

Objective The recent legalization of marijuana has increased overall use, including in pregnancy. Studies have previously associated marijuana use with adverse fetal neurodevelopmental outcomes. We sought to compare fetal sonographic growth parameters and placental perfusion, as measured by umbilical artery Dopplers, in women using daily marijuana versus nonusers. Methods A retrospective cohort study capturing self – identified pregnant daily marijuana users with gestational aged matched controls was performed. We compared maternal demographics, fetal biometry, nuchal translucency, and umbilical artery Dopplers in marijuana users versus controls. Intrauterine growth restriction was defined as an estimated fetal weight <10th %. Results In 55 first trimester ultrasounds, there were no differences in crown rump lengths or nuchal translucencies between the groups. Likewise, in 195-second trimester ultrasounds, no differences were noted in biometry. Second trimester umbilical artery systolic to diastolic ratios were higher in marijuana users compared to nonusers (4.02 versus 3.92, p = .024). In the third trimester, 26 of 192 marijuana exposed fetuses were growth restricted compared to 6 of 192 controls (p = .002), and umbilical artery systolic to diastolic ratios were higher (3.52 versus 3.12, p = .0001). Four cases of absent and reversed end diastolic flow were observed in marijuana users, while no cases were observed in controls. Conclusions Our data shows that daily marijuana use is associated with impaired fetal growth and increased placental vascular resistance. Marijuana consumption in pregnancy should be avoided until further studies delineate its exact potential for fetotoxicity.

The objective of the paper is to introduce a novel method for nuchal translucency (NT) boundary detection and thickness measurement, which is one of the most significant markers in the early screening of chromosomal defects, namely Down syndrome. To improve the reliability and reproducibility of NT measurements, several automated methods have been introduced. However, the performance of their methods degrades when NT borders are tilted due to varying fetal movements. Therefore, we propose a principal direction estimation based NT measurement method to provide reliable and consistent performance regardless of both fetal positions and NT directions. At first, Radon Transform and cost function are used to estimate the principal direction of NT borders. Then, on the estimated angle bin, i.e., the main direction of NT, gradient based features are employed to find initial NT lines which are beginning points of the active contour fitting method to find real NT borders. Finally, the maximum thickness is measured from distances between the upper and lower border of NT by searching along to the orthogonal lines of main NT direction. To evaluate the performance, 89 of in vivo fetal images were collected and the ground-truth database was measured by clinical experts. Quantitative results using intraclass correlation coefficients and difference analysis verify that the proposed method can improve the reliability and reproducibility in the measurement of maximum NT thickness.

Introduction/Objective. Fetal growth restriction (FGR) is associated with increased fetal and neonatal mortality and morbidity. The study objective was to investigate the correlation of maternal blood biochemical markers routinely determined in the first and second trimester screening and ultrasound fetal surveillance parameters in the prediction of fetal growth and condition in singleton pregnancies. Methods. In the first trimester we measured serum levels of beta subunit of human chorionic gonadotropin (?HCG) and pregnancy-associated plasma protein A (PAPP-A). In the second trimester we measured values of chorionic gonadotropin (HCG), alpha fetoprotein (AFP), unconjugated estriol (E3) and inhibin A, also examined ultrasonographic biometric fetal parameters, amniotic fluid index (AFI) and Doppler resistance indexes. FGR was defined as ultrasonographically determined fetal weight and growth parameters below the 10th percentile for the gestational age. Obtained biochemical and ultrasonographic parameters were correlated. Results. Study included 104 singleton pregnancies. ?HCG in the first trimester correlated negatively with fetal growth in the second and third trimester, and the second trimester AFI. Increased PAPP-A correlated positively with elevated resistance index in medial cerebral artery, lower biophysical profile scores, and intermediate type of non-stress test. Lower values of E3 were associated with FGR. Elevated serum AFP levels were linked to oligoamnion in the third trimester. There was no correlation of inhibin A levels with fetal condition. Conclusion. First and second trimester biochemical markers of pregnancy (?HCG, PAPP-A, HCG, AFP and E3) in combination with ultrasonographic biophysical parameters of fetus have predictive value for fetal growth and development.

The last 20 years have seen the development of fetal surgery, particularly for the treatment of twin-to-twin transfusion syndrome (TTTS). Although fetoscopy increases survival rate, it is also invasive and responsible for fetal and maternal complications affecting the neonatal outcome. A completely non-invasive treatment that could occlude deep anastomoses would prevent the risks of invasive fetoscopy while offering the potential for more effective therapy. We previously developed a toroidal HIFU transducer that enables the destruction of large tissue volumes. The effectiveness of this HIFU device applied to the perfused placental unit must now be studied in a preclinical animal study under conditions similar to those in humans before starting a clinical trial. We report here the first use of a completely non-invasive treatment of the placenta in pregnant animals. A toroidal HIFU transducer working at 2.5 MHz and composed of 32 ring-shaped emitters was used. In vivo experiments were performed in eight pregnant monkeys. Lesions on placental tissues were performed non-invasively by placing the HIFU probe on the skin. Fetal and maternal parameters, such as maternal heart rate, fetal heart rate, and subcutaneous and intra-amniotic fluid temperature, were recorded. A C-section was performed immediately after insonification to extract the placenta, inspect the fetus and inspect the maternal abdominal cavity. Placental HIFU lesions were studied using ultrasound images, gross pathology and histology. Thirteen HIFU exposures were performed on placentas. The parameters used in this study were acoustic powers of 65, 80, 110 and 120 W applied for 30, 15, 20 and 20 seconds, respectively. This gradual increase in the total energy delivered was used to determine a set of parameters to create reproducible lesions in the placentas without any complications. The dimensions of the placental lesions were an average diameter of 6.4 ± 0.5 mm and 7.8 ± 0.7 mm and an average depth of 3.8 ± 1.5 mm. Ultrasound images revealed a hyperechoic region that was correlated with the macroscopic analyses of the HIFU lesions. Necrosis of placental tissues exposed to HIFU was confirmed with histology. No significant variation in maternal and fetal parameters was observed during HIFU exposure. This study demonstrates in a monkey model of pregnancy the feasibility of HIFU treatment applied to the placenta for potential application to treat twin-to-twin transfusion syndrome.