Fetal Biometry Research Articles

EP23.08: Fetal biometry measurements can predict neonatal hypoglycemia in women with diabetic mellitus

EP23.08: Fetal biometry measurements can predict neonatal hypoglycemia in women with diabetic mellitus

DETERMINING THE GESTATIONAL USING FOETAL KIDNEY LENGTH DURING THIRD TRIMESTER PREGNANCY IN INDIAN POPULATION

Introduction: Although fetal biometry measurements aid in an accurate estimation of GA in the early second trimester, the biological variations of size lead to these parameters' accuracy to vary as the age of the fetus advanced, making it challenging to date a fetus accurately in the late second or third trimester. Therefore, this study conducted to assess correlation of foetal kidney length with gestational age in third trimester of pregnancy. Methodology: This was a cross-sectional observational study conducted among 120 pregnant women in the 3rd trimester. For obtaining foetal kidney length, longitudinal section was taken in sagittal plane using ultrasound. Results: Out of total 120 cases, the left kidney length (LKL) is slightly higher than the right kidney length (RKL). Mean kidney lengths (MKL) rose consist-ently with gestational age, from 27.18 ± 2.2O mm at 28 weeks to З8.O ± l.8O mm at З9 weeks. RKL, LKL and MKL were positively correlated with gestational age. R squared (R2) value was 0.769 which is a good fit and indicates that this regression model explains 76.9% changes in GA with MKL. Conclusion: Foetal kidney length is a reliable measure of gestational age. Measuring the foetal mean kidney length using ultrasound is a simple tech-nique to determine the gestational age. In third trimester pregnancy with un-certain LMP, the length of the foetal kidneys may be extremely helpful in de-termining gestational age.

Lung Hypoplasia in Fetuses with Skeletal Dysplasia Determined by Fetal Lung Weight: Which Ultrasound Measurement/Ratio Has the Highest Detection Rate

Introduction: To determine lung hypoplasia in cases with fetal skeletal dysplasia based on the total lung weight at autopsy as the most accountable surrogate marker for pulmonary hypoplasia. Methods: This retrospective cohort study included all pregnancies with antenatal diagnosis of skeletal dysplasia (2012–2018). We included only cases in which information on fetal biometry was available within 2 weeks before delivery and had autopsy and skeletal X-rays + molecular analysis using extracted fetal DNA. We compared the predictive accuracy of fetal sonographic body-proportional ratios (BPRs) including: (1) thoracic circumference-to-abdominal circumference ratio, (2) the femur length-to-abdominal circumference (FL/AC) ratio, (3) head circumference-to-abdominal circumference ratio, and (4) foot length-to-femur length ratio. Lung hypoplasia was defined as total lung weight below −2 SD from the expected mean for gestational age. Results: Fifty three pregnancies with antenatal diagnosis of skeletal dysplasia underwent autopsy included. Lung hypoplasia was determined in 34 (64.1%). Median of gestational age at last sonographic assessment was 21.3 (19.9–24.9) weeks. FL/AC ratio demonstrated the highest area under the curve of 0.817 (95% CI: 0.685–0.949; p < 0.0001). FL/AC ≤0.1550 demonstrated the highest detection rate of 88.2% along with the highest negative predictive value of 75%. Conclusion: Using a novel, more practical approach to predict lung hypoplasia in skeletal dysplasia, fetal sonographic BPRs and, specifically, FL/AC ratio demonstrate a high detection rate of lung hypoplasia.

The effects of gestational diabetes mellitus on fetal growth: is it different for low-risk and medium-high-risk pregnant women?

It has been suggested that gestational diabetes mellitus (GDM) alters the growth trajectory of a fetus and increases the risk of abnormal birth weight. In spite of this, there is still a significant debate regarding the mode and optimal timing of diagnosing this condition. Our aim was to determine fetal growth velocity and birth biometry in pregnant women with GDM at varying risk levels. We conducted a cohort study involving 1023 pregnant women at a maternity hospital in Ma'anshan, China. All women completed an oral glucose tolerance test at 24-28 weeks' gestation. We measured fetal head circumference (HC), femoral length (FL), abdominal circumference (AC), biparietal diameter (BPD), and estimate fetal weight (EFW) by ultrasound at 17, 24, 31, and 35 weeks' gestation, respectively. Overall, 5115 ultrasound scans were performed. Among both low-risk and medium-high-risk pregnant women at 17-24 weeks' gestation, GDM exposure was associated with an increase in fetal growth velocity. Neonates born to women with GDM at medium-high risk had significantly larger birth weights than those born to women without GDM, while this was not observed in women at low risk. In medium-high-risk pregnant women, exposure to GDM has a greater effect on the fetus, leading to abnormal fetal growth velocity that lasts beyond week 24. It is evident from our results that the effects of GDM on fetal growth differ between medium-high-risk pregnant women and low-risk pregnant women, and therefore a different screening program based on the risk factor for GDM is warranted.

Memory-based unsupervised video clinical quality assessment with multi-modality data in fetal ultrasound

In obstetric sonography, the quality of acquisition of ultrasound scan video is crucial for accurate (manual or automated) biometric measurement and fetal health assessment. However, the nature of fetal ultrasound involves free-hand probe manipulation and this can make it challenging to capture high-quality videos for fetal biometry, especially for the less-experienced sonographer. Manually checking the quality of acquired videos would be time-consuming, subjective and requires a comprehensive understanding of fetal anatomy. Thus, it would be advantageous to develop an automatic quality assessment method to support video standardization and improve diagnostic accuracy of video-based analysis. In this paper, we propose a general and purely data-driven video-based quality assessment framework which directly learns a distinguishable feature representation from high-quality ultrasound videos alone, without anatomical annotations. Our solution effectively utilizes both spatial and temporal information of ultrasound videos. The spatio-temporal representation is learned by a bi-directional reconstruction between the video space and the feature space, enhanced by a key-query memory module proposed in the feature space. To further improve performance, two additional modalities are introduced in training which are the sonographer gaze and optical flow derived from the video. Two different clinical quality assessment tasks in fetal ultrasound are considered in our experiments, i.e., measurement of the fetal head circumference and cerebellar diameter; in both of these, low-quality videos are detected by the large reconstruction error in the feature space. Extensive experimental evaluation demonstrates the merits of our approach.

Comparaison pragmatique des courbes de biométries fœtales élémentaires

IntroductionThe fetal biometrics charts recommended in France for ultrasound screening include measurements of head circumference (HC), biparietal diameter (BIP), abdominal circumference (AC) and femur length (FL). New international growth standards have been recommended since 2022. The aim of this work is to quantitatively describe the differences between these biometric curves. MethodsThe biometry curves from the French College for Fetal Ultrasound, OMS and INTERGROWTH-21 are pragmatically compared based on their original quantile regression equations (superposition and quantification of differences in millimeters and in proportion) for different percentiles of clinical interest. ResultsCompared with the new charts, CFEF underestimates HC<-3DS and AC<10eP. The proportions of differences between the CFEF and INTERGROWTH-21 or WHO curves always remained <5%. The proportions of difference of the 3rd percentile of HC and FL, 10th and 90th percentile of AC were always lower than 2%, 2%, 5% and 4% respectively, between OMS and INTERGROWTH-21. ConclusionThe switch to prescriptive standards suggests an improvement in the detection of fetuses with AC<10th percentile, an improvement in the detection of prenatal onset microcephaly, with no argument for a decrease in the detection rate of severe constitutional bone disease or modification of obstetrical guidelines.

A system-on-chip solution for deep learning-based automatic fetal biometric measurement

Ultrasound assessment of fetal biometry is widely used for gestational age prediction and abnormal fetal growth diagnosis. However, manual biometric measurements require time-consuming procedures and current automated measurement approaches remain challenging in terms of accuracy and computational complexity. This paper proposes deep learning-based efficient automatic fetal biometry measurement method for system-on-chip (SoC) solution. For end-to-end automated measurements, a hardware-friendly bilateral segmentation network (H-BiSeNet) was designed and optimized for multiple fetal objects (i.e., head, abdomen and femur), and fetal biometric parameters were then calculated with a robust multiple keypoint detection algorithm. For hardware implementation with a SoC, a deep learning processing unit (DPU) was employed to accelerate the proposed segmentation network, and biometric measurements with image pre- and postprocessing were conducted on an application processing unit (APU). A total of 6000 fetal ultrasound images in the three regions were collected from 2568 subjects, and the dataset was utilized to train the proposed network. In the performance evaluation, the proposed segmentation network with optimal quantization (H-BiSeNet-Q) outperformed other segmentation networks (i.e., U-Net, U-Net++, Attention U-Net, U-Net3+, DeepLabv3 + and BiSeNetv2) in terms of the average Dice coefficient, and automated measurements with H-BiSeNet-Q were highly correlated with manual measurements (r ≥ 0.983, p < 0.01 for all parameters, i.e., biparietal diameter, head circumference, abdominal circumference and femur length). In the execution time analysis, H-BiSeNet-Q ran at 4.25 frames per second (FPS) with parallelism corresponding to 80% resource utilization in the SoC. These results showed feasibility in low-resource hardware settings such as portable ultrasound systems.

ROLE OF DOPPLER ULTRASOUND AT 13 WEEKS GESTATION IN PREDICTION OF PRE-ECLAMPSIA

Objective: The objective of this study was to assess the role of Doppler ultrasound (USG) at 13-week gestation in the prediction of pre-eclampsia (PE) and to assess the mean pulsatility index (PI) in uterine arteries at 13-week Doppler ultrasonography for the early prediction of PE. Methods: This was a observational prospective cohort study in which all the pregnant females at 12–14 weeks gestation were subjected to Doppler waveform analysis on color Doppler USG machines. Obstetric parameters of fetal biometry, mean PI (using the TVS method), and percentiles were calculated using fetal medicine foundation proforma. Reports were categorized as high risk or low risk for the development of PE. Routine USG follow-up scanning was done at 18–20 weeks (Anomaly scan) 24–28 weeks (Growth scan) and 34–36 weeks (Doppler scan) for the development of PE and intrauterine growth restriction. Development or absence of PE was noted. Results: Four hundred antenatal patients were included in the study. The maximum number of patients was in the age group 21–30 years (75.50%). No significant difference in the occurrence of PE in different age groups was found in our study. The incidence of PE was 3.33% (1 out of 30) in patients who developed PE at a later stage. Similar incidence of hypertension was 10% (three out of 30), smoking, and diabetes in 2 and 3 each. The mean uterine artery PI level at 12–14 weeks was 3.11±0.12 in patients who developed PE. In our study, 24 (80%) high-risk (&gt;1:150) and 10 (33.33%) low-risk (≤1:150) patients developed PE. Out of 30, 4 (13.33%) had Apgar 0–3, 6 (20%) had Apgar 4–6, and 20 (66.67%) had Apgar 7–10 in patients who developed PE. Conclusion: High mean uterine artery PI between 12 and 14 weeks gestation is a good predictor of PE and can be used as an effective screening tool. Diastolic notch in the uterine artery and combination of uterine artery Doppler parameters is better in the prediction of PE.

Do differences in diagnostic criteria for late fetal growth restriction matter?

Criteria for diagnosis of fetal growth restriction differ widely according to national and international guidelines, and further heterogeneity arises from the use of different biometric and Doppler reference charts, making the diagnosis of fetal growth restriction highly variable. This study aimed to compare fetal growth restriction definitions between Delphi consensus and Society for Maternal-Fetal Medicine definitions, using different standards/charts for fetal biometry and different reference ranges for Doppler velocimetry parameters. From the TRUFFLE 2 feasibility study (856 women with singleton pregnancy at 32+0 to 36+6 weeks of gestation and at risk of fetal growth restriction), we selected 564 women with available mid-pregnancy biometry. For the comparison, we used standards/charts for estimated fetal weight and abdominal circumference from Hadlock, INTERGROWTH-21st, and GROW and Chitty. Percentiles for umbilical artery pulsatility index and its ratios with middle cerebral artery pulsatility index were calculated using Arduini and Ebbing reference charts. Sensitivity and specificity for low birthweight and adverse perinatal outcome were evaluated. Different combinations of definitions and reference charts identified substantially different proportions of fetuses within our population as having fetal growth restriction, varying from 38% (with Delphi consensus definition, INTERGROWTH-21st biometric standards, and Arduini Doppler reference ranges) to 93% (with Society for Maternal-Fetal Medicine definition and Hadlock biometric standards). None of the different combinations tested appeared effective, with relative risk for birthweight <10th percentile between 1.4 and 2.1. Birthweight <10th percentile was observed most frequently when selection was made with the GROW/Chitty charts, slightly less with the Hadlock standard, and least frequently with the INTERGROWTH-21st standard. Using the Ebbing Doppler reference ranges resulted in a far higher proportion identified as having fetal growth restriction compared with the Arduini Doppler reference ranges, whereas Delphi consensus definition with Ebbing Doppler reference ranges produced similar results to those of the Society for Maternal-Fetal Medicine definition. Application of Delphi consensus definition with Arduini Doppler reference ranges was significantly associated with adverse perinatal outcome, with any biometric standards/charts. The Society for Maternal-Fetal Medicine definition could not accurately detect adverse perinatal outcome irrespective of estimated fetal weight standard/chart used. Different combinations of fetal growth restriction definitions, biometry standards/charts, and Doppler reference ranges identify different proportions of fetuses with fetal growth restriction. The difference in adverse perinatal outcome may be modest, but can have a significant impact in terms of rate of intervention.

Admission ultrasonography as a means of identifying unrecognized fetal compromise in term singleton pregnancies at the onset of labor – a feasibility study

Objectives Apparently uncomplicated low-risk pregnancies, especially first time births, account for a significant proportion of adverse birth outcomes. Improved risk stratification with a simple bedside scan on admission in early labor could potentially reduce adverse intrapartum outcomes. The aim of this feasibility study was to assess a cohort of low-risk subjects with admission ultrasonography at the onset of labor with a view to conducting a future randomized controlled trial (RCT). The objectives were three-fold; i) to determine the logistics of performing a labor admission ultrasound scan ii) to establish whether abnormal ultrasound features can be identified and iii) whether they are associated with emergency delivery and/or poor condition of the neonate at birth. Methods We performed a prospective cohort study of 295 participants with term singleton cephalic pregnancies admitted in early labor or for labor induction with non-fetal indications. The setting was a university teaching hospital in Ireland with almost 8000 births annually. A bedside ultrasound scan was performed to assess fetal biometry, amniotic fluid volume and placental maturity. Patients and their babies were followed up until hospital discharge. The outcomes of interest included image quality, time to perform a scan, oligohydramnios (Single Deepest Pool ≤ 2 cm), small for gestational age (SGA; abdominal circumference <10th centile), mature placenta (Grannum 2 or 3), pathological CTG, emergency cesarean section (CS), fetal acidosis (cord arterial pH <7.10 or base excess <-12.0), low Apgar score <7 at 5 min and neonatal unit admission. Results Image quality was optimal in 274 of the 295 scans (93%) and 271 (92%) were completed in less than 10 min. Of this low-risk population, 67 of 294 (23%) had oligohydramnios, 11 (4%) were small for gestational age and 87 (30%) had a mature placenta (Grannum grade 2). The incidence of pathological CTG and emergency CS was higher among patients with oligohydramnios than those with a normal scan but did not reach statistical significance; Odds Ratio 3.40 (95% Confidence Intervals 0.55 to 20.92) and OR 1.43 (95% CI 0.66 to 3.08) respectively. The mean birthweight was significantly lower in those with oligohydramnios −139 g (95% CI −248 to −30) and admission scan detected SGA −357 g (95% CI −557 to −137). Adverse perinatal outcomes were uncommon with a higher incidence of fetal acidosis (pH < 7.10) in the oligohydramnios group. The incidence of neonatal unit admission >24 h was higher in the oligohydramnios group but not statistically significant; OR 3.75 (95% CI 0.61 to 22.97). Results for SGA alone were non-significant and results for oligohydramnios and SGA combined were similar to those for oligohydramnios alone. Conclusions Admission ultrasonography is feasible in a routine clinical setting, but evidence of benefit is weak and does not currently justify a randomized controlled trial.

First-trimester choroid-plexus-to-lateral-ventricle disproportion and prediction of subsequent ventriculomegaly.

Ventriculomegaly can be associated with long-term neurodevelopmental impairment. Prenatal diagnosis of ventriculomegaly is most commonly made at the routine second-trimester anomaly scan. The value of first-trimester ultrasound has expanded to early diagnosis and screening of fetal abnormalities. The objective of this study was to assess the predictive accuracy of first-trimester choroid-plexus-to-lateral-ventricle-or-head ratios for development of ventriculomegaly at a later gestational age. This was a case-control study of fetuses with isolated ventriculomegaly diagnosed after 16 weeks' gestation and a control group of normal fetuses (without ventriculomegaly). The exclusion criteria included aneuploidy, genetic syndrome and/or other brain abnormality. Stored two-dimensional first-trimester ultrasound images were analyzed blindly offline and fetal biometry was performed in the axial view of the fetal head. The ratios of choroid plexus area (PA) to lateral ventricular area (VA), choroid plexus length (PL) to lateral ventricular length (VL), choroid plexus diameter (PD) to lateral ventricular diameter (VD) and PA to biparietal diameter (BPD) were measured at 11 + 0 to 13 + 6 weeks' gestation. Intra- and interobserver variability of measurement of these fetal head biometric parameters at 11 + 0 to 13 + 6 weeks' gestation were assessed in 20 normal fetuses using intraclass correlation coefficients with 95% CI. The accuracy of first-trimester biometric measurements for prediction of ventriculomegaly was assessed using the area under the receiver-operating-characteristics curves (AUC). The analysis included 683 singleton pregnancies, of which 102 fetuses were diagnosed with ventriculomegaly. Ventriculomegaly was mild in 86 (84.3%) cases and severe in the other 16 (15.7%). All first-trimester fetal choroid-plexus-to-lateral-ventricle/head ratios were significantly lower in cases with ventriculomegaly compared with controls (P < 0.001), with good inter- and intraobserver agreement (≥ 0.95) for the majority of the fetal head biometric parameters assessed. On adjusting for crown-rump length, optimism-adjusted AUC values obtained after cross-validation showed that both PL/VL ratio (AUC, 0.87 (95% CI, 0.73-0.98)) and PA/VA ratio (AUC, 0.90 (95% CI, 0.82-0.98)) had good predictive accuracy for severe ventriculomegaly. The PA/BPD ratio (AUC, 0.73 (95% CI, 0.54-0.90)) had modest predictive ability, which was significantly lower compared with that of the PA/VA ratio and PL/VL ratio (P = 0.003 and P = 0.001, respectively). The predictive accuracy of PD/VD ratio was low with an AUC of 0.65 (95% CI, 0.47-0.84). Optimism-adjusted AUC values obtained after cross-validation showed that PA/VA ratio offered the highest predictive accuracy for mild ventriculomegaly with an AUC of 0.84 (95% CI, 0.79-0.89), followed by PL/VL ratio (AUC, 0.82 (95% CI, 0.76-0.88)), PA/BPD ratio (AUC, 0.76 (95% CI, 0.69-0.82)) and PD/VD ratio (AUC, 0.75 (95% CI, 0.67-0.81)). Calibration plots showed that both PA/VA and PL/VL ratios had good calibration. First-trimester prediction of ventriculomegaly using ratios of fetal choroid plexus to lateral ventricle/head appears promising. Future prospective studies are needed to validate the predictive accuracy of these ultrasound markers as a screening tool for ventriculomegaly. © 2023 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

Artificial intelligence in obstetric ultrasound: A scoping review.

The objective is to summarize the current use of artificial intelligence (AI) in obstetric ultrasound. PubMed, Cochrane Library, and ClinicalTrials.gov databases were searched using the following keywords "neural networks", OR "artificial intelligence", OR "machine learning", OR "deep learning", AND "obstetrics", OR "obstetrical", OR "fetus", OR "foetus", OR "fetal", OR "foetal", OR "pregnancy", or "pregnant", AND "ultrasound" from inception through May 2022. The search was limited to the English language. Studies were eligible for inclusion if they described the use of AI in obstetric ultrasound. Obstetric ultrasound was defined as the process of obtaining ultrasound images of a fetus, amniotic fluid, or placenta. AI was defined as the use of neural networks, machine learning, or deep learning methods. The authors' search identified a total of 127 papers that fulfilled our inclusion criteria. The current uses of AI in obstetric ultrasound include first trimester pregnancy ultrasound, assessment of placenta, fetal biometry, fetal echocardiography, fetal neurosonography, assessment of fetal anatomy, and other uses including assessment of fetal lung maturity and screening for risk of adverse pregnancy outcomes. AI holds the potential to improve the ultrasound efficiency, pregnancy outcomes in low resource settings, detection of congenital malformations and prediction of adverse pregnancy outcomes.

Evaluation of fetal biometric indices for fetal growth restriction diagnosis

BACKGROUND: Fetal Growth Restriction occurs when a fetus does not reach its intrauterine growth potential due to genetic and/or environmental factors; it is associated with increased perinatal mortality and morbidity and also predisposes to the development of chronic disorders in adulthood. The aim of this study was to evaluate the accuracy of the Biometric Indices: Femur Length/Abdominal Circumference (FL/AC); Transverse Cerebellar Diameter/Abdominal Circumference (TCD/AC) and Humerus, Cerebellum, Femur/Abdominal Circumference Equation (HCF/AC); in predicting fetal growth retardation. METHODS: Diagnostic tests validation study, with a universe of pregnant patients who attended the outpatient clinic of Hospital General Machala, El Oro-Ecuador, for prenatal control, between 32 and 38 weeks of gestation. The following variables were obtained: gestational dating; ultrasound fetal biometry of all the necessary parameters for the described indices calculation; fetal weight estimated by ultrasound, with cut-off point ≤ P° 10. The LH/CA and TCD/CA Indices were calculated, with cut-off points for fetal growth retardation diagnosis of ≥ 23.5 and ≥16.1 respectively. The index proposed by the authors HCF/CA was also applied, taking as cut-off point the 90th percentile: ≥ 1.063. RESULTS: The prevalence of fetal weight less P° 10 in the present study was 12.22%. The biometric index with the highest sensitivity was the HCF CA index with 70.3%; however, the highest specificity was obtained for the LF CA index with 84%. The positive predictive value of the DTC CA index was 24.7%, of the LF CA index: 27.9%, and of the HCF CA index: 31.1%. The negative predictive values found were, DTC CA: 93.9%; LF CA: 91.6% and HCF CA: 95.0%. The positive likelihood ratios obtained were: DTC CA: 2.352; LF CA: 2.781 and HCF CA: 3.25. The negative likelihood ratios were, HCF CA: 0.378, DTC CA: 0.465, LF CA: 0.661. CONCLUSION:The biometric indices for prediction of fetal growth retardation have limited positive predictive accuracy. All indices have high negative predictive accuracy. To confirm the presence of condition disease the HCF CA index has better results, as well as to confirm the absence of the condition disease; the addition of the HCF CA Index increases the predictive results; the Odds Rate obtained indicates that there is 8.595 times higher probability of a positive response, when the condition"fetus in percentile ≤ 10" is present.

Effect of magnet strength on fetal brain biometry - a single-center retrospective MRI-based cohort study.

Abnormal fetal brain measurements might affect clinical management and parental counseling. The effect of between-field-strength differences was not evaluated in quantitative fetal brain imaging until now. Our study aimed to compare fetal brain biometry measurements in 3.0T with 1.5T scanners. A retrospective cohort of 1150 low-risk fetuses scanned between 2012 and 2021, with apparently normal brain anatomy, were retrospectively evaluated for biometric measurements. The cohort included 1.5T (442 fetuses) and 3.0T scans (708 fetuses) of populations with comparable characteristics in the same tertiary medical center. Manually measured biometry included bi-parietal, fronto-occipital and trans-cerebellar diameters, length of the corpus-callosum, vermis height, and width. Measurements were then converted to centiles based on previously reported biometric reference charts. The 1.5T centiles were compared with the 3.0T centiles. No significant differences between centiles of bi-parietal diameter, trans-cerebellar diameter, or length of the corpus callosum between 1.5T and 3.0T scanners were found. Small absolute differences were found in the vermis height, with higher centiles in the 3.0T, compared to the 1.5T scanner (54.6th-centile, vs. 39.0th-centile, p < 0.001); less significant differences were found in vermis width centiles (46.9th-centile vs. 37.5th-centile, p = 0.03). Fronto-occipital diameter was higher in 1.5T than in the 3.0T scanner (66.0th-centile vs. 61.8th-centile, p = 0.02). The increasing use of 3.0T MRI for fetal imaging poses a potential bias when using 1.5T-based charts. We elucidate those biometric measurements are comparable, with relatively small between-field-strength differences, when using manual biometric measurements. Small inter-magnet differences can be related to higher spatial resolution with 3T scanners and may be substantial when evaluating small brain structures, such as the vermis.

Use of artificial intelligence and deep learning in fetal ultrasound imaging.

Deep learning is considered the leading artificial intelligence tool in image analysis in general. Deep-learning algorithms excel at image recognition, which makes them valuable in medical imaging. Obstetric ultrasound has become the gold standard imaging modality for detection and diagnosis of fetal malformations. However, ultrasound relies heavily on the operator's experience, making it unreliable in inexperienced hands. Several studies have proposed the use of deep-learning models as a tool to support sonographers, in an attempt to overcome these problems inherent to ultrasound. Deep learning has many clinical applications in the field of fetal imaging, including identification of normal and abnormal fetal anatomy and measurement of fetal biometry. In this Review, we provide a comprehensive explanation of the fundamentals of deep learning in fetal imaging, with particular focus on its clinical applicability. © 2022 International Society of Ultrasound in Obstetrics and Gynecology.

Effect of infection with severe acute respiratory syndrome coronavirus 2 on the fetus in pregnant women who recovered from infection.

The effect of maternal infection with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) on the fetus is unclear, and there is no data from Saudi Arabia. Assess the effect of maternal SARS-CoV-2 infection on fetal growth. Retrospective case-control SETTING: Tertiary care hospital, Riyadh, Saudi Arabia PATIENTS AND METHODS: We selected pregnant women who underwent an obstetric growth scan and umbilical artery Doppler ultra-sound examination between 28 and 41 weeks of pregnancy. Women with multiple pregnancy, fetal abnormalities, maternal body mass index >30, maternal hypertension, any other chronic diseases that might affect fetal growth or pregnant women suffering from cancer were excluded. Fetal growth parameters assessed included fetal biometry (biparietal diameter, head circumference, abdominal circumference and femur length). We also did an umbilical artery Doppler assessment, which includes the umbilical artery pulsatility index, resistive index and the systolic/diastolic ratio. Fetal biometry and biophysical profile SAMPLE SIZE: 48 SARS-CoV-2; 98 non-SARS-CoV-2 RESULTS: More women who had recovered from SARS-CoV-2 infection had small for gestational age fetuses compared with the control group (P=.001). Maternal SARS-CoV-2 infection during pregnancy was associated with a higher prevalence of small for gestational age (SGA) fetuses. Retrospective, middle cerebral artery and uterine artery Doppler data were not included nor were the effect of tobacco use and socioeconomic status, the relationship between the date of infection with the date of conceiving or the relationship between the severity of infection in the mother and fetal biometry and growth. None.

Ultrasonographic Estimation of the Gestational Age Using the Fetal Kidney Length in the Second and Third Trimesters of Pregnancy Among South Indian Antenatal Women: A Cross-Sectional Study.

Background and Objective Accurately estimating the age of the fetus is crucial to prevent morbidity and mortality for both the fetus and mother during the perinatal period. Additionally, it enables early intervention in cases of complicated pregnancies. Multiple parameters are used for the estimation of fetal gestational age (FGA) and the expected date of delivery (EDD), butno single parameter is found to be accurate and standard. This study aims to analyze the fetal kidney length (FKL) as a means to estimate gestational age and investigate the growth pattern of the fetal kidney during the early and late weeks of gestation. Furthermore, it seeks to establish correlations between FKL and gold standard parameters from the 18th week to the 38th week of gestation. Methodology This cross-sectional research was carried out after obtaining proper institutional ethical clearance. The pregnant women who came to the gynecology outpatient department (OPD) between 18 and 38 weeks were included in this study after obtaining informed consent. The fetal biometry was measured using the ultrasonographic transducer (3-5 MHz). Results The mean FKL exhibited a consistent increase throughout the entire pregnancy, ranging from 16.50 ± 2.10to 39.20 ± 3.10 mm. The rate of increase in FKL was significant between the early weeks (18-24) of pregnancy, with insignificant growth in other weeks of gestation. The growth of the fetal kidney (length) exhibited a gradual increase from the early weeks to the late weeks of pregnancy, with a consistent growth rate of approximately 1mm per week from 18 to 35 weeks. However, in the final three weeks of pregnancy (36th, 37th, and 38th weeks), the FKL measurements were recorded as 37.90 ± 3.90, 38.90 ± 3.10, and 40.20 ± 3.10 mm, respectively. A positive correlationwas noted between the FKL with all standard parameters such as biparietal diameter (BPD), femur length (FL), head circumference (HC), and abdominal circumference (AC). Conclusions This study concluded that incorporating FKLalongside standard fetal biometric parameters such as BPD, FL, HC, and ACenhanced the accuracy of calculating FGAand EDDduring the early second trimester. Furthermore, it proved beneficial in diagnosing fetal anomalies during early pregnancies.

ULTRASOUND FETAL KIDNEY LENGTH FOR ASSESSMENT OF GESTATIONAL AGE

Fetal kidney length (FKL) has recently been found to have a strong correlation with gestational age. According to the findings of these investigations, the fetal kidney length may be utilized to estimate gestational age when dates are ambiguous or when women seek ultrasound fetal biometry dating during the third trimester itself.&#x0D; GA estimation is also a prerequisite to interpret certain tests (amniotic fluid assay, serum assay, chorionic villus sampling) and to plan timing of various forms of fetal therapy. Failure in estimating GA accurately can result in unnecessary induction, dysfunctional labor, operative delivery, iatrogenic prematurity or post maturity, false interpretation of tests and delay or failure of fetal therapy, thereby increasing perinatal morbidity and mortality.&#x0D; This review looks in to various studies assessing correlation of Fetal kidney length with gestational age in third trimester of pregnancy and provide a comprehensive view on use of Fetal kidney length for estimation of gestational age in third trimester of pregnancy.

Evaluation of fetal adrenal artery Doppler velocimetry and fetal adrenal gland size in pregnancies after recovery from COVID-19.

Assessment of the fetal adrenal gland (FAG) size and middle adrenal artery (MAA) Doppler parameters in pregnancy recovered from Coronavirus Disease (COVID-19) and comparison of the values with the healthy control group. Thirty-eight pregnant women who had recovered from COVID-19 infection and 76 healthy control group between 33 and 35 weeks of gestation were involved in this case-control study. Fetuses were examined for fetal biometry, fetal well-being, adrenal gland dimensions, and Doppler parameters 4-6 weeks after the diagnosis of COVID 19 infection. FAG dimensions were measured in two planes and MAA blood flow velocity was evaluated with pulsed Doppler. Pregnant women with COVID-19 infection were grouped according to the National Institutes of Health for the severity of the disease, and those with mild and moderate infections were examined in the study. The total adrenal gland (TAG) height, fetal zone (FZ) length and width, and MAA-Peak Systolic Velocity (MAA-PSV) were significantly higher, and the MAA-Pulsatility Index (MAA-PI) was significantly lower in the COVID-19 group (p < 0.05). The lower in MAA-PI and the higher in MAA-PSV, the width of the FZ, and width of the TAG were found to be significant in the moderate group compared to the mild groups (p < 0.05). COVID-19 pregnancies might cause early maturation of the FAG and its vasculature depends on the intrauterine stress due to the hyper-inflammation, so fetuses exposed to maternal COVID-19 suggested to have an increase in blood flow to the adrenal gland and fetal adrenal size.

Fetal growth restriction and small for gestational age as predictors of neonatal morbidity: which growth nomogram to use?

Fetal growth nomograms were developed to screen for fetal growth restriction and guide clinical care to improve perinatal outcomes; however, existing literature remains inconclusive regarding which nomogram is the gold standard. This study aimed to compare the ability of 4 commonly used nomograms (Hadlock, International Fetal and Newborn Growth Consortium for the 21st Century, Eunice Kennedy Shriver National Institute of Child Health and Human Development-unified standard, and World Health Organization fetal growth charts) and 1 institution-specific reference to predict small for gestational age and poor neonatal outcomes. This was a retrospective cohort study of all nonanomalous singleton pregnancies undergoing ultrasound at ≥20 weeks of gestation between 2013 and 2020 and delivering at a single academic center. Using random selection methods, the study sample was restricted to 1 pregnancy per patient and 1 ultrasound per pregnancy completed at ≥22 weeks of gestation. Fetal biometry data were used to calculate estimated fetal weight and percentiles according to the aforementioned 5 nomograms. Maternal and neonatal data were extracted from electronic medical records. Logistic regression was used to estimate the association between estimated fetal weight of <10th and <3rd percentiles compared with estimated fetal weight of 10th to 90th percentile as the reference group for small for gestational age and the neonatal composite outcomes (perinatal mortality, hypoxic-ischemic encephalopathy or seizures, respiratory morbidity, intraventricular hemorrhage, necrotizing enterocolitis, hyperbilirubinemia or hypoglycemia requiring neonatal intensive care unit admission, and retinopathy of prematurity). Receiver operating characteristic curve contrast estimation (primary analysis) and test characteristics were calculated for all nomograms and the prediction of small for gestational age and the neonatal composite outcomes. We restricted the sample to ultrasounds performed within 28 days of delivery; moreover, similar analyses were completed to assess the prediction of small for gestational age and neonatal composite outcomes. Among 10,045 participants, the proportion of fetuses classified as <10th percentile varied across nomograms from 4.9% to 9.7%. Fetuses with an estimated fetal weight of <10th percentile had an increased risk of small for gestational age (odds ratio, 9.9 [95% confidence interval, 8.5-11.5] to 12.8 [95% confidence interval, 10.9-15.0]). In addition, the estimated fetal weight of <10th and <3rd percentile was associated with increased risk of the neonatal composite outcome (odds ratio, 2.4 [95% confidence interval, 2.0-2.8] to 3.5 [95% confidence interval, 2.9-4.3] and 5.7 [95% confidence interval, 4.5-7.2] to 8.8 [95% confidence interval, 6.6-11.8], respectively). The prediction of small for gestational age with an estimated fetal weight of <10th percentile had a positive likelihood ratio of 6.3 to 8.5 and an area under the curve of 0.62 to 0.67. Similarly, the prediction of the neonatal composite outcome with an estimated fetal weight of <10th percentile had a positive likelihood ratio of 2.1 to 3.1 and an area under the curve of 0.55 to 0.57. When analyses were restricted to ultrasound within 4 weeks of delivery, among fetuses with an estimated fetal weight of <10th percentile, the risk of small for gestational age increased across all nomograms (odds ratio, 16.7 [95% confidence interval, 12.6-22.3] to 25.1 [95% confidence interval, 17.0-37.0]), and prediction improved (positive likelihood ratio, 8.3-15.0; area under the curve, 0.69-0.75). Similarly, the risk of neonatal composite outcome increased (odds ratio, 3.2 [95% confidence interval, 2.4-4.2] to 5.2 [95% confidence interval, 3.8-7.2]), and prediction marginally improved (positive likelihood ratio, 2.4-4.1; area under the curve, 0.60-0.62). Importantly, the risk of both being small for gestational age and having the neonatal composite outcome further increased (odds ratio, 21.4 [95% confidence interval, 13.6-33.6] to 28.7 (95% confidence interval, 18.6-44.3]), and the prediction of concurrent small for gestational age and neonatal composite outcome greatly improved (positive likelihood ratio, 6.0-10.0; area under the curve, 0.80-0.83). In this large cohort, Hadlock, recent fetal growth nomograms, and a local population-derived fetal growth reference performed comparably in the prediction of small for gestational age and neonatal composite outcomes.