Search

Background:: Detecting congenital heart defects (CHDs) is challenging due to the difficulty of identifying subtle abnormalities in fetal heart structures. Objectives:: To develop a deep learning-based method for segmenting vessels in the three-vessel view (3VV) to characterise the vessels by size and spatial relationships to detect abnormal fetal hearts. Methods:: We present a deep learning-based method that takes as input a fetal heart ultrasound (US) video of the three vessels view (3VV) and an anchor frame, which contains the segmentation of the pulmonary artery (PA), aorta (Ao), and superior vena cava (SVC) in the 3VV. The method automatically segments the anatomical structures subsequent to the anchor frame and classifies the US video as normal or abnormal. The method consists of two phases. The first phase combines three residual networks (ResNets) extended with a self-attention block and a refinement module. The second phase extends a ResNet with two CoordConv layers integrating spatial coordinates. We assess segmentation performance using the intersection over union (IoU) and dice similarity coefficient (DSC) metrics and classification of US videos using sensitivity and specificity. We also investigate the tolerance to failure of the method by introducing mislabelled anchor frames. The dataset used in this study consists of 150 US videos of the 3VV; 50 videos were used for training, and 100 videos (50 normal videos, 50 abnormal videos) for testing. Results:: In terms of anatomical structure segmentation accuracy, the method achieves an average IoU of 89.5% (99.5% for PA, 85.0% for Ao, and 84.1% for SVC), and an average DSC of 0.950% (0.946% for PA, 0.969% for Ao, and 0.934% for SVC). Detection of abnormal videos achieved a sensitivity of 0.99 and specificity of 1.0. The tolerance to failure analysis shows a decrease in the sensitivity of 0.023 and 0.015 for normal and abnormal case videos, respectively. Conclusions:: The initial evaluation of our approach to fetal CHDs on 3VV ultrasound videos is promising but requires further refinement and evaluation on a larger dataset to assess clinical utility. The approach is designed to be translatable to low-resource settings where fetal echocardiography experts are unavailable due to the simple acquisition protocol.

Abstract Background Twin pregnancy comprising of a complete hydatidiform mole with a coexisting twin live fetus is an uncommon condition with an incidence rate of 1 in 20,000 to 1 in 100,000 pregnancies, more so in assisted reproductive technologies. The primary diagnosis is made on ultrasound and adjunct fetal MRI helps in unequivocally differentiating it from other disorder. Case presentation We present a case report of a twin pregnancy consisting of complete hydatidiform mole with a coexisting twin live fetus in a 27-year-old primigravida conception, primarily focusing on its diagnostic algorithm and related clinical aspects, adding to the paucity of existing literature. Conclusions Following the correct diagnostic algorithm with imaging studies like USG and more importantly MRI, combined with the bioclinical picture helps in reaching the accurate diagnosis.

Abstract Background According to prenatal ultrasonographic studies, single umbilical artery may be present alone or in association with other fetal abnormalities. So far, the exact pathogenesis of bladder exstrophy is unclear. Some scholars believe that bladder exstrophy and cloacal exstrophy should be regarded as a disease spectrum to explore their pathogenesis. If bladder exstrophy and cloacal exstrophy are regarded as the same disease spectrum, then we can speculate that the single umbilical artery should have the probability of being accompanied by bladder exstrophy at the same time. Case presentation For the first time, we report a rare case of fetal bladder exstrophy with single umbilical artery in single pregnancy. This patient underwent targeted color Doppler ultrasound at 26 weeks of pregnancy which first suspected bladder exstrophy with single umbilical artery and fetal MRI for diagnosis at 38 + 3 weeks of pregnancy which confirmed the suspicion. After the diagnosis was confirmed, the patient was scheduled for a multidisciplinary discussion. Ultimately the patient opted for induced fetal demise at 38 + 5 weeks of pregnancy and the physical appearance of the fetal demise affirmed previous ultrasound and MRI examination results. Conclusions Our report is the first finding of single umbilical artery combined with bladder exstrophy in a singleton pregnancy. Accordingly, our case enhances the evidence that cloacal exstrophy and bladder exstrophy should be treated as the same disease spectrum. In addition, we conducted a literature review on the diagnostic progress of single umbilical artery combined with bladder exstrophy, hoping to provide useful references for the diagnosis of this disease.

The detection of fetal ultrasound standard planes (FUSPs) is important for the diagnosis of fetal malformation and the prevention of perinatal death. As a promising deep-learning technique in FUSP detection, SonoNet’s network parameters have a large size. In this paper, we introduced a light pyramid convolution (LPC) block into SonoNet and proposed LPC-SonoNet with reduced network parameters for FUSP detection. The LPC block used pyramid convolution architecture inspired by SimSPPF from YOLOv6 and was able to extract features from various scales with a small parameter size. Using SonoNet64 as the backbone, the proposed network removed one of the convolutional blocks in SonoNet64 and replaced the others with LPC blocks. The proposed LPC-SonoNet model was trained and tested on a publicly available dataset with 12,400 ultrasound images. The dataset with six categories was further divided into nine categories. The images were randomly divided into a training set, a validation set, and a test set in a ratio of 8:1:1. Data augmentation was conducted on the training set to address the data imbalance issue. In the classification of six categories and nine categories, LPC-SonoNet obtained the accuracy of 97.0% and 91.9% on the test set, respectively, slightly higher than the accuracy of 96.60% and 91.70% by SonoNet64. Compared with SonoNet64 with 14.9 million parameters, LPC-SonoNet had a much smaller parameter size (4.3 million). This study pioneered the deep-learning classification of nine categories of FUSPs. The proposed LPC-SonoNet may be used as a lightweight network for FUSP detection.

Introduction: Toxoplasmosis is a parasitism transmitted by Toxoplasma gondii, part of the TORCH complex, the most prevalent parasitism worldwide. It is asymptomatic in immunocompetent individuals but causes severe infections and developmental abnormalities in pregnant women, mainly affecting the central nervous system and the gastrointestinal system. Methods: In our prospective study, we analyzed cases of recent maternal Toxoplasma infections confirmed by serological testing between 1996 and 2020 at the Department of Obstetrics and Gynecology, Semmelweis University. Amniocentesis, followed by PCR, was performed in cases of recent infection confirmed by serological testing during pregnancy. After birth, a neonatological, microbiological, pediatric neurological and ophthalmological examination and a follow-up was carried out. Results: During the study period, a total of 238 cases of amniotic fluid Toxoplasma PCR testing due to Toxoplasma recent infection were performed. In terms of pregnancies, there were 219 deliveries and seven abortions. Twelve cases had no data available on the outcome of the pregnancy. In total, 133 cases of ultrasound abnormalities were detected during pregnancy, while in 105 cases, no abnormalities were detected on ultrasound examination. During amniocentesis, eight cases of Toxoplasma infection were revealed in amniotic fluid samples by PCR, and in 230 cases, the result was negative. Neonatal follow-up was performed in 139 cases, with no abnormalities during follow-up in 117 cases, and in 22 cases, there was a detectable complication that was likely to be related to Toxoplasma infection. In all 22 cases, amniotic fluid PCR Toxoplasma testing was negative. Conclusions: The most common ultrasound abnormalities involve the nervous system and the gastrointestinal system. In cases of suspicion, it is recommended to perform amniocentesis Toxoplasma PCR testing besides the indirect methods to help the pregnant woman decide whether to carry the pregnancy to term. During follow-up, a multidisciplinary team experienced in pregnancies complicated by toxoplasmosis must carry out the follow-up, care and subsequent development.

Objective: We present prenatal ultrasound images of two high anal atresia cases. The main screening tool used in our clinic is the “target sign” in the tangential view of the fetal perineum. In the current report, we discuss some challenges in the existing screening practices. Case report: Case 1: A 28-year-old woman (gravida 1, para 0) with a twin pregnancy underwent ultrasound screening at 21 weeks of gestation when an absent “target sign” in twin A was discovered. At the same time, we were able to present evidence that if the wrong plane was visualized, other structures could be mistaken as the “target sign”. Eventually, high-type anal atresia was confirmed postnatally in Twin A. Case 2: A 29-year-old woman (gravida 1, para 0) came to our clinic for routine screening at 23 weeks of gestation. In the standard tangential view at the level of the perineum, a low-high concentric circle structure resembling a “target sign” was visualized during a prenatal scan. However, anal atresia was discovered postnatally. A retrospective review of prenatal images revealed discrepancies from the typical “target sign”. Conclusion: High-type anal atresia may present as a pseudo “target sign” on prenatal ultrasound. Visualization of a “target sign” on fetal ultrasound does not always exclude the diagnosis of anal atresia. It is crucial to evaluate the size, shape, level, and position of the “target sign”. The appearance of the bilateral hyperechoic perianal tissue is a hint for the screening of anal atresia.

Abstract Objective The cause of fetal overgrowth during pregnancy is still unclear. This study aimed to analyze and predict the risk of macrosomia in pregnant women with gestational diabetes mellitus (GDM). Methods This study was a retrospective study collected from October 2020 to October 2021. A total of 6072 pregnant women with a routine 75-g oral glucose tolerance test (OGTT) during 24–28 gestational weeks were screened. Nearly equal numbers of pregnant women with gestational diabetes and with normal glucose tolerance (NGT) were included in the study. Multivariate logistic regression analysis and receiver operating characteristic (ROC) curve were performed to determine the index and inflection point for predicting macrosomia occurrence. Results The data of perinatal outcomes of 322 GDM and 353 NGT who had given birth to single live babies at term were analyzed. We found that significant cut-off values for the prediction of macrosomia are 5.13mmol/L in fasting plasma glucose (FPG), 12.25kg in gestational weight gain (GWG), 3,605g in ultrasound fetal weight gain (FWG) and 124mm in amniotic fluid index (AFI).The area under the ROC curve of this predictive model combined all variables reached 0.953 (95% CI: 0.914 ~ 0.993) with a sensitivity of 95.0% and a specificity of 85.4%. Conclusions FPG is positively associated with newborn birth weight. An early intervention to prevent macrosomia may be possible by combining maternal GWG, FPG, FWG, and AFI in gestational diabetes.

Fetal cardiac MRI is a rapidly evolving form of diagnostic testing with utility as a complementary imaging modality for the diagnosis of congenital heart disease and assessment of the fetal cardiovascular system. Previous technical limitations without cardiac gating for the fetal heart rate has been overcome with recent technology. There is potential utility of fetal electrocardiography for direct cardiac gating. In addition to anatomic assessment, innovative technology has allowed for assessment of blood flow, 3D datasets, and 4D flow, providing important insight into fetal cardiovascular physiology. Despite remaining technical barriers, with increased use of fCMR worldwide, it will become an important clinical tool to improve the prenatal care of fetuses with CHD.

Aim To determine the trends in preterm birth (PTB) rates in Samrakshan after initiating a third-trimester screening protocol. Methods The Samrakshan program of IRIA focused on clinical stage-based management of fetal growth restriction (FGR) in the third trimester integrating fetal Doppler studies with routine trimester-specific antenatal scans. Mean uterine artery pulsatility index (PI), umbilical artery PI, middle cerebral artery PI, and cerebroplacental ratio were assessed for all third-trimester pregnant women in the program. Results From 2019 to 2022, 249 (18.33%, 95% CI: 16.34, 20.54) women had PTB with 221 (16.67%, 95% CI: 14.73, 18.75) PTBs between 34 and 37 gestation weeks and 22 (1.66%, 95% CI: 1.10, 2.50) PTBs at gestation

It is now almost impossible to imagine a pregnancy in The Netherlands without one or two fetal ultrasounds. In contrast to the biomedical view of seeing ultrasound technology as a transparent window into the womb, much scholarly research in the social sciences highlights that the technology is not neutral, but has different meanings and applications depending on the context. Feminist anthropologists have mostly criticized ultrasound technology for invading the intimate experience of pregnancy and making women “invisible.” This article focuses on socalled “entertainment” ultrasounds to explore how pregnant women in The Netherlands use ultrasound technology for new, unintended purposes. Using semi-structured interviews and discourse analysis of websites of commercial ultrasound clinics, I demonstrate that many pregnant women in The Netherlands consider the ultrasound scan a positive and valuable experience that they can consciously use to feel less insecure and to relax during their pregnancy. It is argued that, in looking so closely at the structural power relations that limit women’s agency, feminist anthropologists often downplay the possible leeway that expectant mothers have. These women are not forced into doing “entertainment” ultrasound scans but are active agents appropriating the technology.

Christy L Pylypjuk,1 Shiza F Memon,2 Bernard N Chodirker3 1Department of Obstetrics, Gynecology and Reproductive Sciences (Section of Maternal-Fetal Medicine), Children’s Hospital Research Institute of Manitoba, University of Manitoba, Winnipeg, MB, Canada; 2Department of Obstetrics, Gynecology & Reproductive Sciences, University of Manitoba, Winnipeg, MB, Canada; 3Departments of Pediatrics and Child Health (Section of Genetics and Metabolism) & Biochemistry and Medical Genetics, University of Manitoba, Winnipeg, MB, CanadaCorrespondence: Christy L Pylypjuk, WN5002, HSC Women’s Hospital, 820 Sherbrook Street, Winnipeg, MB, R3A 1R9, Canada, Tel +1 204 787-4821, Fax +1 204 787-2920, Email cpylypjuk@hsc.mb.caObjective: To evaluate the utility of measuring fetal cavum septum pellucidum (CSP) width during routine, mid-pregnancy ultrasound for improving diagnosis of 22q11.2 deletion syndrome amongst fetuses with and without conotruncal anomalies.Patients and Methods: This was a retrospective case-control study (2005– 2016). Fetuses and newborns with 22q11.2 deletion and/or conotruncal cardiac anomalies were identified using a regional, clinical database. A control group was assembled in a 2:1 ratio to create three groups for comparison: i) 22q11.2 deletion syndrome; ii) isolated conotruncal anomalies; and iii) controls. Eligibility was restricted to those with stored ultrasound images between 18– 22 weeks’ gestation and a minimum biparietal diameter of 40 mm. Post-processing measurement of CSP width was performed in a standardized fashion by two blinded and independent study personnel. Descriptive and inferential statistics, regression modeling, and receiver operator curves (ROC) were used to compare outcomes between groups and evaluate sensitivity/specificity of CSP width as a marker of 22q11.2 deletion syndrome.Results: Twenty-nine cases of 22q11.2 deletion and 64 cases of isolated conotruncal anomalies were matched to 186 healthy controls. Cases with 22q11.2 deletion syndrome had significantly larger CSP widths (5.36 mm; SD=1.2) compared to those with isolated conotruncal anomalies (3.75 mm; SD=1.11) and healthy controls (2.93 mm; SD=0.57; p< 0.0001). There was no difference in CSP width amongst those with 22q11.2 deletion irrespective of the presence/absence of a conotruncal anomaly (p=0.362), or by type of conotruncal anomaly (p=0.211). Using a CSP width cutoff > 4.3 mm, fetuses with 22q11.2 deletion can be accurately identified with good sensitivity (89.7%) and specificity (84%).Conclusion: Fetuses with 22q11.2 deletion syndrome have dilated CSPs when compared to those with isolated conotruncal anomalies or controls. Because CSP dilation can be evaluated during routine mid-pregnancy ultrasound using standard images of the fetal head, measurement could easily be incorporated to enhance prenatal diagnosis of this phenotypically diverse condition.Keywords: DiGeorge syndrome, 22q11 microdeletion, cavum septum pellucidum, prenatal diagnosis, fetal ultrasound, neurosonography

Abstract Background Third trimester fetal anthropometric parameters are known to predict neonatal complications. A better understanding of predictors of adverse fetal parameters might help to personalize the use and frequency of fetal ultrasound. The objectives of this study were: (a) to evaluate the utility of maternal sociodemographic, anthropometric and metabolic predictors to predict 3rd trimester fetal anthropometric parameters in women with gestational diabetes mellitus (GDM), (b) to assess whether the impact of these maternal predictors is fetal sex-dependent, and (c) to provide a risk stratification for markers of fetal overgrowth (fetal weight centile (FWC) and fetal abdominal circumference centile (FACC) depending on prepregnancy BMI and gestational weight gain (GWG) until the 1st GDM visit. Methods This prospective study included 189 women with GDM. Maternal predictors were age, ethnicity, prepregnancy BMI, GWG and excessive weight gain until the 1st GDM visit, fasting, 1-hour and 2-hour blood glucose oral glucose tolerance test values, HbA1c at the 1st visit and medical treatment requirement. Fetal outcomes included FWC, FWC >90% and 90% and 90% and FACC. GWG until the 1st GDM visit was associated with FWC, FACC and FACC > 90% (all p ≤ 0.045). Other maternal parameters were not significantly associated with fetal anthropometry in multivariate analyses (all p ≥ 0.054). In female fetuses, only GWG was associated with FACC (p= 0.044). However, in male fetuses, prepregnancy BMI was associated with FWC, FWC > 90% and FACC and GWG with FWC in multivariate analyses (all p ≤ 0.030). In women with a prepregnancy BMI of ≥ 25 kg/m2 and a GWG until the 1st GDM visit ≥ 10.3 kg (mean GWG), the risk for FWC > 90% and FACC > 90% was 5.3 and 4 times higher than in their counterparts. Conclusions A personalized fetal ultrasound surveillance guided by fetal sex, prepregnancy BMI and GWG may be beneficial in reducing adverse fetal and neonatal outcomes.

Introduction Maternal glycemic state is positively correlated with fetal insulin secretion. Randomized control studies have shown that treatment during pregnancy inhibits to some degree this glycemic effect. Our study aimed to assess fetal pancreas size in a population of treated mothers with gestational diabetes. Material and methods A cross-sectional, prospective observational study was conducted. Pregnant women at 19–36 weeks of gestation with pre-gestational diabetes receiving insulin therapy or with gestational diabetes receiving either insulin or oral hypoglycemic therapy were recruited. The fetal pancreas circumference was measured and compared to the normal reference range. The Z score of the difference between measured and normal predicted mean pancreas circumference, the regression analysis throughout pregnancy, and the correlation between estimated fetal weight centile and pancreas circumference were calculated. Results Ninety-one women who had gestational diabetes and thirty-four women who had pre-gestational diabetes were included in the study. For both groups, fetal pancreas circumference correlated significantly with abdominal circumference, estimated fetal weight and gestational age. The mean Z score between the predicted pancreas circumference in the group of women diagnosed with gestational diabetes and the predicted pancreas circumference in a normal population peaked at around 24 weeks of gestation (1.1) and decreased gradually afterward to a value of zero at 37 weeks. The mean Z score between the predicted pancreas circumference in the group of women with pre-gestational diabetes and the predicted pancreas circumference in a normal population constantly decreased with duration of pregnancy. It was positive until the 25th week of gestation and then presented negative values towards the term. Conclusions The presented preliminary data suggest a possible correlation between glycemic control treatment, pancreas size, and gestational age.

Abstract Background The molecular mutations of the L1CAM gene and the imaging appearances of four fetuses with L1 syndrome from three independent Chinese families with a history of hydrocephalus were reported in this study. Two of the three are novel L1CAM variants. Methods Results of clinical and imaging examinations of three Chinese families were collected. Fetal samples were collected by puncture, genomic DNA was extracted, whole‐exome sequencing was performed, and the L1CAM gene mutation sites were verified by PCR and Sanger sequencing. Results In this case report, we described the imaging appearance and investigated the mutations of the L1CAM gene in three Chinese families with a history of L1 syndrome; these included two nonsense mutations (c.262C>T and c.261C>G) and one splice‐site mutation (c.524‐1G>A). Two of these three are novel L1CAM variants: c.262C>T and c.261C>G. The results of the sonographic images of the affected fetuses showed severe hydrocephalus. Bilateral lateral ventricles were dilated in the fetuses with c.262C>T and c.261C>G mutations. The left ventricle was about 14 mm wide and the right was about 14 mm in the fetus with c.262C>T mutation. The left ventricle was about 24.9 mm wide and the right was about 23.9 mm in the fetus with c.261C>G mutation. The ultrasound examination of the fetus with c.524‐1G>A mutation showed that the third ventricle (7.5 mm wide) was raised, and the fourth ventricle was communicated with the cisterna magna. The parents requested termination of the above pregnancy. Conclusion The current study emphasizes the importance of combining family history, prenatal ultrasonography, and L1CAM mutation testing positive for the diagnosis of the L1 syndrome.

Background: Prenatal inguinoscrotal hernia is a rare condition and currently there are only several reports in the literature. Materials: We present a case of inguinoscrotal hernia in a 37-weeks’ gestation fetus, diagnosed at routine prenatal ultrasound. Surgical anomaly correction was done two months after Cesarian section in 39 weeks’ gestation. Results: We discussed the differential diagnosis of scrotal tumor formations that may occur prenatally. We performed a systematic literature review to provide useful information for the diagnosis and the management of this rare prenatal pathology. Discussion: Inguinoscrotal hernia occurs in both single or multifetal pregnancies with no side predilection; it does not mandate a change in the mode or time of delivery with recommendations for correction shortly after birth. Currently, there are no long-term follow-up data about fertility issues in fetuses with inguinoscrotal hernia in their adolescence.

Background: Ultrasonography (US) is the first-line diagnostic tool used to assess fetal musculoskeletal (MSK) anomalies. Associated anomalies in other organ systems may benefit from evaluation via Magnetic Resonance Imaging (MRI). In this study, we compared the diagnostic accuracy of US and MRI to diagnose fetal MSK (primary objective) and non-MSK anomalies (secondary objective). We describe additional findings by low-dose computerized tomography (CT) in two cases incompletely characterized via US and MRI. Materials and Methods: This was an IRB-approved retrospective study of consecutive patients with suspected fetal MSK anomalies examined between December 2015 and June 2020. We compared individual MSK and non-MSK anomalies identified via US, MRI, and CT with postnatal outcomes. Sensitivity and specificity for US and MRI were calculated and compared. Results: A total of 31 patients with 112 MSK and 43 non-MSK anomalies were included. The sensitivity of MRI and US for MSK anomalies was not significantly different (76.6% vs. 61.3%, p = 0.3). Low-dose CT identified eight additional skeletal anomalies. MRI diagnosed a higher number of non-MSK anomalies compared to US (81.4% vs. 37.2%, p < 0.05). Conclusions: Fetal MRI and US have comparable sensitivity for MSK anomalies. In selected cases, low-dose CT may provide additional information. Fetal MRI detected a larger number of non-MSK anomalies in other organ systems compared to US. Multimodality imaging combining all the information provided by MRI, US, and CT, if necessary, ultimately achieved a sensitivity of 89.2% (95% CI: 83.4% to 95.0%) for the diagnosis of musculoskeletal anomalies and 81.4% for additional anomalies in other organs and systems.

Background: Fetal tachyarrhythmia is a condition that may lead to cardiac dysfunction, hydrops, and death. Despite a transplacental treatment, failure to obtain or maintain sinus rhythm may occur. Objective: We aimed to analyze the perinatal outcomes of sustained fetal tachyarrhythmias after in utero treatment. Methods: We performed a retrospective evaluation of 69 cases with sustained fetal tachyarrhythmia. We compared the perinatal and long-term outcomes of prenatally converted and drug-resistant fetuses. Tachyarrhythmia subtypes were also evaluated. Results: Conversion to sinus rhythm was obtained in 74% of cases; 26% of cases were drug-resistant and delivered arrhythmic. Three perinatal deaths occurred in both groups (6.7% vs 17%, P = .34). Neonates delivered arrhythmic were more frequently admitted to neonatal intensive care units (75% vs 31%, P < .01), and their hospital stay was longer (20.9 vs 6.64 days, P < .001). Multiple neonatal recurrences (81% vs 11%, P < .001), temporary hemodynamic dysfunction or heart failure (50% vs 6.7%, P < .001), and postnatal use of a combination treatment (44% vs 13%, P = .028) were also more frequent in this population. Beyond the neonatal period, rates of recurrences within the first 16 months were higher in drug-resistant fetuses (HR = 16.14, CI 95% [4.485; 193.8], P < .001). In this population, postnatal electrocardiogram revealed an overrepresentation of rare mechanisms, especially permanent junctional reciprocating tachycardia (PJRT) (31%). Conclusion: Prenatal conversion to stable sinus rhythm is a major determinant of perinatal and long-term outcomes in fetal tachyarrhythmias. The underlying electrophysiological mechanisms have a major role in predicting these differential outcomes with an overrepresentation of PJRT in the drug-resistant population.

During pregnancy, fetal ultrasound provides essential insight into a baby’s growth and development. In this ultrasound, accurate assessment of fetal head biometry is critical to the clinical management of pregnancy. Current methodologies used for fetal head biometry heavily rely upon sonographer skills and experience to locate a baby’s head. In this paper a novel approach is proposed to automate the fetal head biometry using live ultrasound feed; which is also capable of tackling low abdominal contrast against surroundings. Proposed model is trained on ALEXNET and UNET for classification and segmentation of headframes respectively from ultrasound video. To compute biparietal diameter (BPD) and head circumference (HC); which are essential requirements to compute gestational age, an ellipse is drawn on the contour of the annotated segmented fetal head. It should be noted that to validate gestational age estimate, ellipse are drawn on multiple best classified headframes obtained using ALEXNET. The proposed system is able to estimate gestational age within clinically acceptable ± one week of observed gestational age with an accuracy of 96%. Moreover, it uses robust machine vision features to reduce the sonographer’s interaction with the system, thus reducing the overall procedure time and making it independent of sonographer’s skill.

Abstract Background Meconium peritonitis (MP) is a rare fetal disease that needs to be urgently identified for surgical intervention. We report a series of 35 patients diagnosed prenatally with MP by magnetic resonance imaging (MRI), illustrate the imaging findings and investigate the predictive value of these findings for postpartum management. Method A consecutive cohort of patients diagnosed with MP who were born at our institution from 2013 to 2018 was enrolled retrospectively. The prenatal ultrasound and MRI findings were analyzed. Fisher’s exact probability test was used to evaluate the predictive value of MRI for surgical intervention between the operative group and the nonoperative group. Results Ascites (30/35) and distended bowel loops (27/35) were two of the most common prenatal MP-related findings on fetal MRI. Of the 35 infants, 26 received surgical intervention. All fetuses with MRI scans showing bowel dilatation (14/26, p = 0.048) and micro-colorectum (13/26, p = 0.013) required surgery. There were no significant differences in the number of fetuses with meconium pseudocysts and peritoneal calcifications between the two groups. Conclusion Fetuses with bowel dilatation and micro-colorectum on MRI may need postpartum surgical intervention. Infants with only a small amount of ascites and slight bowel distention were likely to receive conservative treatment.

In our case, the hyperechogenicity of the fetal intestine was observed for the first time during the 12th week sonography and was not resolved later. At the ultrasound checkup at 27 weeks, there was intestinal and gastric dilation; during the following one, at 29 weeks, a peritoneal effusion was also evident. The conditions of the fetus worsened rapidly, and the cardiotocographic trace showed a very reduced cardiac variability that required an urgent cesarean section. The abdominal ultrasound per­formed immedi­ately after birth revealed corpuscolar abdominal free fluids. The bowel loops were dilated, with very thick walls, filled with corpuscle material. The child’s clinical condition worsened rapidly. The oxygen saturation was at the lower limit even after the administration of Curosurf®. For this reason, it was not possible to transfer the patient to the Pediatric Surgery Department. So the surgeon performed a paracentesis in the Neonatal Intensive Care Unit (NICU), subtracting about 100 cc of hemorrhagic fluid. After a transitory improvement, the little girl died. The autopsy confirmed the presence of an intestinal volvulus with extensive hemorrhagic necrosis of the whole ileum, with dilated loops filled with hemorrhagic fluid, in the absence of intestinal malrotation.

A 24-year-old pregnant woman with an in vitro fertilization (IVF)-assisted pregnancy was examined at 12 weeks of gestation with a fetal ultrasound showing intestinal hyperechogenicity. The maternal anamnesis revealed 3 previous miscarriages, 2 due to ectopic pregnancies. Fetal karyotype and screening for cystic fibrosis performed on both parents were normal. Another ultrasound examination at 27 weeks showed fetal intestinal and gastric dilation and moderate polyhydramnios. The day before delivery, an ascitic effusion was found, not associated with pleural or pericardial effusion. At 29 weeks and 6 days of gestation, an emergency cesarean section was performed for absent variability of the cardiotocographic tracing. The female newborn birth weight was 1,390 g. Apgar scores were 5 at 1 minute and 7 at 5 minutes. The patient was intubated in the Delivery Room and remained on mechanical ventilation until she was transferred to the Neonatal Intensive Care Unit (NICU), then she was ventilated in high-frequency oscillatory ventilation (HFOV). At the time of admission to the NICU, in addition to severe respiratory insufficiency (the saturation was at the lower limits, with FiO2 = 1), at the clinical examination she had moderate pale skin and globose abdomen with generalized tenderness. The nasogastric tube was positioned correctly, and 6 ml of gastric fluid mixed with blood were aspirated. It was possible to insert the rectal tube only for 1.5 cm. To better understand the case, anteroposterior (AP) and translateral chest-abdomen X-rays were performed. 1. What do you see in these X-rays? 2. Which further investigations would you suggest? 3. What is your diagnosis?

Background: The role of fetal magnetic resonance imaging (MRI) was studied in antenatal anomalies detected by ultrasound. Materials and Methods: The study was conducted in the Department of Radiodiagnosis and Imaging, Government Medical College, Srinagar, over a period of 12 months including all pregnant women with suspected fetal anomalies on ultrasonography (US). Results: In 9/23 cases (39.1%), the US findings and MRI findings were similar. MRI changed the diagnosis in 11/23 cases (47.8%). MRI provided additional information than US in 2/23 cases (8.69%), and there was 1/23 (4.3%) cases in which US provided additional information to that provided by MRI in terms of intrauterine growth restriction. Conclusions: US and MRI are complementary to each other in reaching a diagnosis in the fetal central nervous system abnormalities, and MRI is a major problem-solving modality where the US findings are inconclusive. The major role for fetal MRI was found in confirmation of inconclusive sonographic findings and the evaluation of sonographically occult diagnoses.

Based on epidemiological and experimental evidence, the origins of childhood obesity and early onset metabolic syndrome can be extended back to developmental processes during intrauterine life. It is necessary to actively investigate antecedent conditions that affect fetal growth by developing reliable measures to identify variations in fetal fat deposition and body composition. Recently, the resolution of ultrasonography has remarkably improved, which enables better tissue characterization and quantification of fetal fat accumulation. In addition, fetal fractional limb volume has been introduced as a novel measure to quantify fetal soft tissue volume, including fat mass and lean mass. Detecting extreme variations in fetal fat deposition may provide further insights into the origins of altered fetal body composition in pathophysiological conditions (i.e., fetal growth restriction or fetal macrosomia), which are predisposed to the metabolic syndrome in later life. Further studies are warranted to determine the maternal or placental factors that affect fetal fat deposition and body composition. Elucidating these factors may help develop clinical interventions for altered fetal growth and body composition, which could potentially lead to primary prevention of the future risk of metabolic dysfunction.

Objective: Large scale retrospective analysis of fetal ultrasound (US) data is important in the understanding of the cumulative impact of antenatal factors on offspring's health outcomes. Although the benefits are evident, there is a paucity of research into such large scale studies as it requires tedious and expensive effort in manual processing of large scale data repositories. This study presents an automated framework to facilitate retrospective analysis of large scale US data repositories. Method: Our framework consists of four modules: (1) an image classifier to distinguish the Brightness (B) -mode images; (2) a fetal image structure identifier to select US images containing user-defined fetal structures of interest (fSOI); (3) a biometry measurement algorithm to measure the fSOIs in the images and, (4) a visual evaluation module to allow clinicians to validate the outcomes. Results: We demonstrated our framework using thalamus as the fSOI from a hospital repository of more than 80,000 patients, consisting of 3,816,967 antenatal US files (DICOM objects). Our framework classified 1,869,105 B-mode images and from which 38,786 thalamus images were identified. We selected a random subset of 1290 US files with 558 B-mode (containing 19 thalamus images and the rest being other US data) and evaluated our framework performance. With the evaluation set, B-mode image classification resulted in accuracy, precision, and recall (APR) of 98.67%, 99.75% and 98.57% respectively. For fSOI identification, APR was 93.12%, 97.76% and 80.78% respectively. Conclusion: We introduced a completely automated approach designed to analyze a large scale data repository to enable retrospective clinical research.

An allantoic cyst is a rare malformation with a frequency of 3 in 1,000,000 that may be seen antenatally by ultrasound assessment when the connection between the cloaca (future bladder) and the allantois fails to regress. A patent urachus that presents as a cyst (allantoic) is usually considered not to be associated with chromosomal abnormalities, but if it is not repaired after birth this leads to complications such as urinary tract infections and stone formation. We present a case of a fetus diagnosed with allantoic cyst at the first trimester ultrasound assessment at 12 weeks gestation. The follow up scans showed a decrease in size of the allantoic cyst with no other obvious major defects and, when invasive testing (amniocentesis with microarray analysis) was performed, a rare microdeletion, 1q21.1q21.2 was identified (1.82 Mb deletion).

Sonographic findings of cerebral arteriovenous malformations in the fetus are uncommon and usually regard aneurysm of the Galen vein. Outcome of arteriovenous malformations is usually severe. We report a case of a fetus at 21 weeks’ gestation with a rarer arteriovenous malformation, referred to us for echocardiography on account of a suspicious cardiomegaly at obstetrical scan. Upon examination, we found cardiomegaly, together with an associated moderate tricuspid regurgitation, however, there were no clear features of tricuspid dysplasia. Considering an unusually dilated superior vena cava, we found via color Doppler imaging a systodiastolic flow at Color Doppler progressing. Subsequent MRI of the central nervous system determined the localization in the sinus dura mater. Due to an already evident hemodynamic impact, the parents opted for the termination of the pregnancy. Autopsy confirmed a voluminous arteriovenous malformation of the transverse sinus of the dura mater, severe cardiomegaly, mainly of the ventricles, and hypoplasia of the lungs.

Background: Adverse outcomes of pregnancy are a challenging health-care problem. Prediction of adverse pregnancy outcomes is important to prevent the morbidities of the foetus and the mother. Aims: To study the clinical interest of fetal nasal bone length in predicting adverse pregnancy outcomes in the first trimester of pregnancy. Study Design: A population-based retrospective cohort study. Methods: Data from 868 women with first-trimester fetal nasal bone length and birth records available were enrolled. Fetal nasal bone length percentiles were determined and evaluated for their ability to predict adverse pregnancy outcomes such as preterm birth, preterm labour, preterm premature rupture of membranes, early preterm birth, gestational diabetes mellitus, gestational hypertension-preeclampsia, small-for-gestational age foetuses, macrosomia, oligohydramnios, polyhydramnios and fetal distress. Results: Fetal nasal bone length >95th percentile was significantly associated with preterm labor and preterm premature rupture of membranes (p=0.02, accuracy 0.91 and p=0.001, accuracy 0.94, respectively), whereas nasal bone length >99th percentile was significantly associated with preterm labor and oligohydramnios (p=0.006, accuracy 0.95 and p=0.014, accuracy 0.97). Conclusion: Fetal nasal bone length at high percentiles in the first trimester of pregnancy may aid in the prediction of adverse outcomes such as preterm labour, preterm premature rupture of membranes and oligohydramnios

The myocardial performance index is widely used as an indicator of the heart’s performance. However, due to the subjective nature of ultrasonic testing, there are differences in the measurements among inspectors, requiring a quantitative and objective assessment. In this study, an automated program was developed to quantitatively evaluate the myocardial performance index (MPI) and the cardiac time intervals in the left ventricle for each trimester. One hundred and thirty-three pregnant women who visited the hospital for prenatal examinations were studied, and skilled inspectors obtained left ventricular blood flow waveforms from 47 fetuses in the 12 weeks, 54 fetuses in the 22 weeks, and 32 fetuses in the 31 weeks of pregnancy using a pulse Doppler mode of ultrasound equipment. The acquired images automatically measured the isovolumetric contraction time (IVCT), isovolumetric relaxation time (IVRT,) ejection time (ET), and filling time (FT), and calculated the Tei index (TI) and the K-index (KI); each interval was manually measured during the actual inspection for comparison. In this study, the ultrasonic Doppler waveform was objectively analyzed and measured by the automated program, and it will help with the evaluation of fetal heart function.

Ventriculomegaly represents the dilation of the cerebral ventricles above 10 mm, being classified as it follows: mild or “borderline” (10-12 mm), moderate (13-15 mm) and severe (over 15 mm). The incidence varies very much depending on the used technique and the gestational age. The level of choice in order to obtain the most exact measurement of the ventricular diameter is at the level of choroid plexus glomus. The MRI is another method to assess the fetal brain that allows also the evaluation of the cerebral surface. Unilateral ventriculomegaly is caused by the morphologic, physical or functional obstruction of foramen Monro. “Borderline” ventriculomegaly can be associated with chromosomal anomalies, congenital infections, cerebral vascular accidents or hemorrhage, but also other extra-cerebral anomalies. The factors that influence the prognosis of children diagnosed with mild ventriculomegaly are: gender, gestational age, ventricular size, uni- or bilateral impairment, symmetrical or asymmentrical bilateral ventriculomegaly, progression of ventriculomegaly – probably the most important factor of prognosis, regression of ventriculomegaly. The parents must be informed about the fact that there are certain ultrasonographic limitations regarding the differentiation of an isolated “borderline” ventriculomegaly of a ventriculomegaly associated to other occult anomalies that can not be identified initially, in order to take an adequate decision. The control fetal ultrasound is preferable to be performed after approximately 1-2 weeks from the moment of initial diagnosis of “ventriculomegaly”.

Congenital heart malformations, with an incidence of 6-8/1,000 births, represent about 30% of cases of infant mortality due to congenital abnormalities. Of these, most require immediate corrective surgery in the neonatal period. Kidney and urinary tract malformations have an incidence of approximately 1%. The development of ultrasound techniques allowed for prenatal diagnosis of many fetal malformations, some of them lifethreatening. Thus, important ethical problems occur, concerning abortion or guidance of the pregnant woman to a center where the newborn will be operated in the first hours of life.

The application of segmentation methods to medical imaging has the potential to create novel diagnostic support models. With respect to fetal ultrasound, the thoracic wall is a key structure on the assessment of the chest region for examiners to recognize the relative orientation and size of structures inside the thorax, which are critical components in neonatal prognosis. In this study, to improve the segmentation performance of the thoracic wall in fetal ultrasound videos, we proposed a novel model-agnostic method using deep learning techniques: the Multi-Frame + Cylinder method (MFCY). The Multi-frame method (MF) uses time-series information of ultrasound videos, and the Cylinder method (CY) utilizes the shape of the thoracic wall. To evaluate the achieved improvement, we performed segmentation using five-fold cross-validation on 538 ultrasound frames in the four-chamber view (4CV) of 256 normal cases using U-net and DeepLabv3+. MFCY increased the mean values of the intersection over union (IoU) of thoracic wall segmentation from 0.448 to 0.493 for U-net and from 0.417 to 0.470 for DeepLabv3+. These results demonstrated that MFCY improved the segmentation performance of the thoracic wall in fetal ultrasound videos without altering the network structure. MFCY is expected to facilitate the development of diagnostic support models in fetal ultrasound by providing further accurate segmentation of the thoracic wall.

Abstract Objective To evaluate the utility of ultrasound in identifying fetuses with uncommon chromosomal abnormalities that would be considered not detectable by cell-free fetal deoxyribonucleic acid (cfDNA). Study Design We performed a retrospective study of fetuses with chromosomal abnormalities that would be undetectable by cfDNA, who underwent an 11- to 14-week ultrasound from 2006 to 2016. Results There were 43 pregnancies included. First-trimester ultrasound revealed a fetal abnormality in 19 (44.2%) cases, of which 13 (30.2%) had a thickened nuchal translucency. There were an additional four fetuses with second-trimester sonographic abnormalities. Overall, 23 (53.5%) fetuses were found to have a major anomaly diagnosed by ultrasound. The rate of first-trimester sonographic abnormalities varied widely based on category of chromosomal abnormalities with high rates seen with triploidy (87.5%) and autosomal trisomy (80%) and lower rates seen with structurally abnormal chromosomes (33.3%), trisomy mosaicism (27.3%), other forms of mosaicism (11.1%), and deletions or duplications (25.0%), p

An increase in prevalence of gestational diabetes mellitus (GDM) was observed using new diagnostic criteria. We evaluated the prevalence of GDM in a population of pregnant women (109 women with gestational age of 24-28 weeks) and risk factors for GDM, such as maternal obesity and weight gain. The evaluation of each patient included an oral glucose tolerance test (OGTT) using the new diagnostic criteria of the International Association of Diabetes and Pregnancy Study Groups (IADPSG) for GDM, 2D ultrasounds and the registration of risk factors. The prevalence of GDM in the age group ≥30 years was 11.9%, which is comparable to the results of other studies. The relative risk (RR) for GDM was 1.738 (95% CI 0.630-4.795) in women over 30 years and 3.782 (95% CI 1.127-12.686) in women over 35. Weight gain in the group with GDM was significantly higher than in the group that included pregnant women without GDM (p

Objectives: This study aims to establish the normal range of maxillary and mandibular lengths within the Taiwanese population at 11+0 weeks to 13+6 weeks of gestation in normal singleton pregnancy as a reference value for prenatal ultrasonographic examinations. Materials and methods: We examined nuchal translucency in 269 normal singleton pregnancies, with the gestational age ranging from 11 weeks to 13+6 weeks in this study. Fetal biometric measurements, with an emphasis on maxillary and mandibular lengths, were obtained from the patients during consecutive routine prenatal ultrasonographic examinations. Results: Maxillary and mandibular lengths were recorded successfully in 191 patients and 179 patients, respectively. The mean maternal age was 31 years (range 19–45 years), with a corresponding gestational age of 12 + 4 weeks (range, 11+0–13+6 weeks). A first-degree correlation was found to exist between the gestational age and maxillary length (r = 0.596; p

Ultrasound is an integral part of obstetric practice, and assessment of gestational age (GA) is a central element of obstetric ultrasonography. Sonographic estimation of GA is derived from calculations based on fetal measurements. Numerous equations for GA calculation from fetal biometry have been adopted in routine practice. This study reports a new method of estimating GA in the second and third trimester using interischial distance (IID), the distance between the two ischial primary ossification centers, on fetal ultrasound. Four hundred women with uncomplicated normal singleton pregnancies from 16 weeks to term were examined. Standard fetal obstetric ultrasound was done measuring biparietal diameter (BPD) and femur length (FL) for each fetus. The IID, in millimeters, was correlated with the GA in weeks based upon the BPD and FL individually, and the BPD and FL together. Statistical analysis showed strong correlation between the IID and GA calculated from the FL with correlation coefficient (r =0.989, P < 0.001). Strong linear correlation was also found between the IID and GA based upon BPD and BPD+FL. Further statistical analysis using regression equations also showed that the IID was slightly wider in female fetuses, but this difference was not statistically significant. Resulting from this analysis, we have arrived at an easy-to-use equation: GA Weeks = (IID mm + 8) ±1 week. We feel this method can be especially applicable in the developing world, where midwives may not have access to software for fetal biometry in their basic handheld ultrasound machines. Even more sophisticated machines may not come with loaded software for obstetrics analysis. There are several limitations to this study, discussed below. We recommend further studies correlating the IID with other biometric parameters.

Objectives : Hydronephrosis is commonly detected during antenatal scans. There are multiple conflicting prognostic factors in the literature with no clear focus on the postnatal outcome. The aim of the study is to assess the outcome of fetal hydronephrosis, based on antenatal sonography. Materials and Methods : Based on the third trimester fetal ultrasound findings, patients were divided into group I (unilateral hydronephrosis) and group II (bilateral hydronephrosis, ureteric dilatation, bladder thickening, etc). Postnatal evaluation and follow-up was performed by a single physician with uniform protocol. The outcomes, spontaneous resolution vs. surgical intervention, were compared between groups. Among group I, further analysis of outcome was done based on 32-week fetal pelvic antero posterior diameter (APD). Results : Among a total of 116 patients in the study group; group I had 78 patients, 7 (9%) required surgery; group II had 38 patients, 21(55%) required surgery. The difference in outcome between the groups was statistically significant (P = 0.002). Among those with unilateral hydronephrosis, none (0/55) with APD < 15 mm required surgery, while all patients (4/4) with fetal APD> 30 mm required surgery. In those with APD between 15-30 mm, 3/19 required surgery and prolonged follow-up was required to arrive at the decision. The difference in outcome between the subgroups was statistically significant (P < 0.001, Chi-square test). Conclusions : The results of our study show that simple unilateral fetal hydronephrosis runs a benign course. In the presence hydronephrosis larger than 15 mm, bilateral disease, or bladder distension, detailed postnatal evaluation and regular follow-up is warranted to plan a timely intervention. The above data could be used in prenatal counselling of these parents. Further larger studies are warranted to through more evidence.