Search

Accurate estimation of gestational age is an essential component of good obstetric care and informs clinical decision-making throughout pregnancy. As the date of the last menstrual period is often unknown or uncertain, ultrasound measurement of fetal size is currently the best method for estimating gestational age. The calculation assumes an average fetal size at each gestational age. The method is accurate in the first trimester, but less so in the second and third trimesters as growth deviates from the average and variation in fetal size increases. Consequently, fetal ultrasound late in pregnancy has a wide margin of error of at least ±2 weeks’ gestation. Here, we utilise state-of-the-art machine learning methods to estimate gestational age using only image analysis of standard ultrasound planes, without any measurement information. The machine learning model is based on ultrasound images from two independent datasets: one for training and internal validation, and another for external validation. During validation, the model was blinded to the ground truth of gestational age (based on a reliable last menstrual period date and confirmatory first-trimester fetal crown rump length). We show that this approach compensates for increases in size variation and is even accurate in cases of intrauterine growth restriction. Our best machine-learning based model estimates gestational age with a mean absolute error of 3.0 (95% CI, 2.9–3.2) and 4.3 (95% CI, 4.1–4.5) days in the second and third trimesters, respectively, which outperforms current ultrasound-based clinical biometry at these gestational ages. Our method for dating the pregnancy in the second and third trimesters is, therefore, more accurate than published methods.

Background: Approximately 3 to 4 billion people worldwide are exposed to household air pollution, which has been associated with increased blood pressure (BP) in pregnant women in some studies. Methods: We recruited 3195 pregnant women in Guatemala, India, Peru, and Rwanda and randomly assigned them to intervention or control groups. The intervention group received a gas stove and fuel during pregnancy, while the controls continued cooking with solid fuels. We measured BP and personal exposure to PM 2.5 , black carbon and carbon monoxide 3× during gestation. We conducted an intention-to-treat and exposure-response analysis to determine if household air pollution exposure was associated with increased gestational BP. Results: Median 24-hour PM 2.5 dropped from 84 to 24 μg/m 3 after the intervention; black carbon and carbon monoxide decreased similarly. Intention-to-treat analyses showed an increase in systolic BP and diastolic BP in both arms during gestation, as expected, but the increase was greater in intervention group for both systolic BP (0.69 mm Hg [0.03–1.35]; P =0.04) and diastolic BP (0.62 mm Hg [0.05–1.19]; P =0.03). The exposure-response analyses suggested that higher exposures to household air pollution were associated with moderately higher systolic BP and diastolic BP; however, none of these associations reached conventional statistical significance. Conclusions: In intention-to-treat, we found higher gestational BP in the intervention group compared with controls, contrary to expected. In exposure-response analyses, we found a slight increase in BP with higher exposure, but it was not statistically significant. Overall, an intervention with gas stoves did not markedly affect gestational BP.

Self-supervised contrastive representation learning offers the advantage of learning meaningful visual representations from unlabeled medical datasets for transfer learning. However, applying current contrastive learning approaches to medical data without considering its domain-specific anatomical characteristics may lead to visual representations that are inconsistent in appearance and semantics. In this paper, we propose to improve visual representations of medical images via anatomy-aware contrastive learning (AWCL), which incorporates anatomy information to augment the positive/negative pair sampling in a contrastive learning manner. The proposed approach is demonstrated for automated fetal ultrasound imaging tasks, enabling the positive pairs from the same or different ultrasound scans that are anatomically similar to be pulled together and thus improving the representation learning. We empirically investigate the effect of inclusion of anatomy information with coarse- and fine-grained granularity, for contrastive learning and find that learning with fine-grained anatomy information which preserves intra-class difference is more effective than its counterpart. We also analyze the impact of anatomy ratio on our AWCL framework and find that using more distinct but anatomically similar samples to compose positive pairs results in better quality representations. Experiments on a large-scale fetal ultrasound dataset demonstrate that our approach is effective for learning representations that transfer well to three clinical downstream tasks, and achieves superior performance compared to ImageNet supervised and the current state-of-the-art contrastive learning methods. In particular, AWCL outperforms ImageNet supervised method by 13.8% and state-of-the-art contrastive-based method by 7.1% on a cross-domain segmentation task.

SlowflowHD is a new ultrasound Doppler imaging technology that allows visualization of flow within small blood vessels. In this mode, a proprietary algorithm differentiates between low-speed flow and signals attributed to tissue motion so that microvessel vasculature can be examined. Our objectives were to describe the low-velocity Doppler mode principles, to assess the bone thermal index (TIb) safety parameter in obstetric ultrasound scans and to evaluate adherence to professional guidelines. To achieve the latter goals, we retrospectively reviewed prospectively collected ultrasound images and video clips from pregnancy ultrasound scans at >10 wk of gestation over 4 mo. We used a custom-built optical character recognition-based software to automatically identify all images and video clips using this technology and extract the TIb. Overall, a total of 185 ultrasound scans performed by three fetal medicine physicians were included, of which 60, 54 and 71 scans were first-, second- and third-trimester scans, respectively. The mean (highest recorded) TIb values were 0.32 (0.70), 0.23 (0.70) and 0.32 (0.60) in the first, second, and third trimesters, respectively. Thermal index values were within recommended values set by the World Federation for Ultrasound in Medicine and Biology American Institute of Ultrasound in Medicine and British Medical Ultrasound Society in all scans.

Ultrasound-based assistive tools are aimed at reducing the high skill needed to interpret a scan by providing automatic image guidance. This may encourage uptake of ultrasound (US) clinical assessments in rural settings in low- and middle-income countries (LMICs), where well-trained sonographers can be scarce. This paper describes a new method that automatically generates an assistive video overlay to provide image guidance to a user to assess placenta location. The user captures US video by following a sweep protocol that scans a U-shape on the lower maternal abdomen. The sweep trajectory is simple and easy to learn. We initially explore a 2-D embedding of placenta shapes, mapping manually segmented placentas in US video frames to a 2-D space. We map 2013 frames from 11 videos. This provides insight into the spectrum of placenta shapes that appear when using the sweep protocol. We propose classification of the placenta shapes from three observed clusters: complex, tip and rectangular. We use this insight to design an effective automatic segmentation algorithm, combining a U-Net with a CRF-RNN module to enhance segmentation performance with respect to placenta shape. The U-Net + CRF-RNN algorithm automatically segments the placenta and maternal bladder. We assess segmentation performance using both area and shape metrics. We report results comparable to the state-of-the-art for automatic placenta segmentation on the Dice metric, achieving 0.83 ± 0.15 evaluated on 2127 frames from 10 videos. We also qualitatively evaluate 78,308 frames from 135 videos, assessing if the anatomical outline is correctly segmented. We found that addition of the CRF-RNN improves over a baseline U-Net when faced with a complex placenta shape, which we observe in our 2-D embedding, up to 14% with respect to the percentage shape error. From the segmentations, an assistive video overlay is automatically constructed that (i) highlights the placenta and bladder, (ii) determines the lower placenta edge and highlights this location as a point and (iii) labels a 2-cm clearance on the lower placenta edge. The 2-cm clearance is chosen to satisfy current clinical guidelines. We propose to assess the placenta location by comparing the 2-cm region and the bottom of the bladder, which represents a coarse localization of the cervix. Anatomically, the bladder must sit above the cervix region. We present proof-of-concept results for the video overlay.

Purpose For highly operator-dependent ultrasound scanning, skill assessment approaches evaluate operator competence given available data, such as acquired images and tracked probe movement. Operator skill level can be quantified by the completeness, speed, and precision of performing a clinical task, such as biometry. Such clinical tasks are increasingly becoming assisted or even replaced by automated machine learning models. In addition to measurement, operators need to be competent at the upstream task of acquiring images of sufficient quality. To provide computer assistance for this task requires a new definition of skill. Methods This paper focuses on the task of selecting ultrasound frames for biometry, for which operator skill is assessed by quantifying how well the tasks are performed with neural network-based frame classifiers. We first develop a frame classification model for each biometry task, using a novel label-efficient training strategy. Once these task models are trained, we propose a second task model-specific network to predict two skill assessment scores, based on the probability of identifying positive frames and accuracy of model classification. Results We present comprehensive results to demonstrate the efficacy of both the frame-classification and skill-assessment networks, using clinically acquired data from two biometry tasks for a total of 139 subjects, and compare the proposed skill assessment with metrics of operator experience. Conclusion Task model-specific skill assessment is feasible and can be predicted by the proposed neural networks, which provide objective assessment that is a stronger indicator of task model performance, compared to existing skill assessment methods.

Objective This study evaluates whether clinical phenotypes of small for gestational (SGA) fetuses can be identified and used for adverse perinatal outcome risk stratification to facilitate decision-making. Methods This multicentre observational cohort study was conducted in two tertiary care university hospitals. It included 17,631 consecutive singleton pregnancies, among which 1274 (7.2%) were defined as SGA at birth according to INTERGROWTH-21st standards. The main outcome was the development of clinical clusters of SGA phenotypes. Results Nine SGA clinical phenotypes were identified using a predefined conceptual framework. Every delivery and perinatal outcome analysed showed statistically significant differences between phenotypes. The total SGA cohort had a 3 times increased risk of perinatal mortality than non-SGA fetuses (1.4% vs 0.4%; pConclusions We identified nine SGA clinical phenotypes associated with different patterns of risk for adverse perinatal outcomes. Our results suggest that adding clinical characteristics to ultrasound results would improve risk stratification and decision-making for SGA fetuses. Future clinical trials on the control of fetuses with SGA should take into account, in addition to Doppler and estimated fetal weight, this clinical information.

In this work, we present a novel gaze-assisted natural language processing (NLP)-based video captioning model to describe routine second-trimester fetal ultrasound scan videos in a vocabulary of spoken sonography. The primary novelty of our multi-modal approach is that the learned video captioning model is built using a combination of ultrasound video, tracked gaze and textual transcriptions from speech recordings. The textual captions that describe the spatio-temporal scan video content are learnt from sonographer speech recordings. The generation of captions is assisted by sonographer gaze-tracking information reflecting their visual attention while performing live-imaging and interpreting a frozen image. To evaluate the effect of adding, or withholding, different forms of gaze on the video model, we compare spatio-temporal deep networks trained using three multi-modal configurations, namely: (1) a gaze-less neural network with only text and video as input, (2) a neural network additionally using real sonographer gaze in the form of attention maps, and (3) a neural network using automatically-predicted gaze in the form of saliency maps instead. We assess algorithm performance through established general text-based metrics (BLEU, ROUGE-L, F1 score), a domain-specific metric (ARS), and metrics that consider the richness and efficiency of the generated captions with respect to the scan video. Results show that the proposed gaze-assisted models can generate richer and more diverse captions for clinical fetal ultrasound scan videos than those without gaze at the expense of the perceived sentence structure. The results also show that the generated captions are similar to sonographer speech in terms of discussing the visual content and the scanning actions performed.

Self-knowledge distillation (SKD) is a recent and promising machine learning approach where a shallow student network is trained to distill its own knowledge. By contrast, in traditional knowledge distillation a student model distills its knowledge from a large teacher network model, which involves vast computational complexity and a large storage size. Consequently, SKD is a useful approach to model medical imaging problems with scarce data. We propose an original SKD framework to predict where a sonographer should look next using a multi-modal ultrasound and gaze dataset. We design a novel Wide Feature Distillation module, which is applied to intermediate feature maps in the form of transformations. The module applies a more refined feature map filtering which is important when predicting gaze for the fetal anatomy variable in size. Our architecture design includes ReSL loss that enables a student network to learn useful information whilst discarding the rest. The proposed network is validated on a large multi-modal ultrasound dataset, which is acquired during routine first trimester fetal ultrasound scanning. Experimental results show the novel SKD approach outperforms alternative state-of-the-art architectures on all saliency metrics.

We present a method for skill characterisation of sonographer gaze patterns while performing routine second trimester fetal anatomy ultrasound scans. The position and scale of fetal anatomical planes during each scan differ because of fetal position, movements and sonographer skill. A standardised reference is required to compare recorded eye-tracking data for skill characterisation. We propose using an affine transformer network to localise the anatomy circumference in video frames, for normalisation of eye-tracking data. We use an event-based data visualisation, time curves, to characterise sonographer scanning patterns. We chose brain and heart anatomical planes because they vary in levels of gaze complexity. Our results show that when sonographers search for the same anatomical plane, even though the landmarks visited are similar, their time curves display different visual patterns. Brain planes also, on average, have more events or landmarks occurring than the heart, which highlights anatomy-specific differences in searching approaches.

BackgroundIn 2021, we showed an increased risk associated with COVID-19 in pregnancy. Since then, the SARS-CoV-2 virus has undergone genetic mutations. We aimed to examine the effects on maternal and perinatal outcomes of COVID-19 during pregnancy, and evaluate vaccine effectiveness, when omicron (B.1.1.529) was the variant of concern.MethodsINTERCOVID-2022 is a large, prospective, observational study, involving 41 hospitals across 18 countries. Each woman with real-time PCR or rapid test, laboratory-confirmed COVID-19 in pregnancy was compared with two unmatched women without a COVID-19 diagnosis who were recruited concomitantly and consecutively in pregnancy or at delivery. Mother and neonate dyads were followed until hospital discharge. Primary outcomes were maternal morbidity and mortality index (MMMI), severe neonatal morbidity index (SNMI), and severe perinatal morbidity and mortality index (SPMMI). Vaccine effectiveness was estimated, adjusted by maternal risk profile.FindingsWe enrolled 4618 pregnant women from Nov 27, 2021 (the day after WHO declared omicron a variant of concern), to June 30, 2022: 1545 (33%) women had a COVID-19 diagnosis (median gestation 36·7 weeks [IQR 29·0-38·9]) and 3073 (67%) women, with similar demographic characteristics, did not have a COVID-19 diagnosis. Overall, women with a diagnosis had an increased risk for MMMI (relative risk [RR] 1·16 [95% CI 1·03-1·31]) and SPMMI (RR 1·21 [95% CI 1·00-1·46]). Women with a diagnosis, compared with those without a diagnosis, also had increased risks of SNMI (RR 1·23 [95% CI 0·88-1·71]), although the lower bounds of the 95% CI crossed unity. Unvaccinated women with a COVID-19 diagnosis had a greater risk of MMMI (RR 1·36 [95% CI 1·12-1·65]). Severe COVID-19 symptoms in the total sample increased the risk of severe maternal complications (RR 2·51 [95% CI 1·84-3·43]), perinatal complications (RR 1·84 [95% CI 1·02-3·34]), and referral, intensive care unit (ICU) admission, or death (RR 11·83 [95% CI 6·67-20·97]). Severe COVID-19 symptoms in unvaccinated women increased the risk of MMMI (RR 2·88 [95% CI 2·02-4·12]) and referral, ICU admission, or death (RR 20·82 [95% CI 10·44-41·54]). 2886 (63%) of 4618 total participants had at least a single dose of any vaccine, and 2476 (54%) of 4618 had either complete or booster doses. Vaccine effectiveness (all vaccines combined) for severe complications of COVID-19 for all women with a complete regimen was 48% (95% CI 22-65) and 76% (47-89) after a booster dose. For women with a COVID-19 diagnosis, vaccine effectiveness of all vaccines combined for women with a complete regimen was 74% (95% CI 48-87) and 91% (65-98) after a booster dose.InterpretationCOVID-19 in pregnancy, during the first 6 months of omicron as the variant of concern, was associated with increased risk of severe maternal morbidity and mortality, especially among symptomatic and unvaccinated women. Women with complete or boosted vaccine doses had reduced risk for severe symptoms, complications, and death. Vaccination coverage among pregnant women remains a priority.FundingNone.

Cooking and heating using solid fuels can result in dangerous levels of exposure to household air pollution (HAP). HAPIN is an ongoing randomized controlled trial assessing the impact of a liquified petroleum gas stove and fuel intervention on HAP exposure and health in Guatemala, India, Peru, and Rwanda among households that rely primarily on solid cooking fuels. Given the potential impacts of HAP exposure on cardiovascular outcomes during pregnancy, we seek to characterize the relationship between personal exposures to HAP and blood pressure among pregnant women at baseline (prior to intervention) in the study. We assessed associations between PM (2.5) (particulate matter with an aerodynamic diameter ≤2.5 μm), BC (black carbon), and CO (carbon monoxide) exposures and blood pressure at baseline, prior to intervention, among 3195 pregnant women between 9 and 19 weeks of gestation. We measured 24-hour personal exposure to PM (2.5) /BC/CO and gestational blood pressure. Multivariable linear regression models were used to evaluate associations between personal exposures to three air pollutants and blood pressure parameters. Trial-wide, we found moderate increases in systolic blood pressure (SBP) and decreases in diastolic blood pressure (DBP) as exposure to PM (2.5) , BC, and CO increased. None of these associations, however, were significant at the 0.05 level. HAP exposure and blood pressure associations were inconsistent in direction and magnitude within each country. We observed effect modification by body mass index (BMI) in India and Peru. Compared to women with normal weights, obese women in India and Peru (but not in Rwanda or Guatemala) had higher SBP per unit increase in log transformed PM (2.5) and BC exposures. We did not find a cross-sectional association between HAP exposure and blood pressure in pregnant women; however, HAP may be associated with higher blood pressure in pregnant women who are obese, but this increase was not consistent across settings.

Pregnancy outcomes; Vaccine effectiveness; Omicron Resultados del embarazo; Efectividad de la vacuna; Omicron Resultats de l'embaràs; Eficàcia de la vacuna; Omicron Background In 2021, we showed an increased risk associated with COVID-19 in pregnancy. Since then, the SARS-CoV-2 virus has undergone genetic mutations. We aimed to examine the effects on maternal and perinatal outcomes of COVID-19 during pregnancy, and evaluate vaccine effectiveness, when omicron (B.1.1.529) was the variant of concern. Methods INTERCOVID-2022 is a large, prospective, observational study, involving 41 hospitals across 18 countries. Each woman with real-time PCR or rapid test, laboratory-confirmed COVID-19 in pregnancy was compared with two unmatched women without a COVID-19 diagnosis who were recruited concomitantly and consecutively in pregnancy or at delivery. Mother and neonate dyads were followed until hospital discharge. Primary outcomes were maternal morbidity and mortality index (MMMI), severe neonatal morbidity index (SNMI), and severe perinatal morbidity and mortality index (SPMMI). Vaccine effectiveness was estimated, adjusted by maternal risk profile. Findings We enrolled 4618 pregnant women from Nov 27, 2021 (the day after WHO declared omicron a variant of concern), to June 30, 2022: 1545 (33%) women had a COVID-19 diagnosis (median gestation 36·7 weeks [IQR 29·0–38·9]) and 3073 (67%) women, with similar demographic characteristics, did not have a COVID-19 diagnosis. Overall, women with a diagnosis had an increased risk for MMMI (relative risk [RR] 1·16 [95% CI 1·03–1·31]) and SPMMI (RR 1·21 [95% CI 1·00–1·46]). Women with a diagnosis, compared with those without a diagnosis, also had increased risks of SNMI (RR 1·23 [95% CI 0·88–1·71]), although the lower bounds of the 95% CI crossed unity. Unvaccinated women with a COVID-19 diagnosis had a greater risk of MMMI (RR 1·36 [95% CI 1·12–1·65]). Severe COVID-19 symptoms in the total sample increased the risk of severe maternal complications (RR 2·51 [95% CI 1·84–3·43]), perinatal complications (RR 1·84 [95% CI 1·02–3·34]), and referral, intensive care unit (ICU) admission, or death (RR 11·83 [95% CI 6·67–20·97]). Severe COVID-19 symptoms in unvaccinated women increased the risk of MMMI (RR 2·88 [95% CI 2·02–4·12]) and referral, ICU admission, or death (RR 20·82 [95% CI 10·44–41·54]). 2886 (63%) of 4618 total participants had at least a single dose of any vaccine, and 2476 (54%) of 4618 had either complete or booster doses. Vaccine effectiveness (all vaccines combined) for severe complications of COVID-19 for all women with a complete regimen was 48% (95% CI 22–65) and 76% (47–89) after a booster dose. For women with a COVID-19 diagnosis, vaccine effectiveness of all vaccines combined for women with a complete regimen was 74% (95% CI 48–87) and 91% (65–98) after a booster dose. Interpretation COVID-19 in pregnancy, during the first 6 months of omicron as the variant of concern, was associated with increased risk of severe maternal morbidity and mortality, especially among symptomatic and unvaccinated women. Women with complete or boosted vaccine doses had reduced risk for severe symptoms, complications, and death. Vaccination coverage among pregnant women remains a priority.

Household air pollution from solid cooking fuel use during gestation has been associated with adverse pregnancy and birth outcomes. The Household Air Pollution Intervention Network (HAPIN) trial was a randomized controlled trial of free liquefied petroleum gas (LPG) stoves and fuel in Guatemala, Peru, India, and Rwanda. A primary outcome of the main trial was to report the effects of the intervention on infant birth weight. Here we evaluate the effects of a LPG stove and fuel intervention during pregnancy on spontaneous abortion, postpartum hemorrhage, hypertensive disorders of pregnancy, and maternal mortality compared to women who continued to use solid cooking fuels. Pregnant women (18-34years of age; gestation confirmed by ultrasound at 9-19weeks) were randomly assigned to an intervention (n=1593) or control (n=1607) arm. Intention-to-treat analyses compared outcomes between the two arms using log-binomial models. Among the 3195 pregnant women in the study, there were 10 spontaneous abortions (7 intervention, 3 control), 93 hypertensive disorders of pregnancy (47 intervention, 46 control), 11 post postpartum hemorrhage (5 intervention, 6 control) and 4 maternal deaths (3 intervention, 1 control). Compared to the control arm, the relative risk of spontaneous abortion among women randomized to the intervention was 2.32 (95% confidence interval (CI): 0.60, 8.96), hypertensive disorders of pregnancy 1.02 (95% CI: 0.68, 1.52), postpartum hemorrhage 0.83 (95% CI: 0.25, 2.71) and 2.98 (95% CI: 0.31, 28.66) for maternal mortality. In this study, we found that adverse maternal outcomes did not differ based on randomized stove type across four country research sites.

Objective: We aimed to determine the prevalence of abnormal umbilical artery (UA), uterine artery (UtA), middle cerebral artery (MCA) and cerebroplacental ratio (CPR) Doppler, and their relationship with adverse perinatal outcomes in women undergoing routine antenatal care in the third trimester. Design: Prospective cohort. Setting: Kagadi Hospital, Uganda. Population: Non-anomalous singleton pregnancies. Methods: Women underwent an early dating ultrasound and a third-trimester Doppler scan between 32 and 40 weeks of gestation, from 2018 to 2020. We handled missing data using multiple imputation and analysed the data using descriptive methods and a binary logistic regression model. Main outcome measures: Composite adverse perinatal outcome (CAPO), perinatal death and stillbirth. Results: We included 995 women. The mean gestational age at Doppler scan was 36.9 weeks (SD 1.02 weeks) and 88.9% of the women gave birth in a health facility. About 4.4% and 5.6% of the UA pulsatility index (PI) and UtA PI were above the 95th percentile, whereas 16.4% and 10.4% of the MCA PI and CPR were below the fifth percentile, respectively. Low CPR was strongly associated with stillbirth (OR 4.82, 95% CI 1.09–21.30). CPR and MCA PI below the fifth percentile were independently associated with CAPO; the association with MCA PI was stronger in small-for-gestational-age neonates (OR 3.75, 95% CI 1.18–11.88). Conclusion: In late gestation, abnormal UA PI was rare. Fetuses with cerebral blood flow redistribution were at increased risk of stillbirth and perinatal complications. Further studies examining the predictive accuracy and effectiveness of antenatal Doppler ultrasound screening in reducing the risk of perinatal deaths in low- and middle-income countries are warranted. Tweetable abstract: Blood flow redistribution to the fetal brain is strongly associated with stillbirths in low-resource settings.

Abstract Background Early onset fetal growth restriction secondary to placental insufficiency can lead to severe maternal and neonatal morbidity and mortality. Pre-clinical studies and a few small randomised clinical trials have suggested that phosphodiesterase type 5 (PDE-5) inhibitors may have protective effects against placental insufficiency in this context; however, robust evidence is lacking. The STRIDER Consortium conducted four randomised trials to investigate the use of a PDE-5 inhibitor, sildenafil, for the treatment of early onset fetal growth restriction. We present a protocol for the pre-planned systematic review with individual participant data meta-analysis, aggregate meta-analysis, and trial sequential analysis of these and other eligible trials. The main objective of this study will be to evaluate the effects of PDE-5 inhibitors on neonatal morbidity compared with placebo or no intervention among pregnancies with fetal growth restriction. Methods We will search the following electronic databases with no language or date restrictions: OVID MEDLINE, OVID EMBASE, the Cochrane Controlled Register of Trials (CENTRAL), and the clinical trial registers Clinicaltrials.gov and World Health Organisation International Clinical Trials Registry Platform (ICTRP). We will identify randomised trials of PDE-5 inhibitors in singleton pregnancies with growth restriction. Two reviewers will independently screen all citations, full-text articles, and abstract data. Our primary outcome will be infant survival without evidence of serious adverse neonatal outcome. Secondary outcomes will include gestational age at birth and birth weight z-scores. We will assess bias using the Cochrane Risk of Bias 2 tool. We will conduct aggregate meta-analysis using fixed and random effects models, Trial Sequential Analysis, and individual participant data meta-analysis using one- and two-stage approaches. The certainty of evidence will be assessed with GRADE. Discussion This pre-defined protocol will minimise bias during analysis and interpretation of results, toward the goal of providing robust evidence regarding the use of PDE-5 inhibitors for the treatment of early onset fetal growth restriction. Systematic review registration PROSPERO (CRD42017069688).

RATIONALE: Pneumonia is the leading cause of death in children worldwide. Identifying and appropriately managing severe pneumonia in a timely manner improves outcomes. Little is known about the readiness of healthcare facilities to manage severe pediatric pneumonia in low-resource settings. OBJECTIVES: As part of the Household Air Pollution Intervention Network (HAPIN) trial, we sought to identify healthcare facilities that were adequately resourced to manage severe pediatric pneumonia in Jalapa, Guatemala (J-GUA); Puno, Peru (P-PER); Kayonza, Rwanda (K-RWA); and Tamil Nadu, India (T-IND). We conducted a facility-based survey of available infrastructure, staff, equipment, and medical consumables. Facilities were georeferenced and a road network analysis was performed. MEASUREMENTS AND MAIN RESULTS: Of the 350 healthcare facilities surveyed, 13% had adequate resources to manage severe pneumonia, 37% had pulse oximeters, and 44% had supplemental oxygen. Mean (±SD) travel time to an adequately-resourced facility was 41±19 minutes in J-GUA, 99±64 minutes in P-PER, 40±19 minutes in K-RWA, and 31±19 minutes in T-IND. Expanding pulse oximetry coverage to all facilities reduced travel time by 44% in J-GUA, 29% in P-PER, 29% in K-RWA, and 11% in T-IND (all p

Background Observational studies relating maternal 25-hydroxyvitamin D status to timing and mode of delivery have reported inconsistent results. We assessed the effect of antenatal cholecalciferol supplementation on the incidence of preterm birth, delivery mode and post-partum haemorrhage (PPH). Methods MAVIDOS was a randomized, double-blind, placebo-controlled trial of 1000 IU/day cholecalciferol from 14 weeks’ gestation until delivery. Gestational age, mode of delivery [categorized as spontaneous vaginal delivery (SVD), instrumental (including forceps and vacuum extraction) or Caesarean section] and PPH (>500 ml estimated blood loss) were determined from medical records. Results A total of 965 women participated in the study until delivery. Gestation at birth and incidence of preterm birth (cholecalciferol 5.7%, placebo 4.5%, P = 0.43) were similar between the two treatment groups. SVD (versus instrumental or Caesarean delivery) was more likely in women randomized to cholecalciferol [Relative Risk (RR) 1.13, 95% confidence interval (CI) 1.02,1.25] due to lower instrumental (RR 0.68, 95%CI 0.51,0.91) but similar risk of Caesarean delivery (RR 0.94, 95%CI 0.74,1.19). PPH was less common in women randomized to cholecalciferol [32.1% compared with placebo (38.1%, P = 0.054) overall], but similar when stratified by delivery mode. Conclusions Antenatal cholecalciferol supplementation did not alter timing of birth or prevalence of preterm birth but demonstrated a possible effect on the likelihood of SVD.

BACKGROUND: Exposure during pregnancy to household air pollution caused by the burning of solid biomass fuel is associated with adverse health outcomes, including low birth weight. Whether the replacement of a biomass cookstove with a liquefied petroleum gas (LPG) cookstove would result in an increase in birth weight is unclear. METHODS: We performed a randomized, controlled trial involving pregnant women (18 to

Objective Stillbirth is a potentially preventable complication of pregnancy. Identifying women at high risk of stillbirth can guide decisions on the need for closer surveillance and timing of delivery in order to prevent fetal death. Prognostic models have been developed to predict the risk of stillbirth, but none has yet been validated externally. In this study, we externally validated published prediction models for stillbirth using individual participant data (IPD) meta-analysis to assess their predictive performance. Methods MEDLINE, EMBASE, DH-DATA and AMED databases were searched from inception to December 2020 to identify studies reporting stillbirth prediction models. Studies that developed or updated prediction models for stillbirth for use at any time during pregnancy were included. IPD from cohorts within the International Prediction of Pregnancy Complications (IPPIC) Network were used to validate externally the identified prediction models whose individual variables were available in the IPD. The risk of bias of the models and cohorts was assessed using the Prediction study Risk Of Bias ASsessment Tool (PROBAST). The discriminative performance of the models was evaluated using the C-statistic, and calibration was assessed using calibration plots, calibration slope and calibration-in-the-large. Performance measures were estimated separately in each cohort, as well as summarized across cohorts using random-effects meta-analysis. Clinical utility was assessed using net benefit. Results Seventeen studies reporting the development of 40 prognostic models for stillbirth were identified. None of the models had been previously validated externally, and the full model equation was reported for only one-fifth (20%, 8/40) of the models. External validation was possible for three of these models, using IPD from 19 cohorts (491 201 pregnant women) within the IPPIC Network database. Based on evaluation of the model development studies, all three models had an overall high risk of bias, according to PROBAST. In the IPD meta-analysis, the models had summary C-statistics ranging from 0.53 to 0.65 and summary calibration slopes ranging from 0.40 to 0.88, with risk predictions that were generally too extreme compared with the observed risks. The models had little to no clinical utility, as assessed by net benefit. However, there remained uncertainty in the performance of some models due to small available sample sizes. Conclusions The three validated stillbirth prediction models showed generally poor and uncertain predictive performance in new data, with limited evidence to support their clinical application. The findings suggest methodological shortcomings in their development, including overfitting. Further research is needed to further validate these and other models, identify stronger prognostic factors and develop more robust prediction models. (c) 2021 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

IntroductionFollowing the detection of fetal growth restriction, there is no consensus about the criteria that should trigger delivery in the late preterm period. The consequences of inappropriate early or late delivery are potentially important yet practice varies widely around the world, with abnormal findings from fetal heart rate monitoring invariably leading to delivery. Indices derived from fetal cerebral Doppler examination may guide such decisions although there are few studies in this area. We propose a randomised, controlled trial to establish the optimum method of timing delivery between 32 weeks and 36 weeks 6 days of gestation. We hypothesise that delivery on evidence of cerebral blood flow redistribution reduces a composite of perinatal poor outcome, death and short-term hypoxia-related morbidity, with no worsening of neurodevelopmental outcome at 2 years.Methods and analysisWomen with non-anomalous singleton pregnancies 32+0 to 36+6 weeks of gestation in whom the estimated fetal weight or abdominal circumference is Ethics and disseminationThe Study Coordination Centre has obtained approval from London-Riverside Research Ethics Committee (REC) and Health Regulatory Authority (HRA). Publication will be in line with NIHR Open Access policy.Trial registration numberMain sponsor: Imperial College London, Reference: 19QC5491. Funders: NIHR HTA, Reference: 127 976. Study coordination centre: Imperial College Healthcare NHS Trust, Du Cane Road, London, W12 0HS with Centre for Trials Research, College of Biomedical & Life Sciences, Cardiff University. IRAS Project ID: 266 400. REC reference: 20/LO/0031. ISRCTN registry: 76 016 200.

OBJECTIVE To compare the screening performance of serum pregnancy-associated plasma protein-A (PAPP-A) vs placental growth factor (PlGF) in routine first-trimester combined screening for pre-eclampsia (PE), small-for-gestational age (SGA) at birth and trisomy 21. METHODS This was a retrospective study nested in pregnancy cohorts undergoing first-trimester combined screening for PE and trisomy 21 using The Fetal Medicine Foundation (FMF) algorithm based on maternal characteristics, nuchal translucency thickness, PAPP-A, free beta-human chorionic gonadotropin, blood pressure and uterine artery Doppler. Women at high risk for preterm PE (≥ 1 in 50) received 150 mg of aspirin per day, underwent serial fetal growth scans at 28 and 36 weeks and were offered elective birth from 40 weeks of gestation. PlGF was quantified retrospectively from stored surplus first-trimester serum samples. The performance of combined first-trimester screening for PE and SGA using maternal history, blood pressure, uterine artery pulsatility index and either PAPP-A or PlGF was calculated. Similarly, the performance of combined first-trimester screening for trisomy 21 was calculated using either PAPP-A or PlGF in addition to maternal age, nuchal translucency thickness and free beta-human chorionic gonadotropin. RESULTS Maternal serum PAPP-A was assayed in 1094 women, including 82 with PE, 111 with SGA (birth weight

BACKGROUND: The World Health Organization recommends a package of pregnancy care that includes obstetric ultrasound scans. There are significant barriers to universal access to antenatal ultrasound, particularly because of the cost and need for maintenance of ultrasound equipment and a lack of trained personnel. As low-cost, handheld ultrasound devices have become widely available, the current roadblock is the global shortage of health care providers trained in obstetric scanning. OBJECTIVE: The aim of this study is to improve pregnancy and risk assessment for women in underserved regions. Therefore, we are undertaking the Computer-Assisted Low-Cost Point-of-Care UltraSound (CALOPUS) project, bringing together experts in machine learning and clinical obstetric ultrasound. METHODS: In this prospective study conducted in two clinical centers (United Kingdom and India), participating pregnant women were scanned and full-length ultrasounds were performed. Each woman underwent 2 consecutive ultrasound scans. The first was a series of simple, standardized ultrasound sweeps (the CALOPUS protocol), immediately followed by a routine, full clinical ultrasound examination that served as the comparator. We describe the development of a simple-to-use clinical protocol designed for nonexpert users to assess fetal viability, detect the presence of multiple pregnancies, evaluate placental location, assess amniotic fluid volume, determine fetal presentation, and perform basic fetal biometry. The CALOPUS protocol was designed using the smallest number of steps to minimize redundant information, while maximizing diagnostic information. Here, we describe how ultrasound videos and annotations are captured for machine learning. RESULTS: Over 5571 scans have been acquired, from which 1,541,751 label annotations have been performed. An adapted protocol, including a low pelvic brim sweep and a well-filled maternal bladder, improved visualization of the cervix from 28% to 91% and classification of placental location from 82% to 94%. Excellent levels of intra- and interannotator agreement are achievable following training and standardization. CONCLUSIONS: The CALOPUS study is a unique study that uses obstetric ultrasound videos and annotations from pregnancies dated from 11 weeks and followed up until birth using novel ultrasound and annotation protocols. The data from this study are being used to develop and test several different machine learning algorithms to address key clinical diagnostic questions pertaining to obstetric risk management. We also highlight some of the challenges and potential solutions to interdisciplinary multinational imaging collaboration. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR1-10.2196/37374.

Funder: NIHR Oxford Biomedical Research Centre, University of Oxford, Funder: NIHR Southampton Biomedical Research Centre, University Hospital Southampton NHS Foundation Trust and University of Southampton, Funder: Royal Osteoporosis Society (UK); Id: http://dx.doi.org/10.13039/100007472, Funder: Bupa Foundation; Id: http://dx.doi.org/10.13039/501100000355, In the Maternal Vitamin D Osteoporosis Study (MAVIDOS) randomized trial, vitamin D supplementation in pregnancy did not lead to greater neonatal bone mass across the trial as a whole, but, in a prespecified secondary analysis by season of birth, led to greater neonatal bone mass among winter-born babies. Demonstrating persistence of this effect into childhood would increase confidence in a long-term benefit of this intervention. We investigated whether antenatal vitamin D supplementation increases offspring bone mineralization in early childhood in a prespecified, single-center follow-up of a double-blinded, multicenter, randomized controlled clinical trial based in the UK (MAVIDOS). A total of 1123 women in early pregnancy with a baseline 25-hydroxyvitamin D level 25-100 nmol/L from three research centers (2008-2014) were randomized to 1000 IU/d cholecalciferol or matched placebo from 14 weeks of gestation to delivery. Offspring born at the Southampton, UK research center were assessed at age 4 years (2013-2018). Anthropometry and dual-energy X-ray absorptiometry (DXA) were performed (yielding whole body less head [WBLH] bone mineral content [BMC], areal bone mineral density [aBMD], bone area [BA], and body composition). Of 723 children, 564 (78.0%) children attended the 4-year visit, 452 of whom had a useable DXA. Maternal vitamin D supplementation led to greater WBLH aBMD in the children compared with placebo (mean [95% confidence interval {CI}]: supplemented group: 0.477 (95% CI, 0.472-0.481) g/cm2; placebo group: 0.470 (95% CI, 0.466-0.475) g/cm2, p = 0.048). Associations were consistent for BMC and lean mass, and in age- and sex-adjusted models. Effects were observed across the whole cohort irrespective of season of birth. Maternal-child interactions were observed, with a greater effect size among children with low milk intake and low levels of physical activity. Child weight, height, and body mass index (BMI) were similar by maternal randomization group. These findings suggest a sustained beneficial effect of maternal vitamin D supplementation in pregnancy on offspring aBMD at age 4 years, but will require replication in other trials. © 2022 The Authors. JBMR Plus published by Wiley Periodicals LLC on behalf of American Society for Bone and Mineral Research.

Deep networks have been shown to achieve impressive accuracy for some medical image analysis tasks where large datasets and annotations are available. However, tasks involving learning over new sets of classes arriving over extended time is a different and difficult challenge due to the tendency of reduction in performance over old classes while adapting to new ones. Controlling such a 'forgetting' is vital for deployed algorithms to evolve with new arrivals of data incrementally. Usually, incremental learning approaches rely on expert knowledge in the form of manual annotations or active feedback. In this paper, we explore the role that other forms of expert knowledge might play in making deep networks in medical image analysis immune to forgetting over extended time. We introduce a novel framework for mitigation of this forgetting effect in deep networks considering the case of combining ultrasound video with point-of-gaze tracked for expert sonographers during model training. This is used along with a novel weighted distillation strategy to reduce the propagation of effects due to class imbalance.

Despite decades of obstetric scanning, the field of sonographer workflow remains largely unexplored. In the second trimester, sonographers use scan guidelines to guide their acquisition of standard planes and structures; however, the scan-acquisition order is not prescribed. Using deep-learning-based video analysis, the aim of this study was to develop a deeper understanding of the clinical workflow undertaken by sonographers during second-trimester anomaly scans.We collected prospectively full-length video recordings of routine second-trimester anomaly scans. Important scan events in the videos were identified by detecting automatically image freeze and image/clip save. The video immediately preceding and following the important event was extracted and labeled as one of 11 commonly acquired anatomical structures. We developed and used a purposely trained and tested deep-learning annotation model to label automatically the large number of scan events. Thus, anomaly scans were partitioned as a sequence of anatomical planes or fetal structures obtained over time.A total of 496 anomaly scans performed by 14 sonographers were available for analysis. UK guidelines specify that an image or videoclip of five different anatomical regions must be stored and these were detected in the majority of scans: head/brain was detected in 97.2% of scans, coronal face view (nose/lips) in 86.1%, abdomen in 93.1%, spine in 95.0% and femur in 92.3%. Analyzing the clinical workflow, we observed that sonographers were most likely to begin their scan by capturing the head/brain (in 24.4% of scans), spine (in 23.2%) or thorax/heart (in 22.8%). The most commonly identified two-structure transitions were: placenta/amniotic fluid to maternal anatomy, occurring in 44.5% of scans; head/brain to coronal face (nose/lips) in 42.7%; abdomen to thorax/heart in 26.1%; and three-dimensional/four-dimensional face to sagittal face (profile) in 23.7%. Transitions between three or more consecutive structures in sequence were uncommon (up to 13% of scans). None of the captured anomaly scans shared an entirely identical sequence.We present a novel evaluation of the anomaly scan acquisition process using a deep-learning-based analysis of ultrasound video. We note wide variation in the number and sequence of structures obtained during routine second-trimester anomaly scans. Overall, each anomaly scan was found to be unique in its scanning sequence, suggesting that sonographers take advantage of the fetal position and acquire the standard planes according to their visibility rather than following a strict acquisition order. © 2022 The Authors. Ultrasound in ObstetricsGynecology published by John WileySons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

BACKGROUND: Approximately 3 to 4 billion people worldwide are exposed to household air pollution, which has been associated with increased blood pressure (BP) in pregnant women in some studies. METHODS: We recruited 3195 pregnant women in Guatemala, India, Peru, and Rwanda and randomly assigned them to intervention or control groups. The intervention group received a gas stove and fuel during pregnancy, while the controls continued cooking with solid fuels. We measured BP and personal exposure to PM2.5, black carbon and carbon monoxide 3× during gestation. We conducted an intention-to-treat and exposure-response analysis to determine if household air pollution exposure was associated with increased gestational BP. RESULTS: Median 24-hour PM2.5 dropped from 84 to 24 μg/m3 after the intervention; black carbon and carbon monoxide decreased similarly. Intention-to-treat analyses showed an increase in systolic BP and diastolic BP in both arms during gestation, as expected, but the increase was greater in intervention group for both systolic BP (0.69 mm Hg [0.03-1.35]; P=0.04) and diastolic BP (0.62 mm Hg [0.05-1.19]; P=0.03). The exposure-response analyses suggested that higher exposures to household air pollution were associated with moderately higher systolic BP and diastolic BP; however, none of these associations reached conventional statistical significance. CONCLUSIONS: In intention-to-treat, we found higher gestational BP in the intervention group compared with controls, contrary to expected. In exposure-response analyses, we found a slight increase in BP with higher exposure, but it was not statistically significant. Overall, an intervention with gas stoves did not markedly affect gestational BP.

In the Maternal Vitamin D Osteoporosis Study (MAVIDOS) randomized trial, vitamin D supplementation in pregnancy did not lead to greater neonatal bone mass across the trial as a whole, but, in a prespecified secondary analysis by season of birth, led to greater neonatal bone mass among winter-born babies. Demonstrating persistence of this effect into childhood would increase confidence in a long-term benefit of this intervention. We investigated whether antenatal vitamin D supplementation increases offspring bone mineralization in early childhood in a prespecified, single-center follow-up of a double-blinded, multicenter, randomized controlled clinical trial based in the UK (MAVIDOS). A total of 1123 women in early pregnancy with a baseline 25-hydroxyvitamin D level 25-100 nmol/L from three research centers (2008-2014) were randomized to 1000 IU/d cholecalciferol or matched placebo from 14 weeks of gestation to delivery. Offspring born at the Southampton, UK research center were assessed at age 4 years (2013-2018). Anthropometry and dual-energy X-ray absorptiometry (DXA) were performed (yielding whole body less head [WBLH] bone mineral content [BMC], areal bone mineral density [aBMD], bone area [BA], and body composition). Of 723 children, 564 (78.0%) children attended the 4-year visit, 452 of whom had a useable DXA. Maternal vitamin D supplementation led to greater WBLH aBMD in the children compared with placebo (mean [95% confidence interval {CI}]: supplemented group: 0.477 (95% CI, 0.472-0.481) g/cm2; placebo group: 0.470 (95% CI, 0.466-0.475) g/cm2, p = 0.048). Associations were consistent for BMC and lean mass, and in age- and sex-adjusted models. Effects were observed across the whole cohort irrespective of season of birth. Maternal-child interactions were observed, with a greater effect size among children with low milk intake and low levels of physical activity. Child weight, height, and body mass index (BMI) were similar by maternal randomization group. These findings suggest a sustained beneficial effect of maternal vitamin D supplementation in pregnancy on offspring aBMD at age 4 years, but will require replication in other trials. © 2022 The Authors. JBMR Plus published by Wiley Periodicals LLC on behalf of American Society for Bone and Mineral Research.

The paper reviews current international and Russian recommendations for organizing and conducting ultrasound examinations in obstetric practice during the pandemic of the novel coronavirus infection COVID-19. It discusses questions on disease control measures and choices of type of personal protective equipment for healthcare workers. The algorithms for scheduling screening and fetal monitoring examinations, invasive procedures in cases of fetal malformations and pregnancy complications in patients with suspected or confirmed COVID-19 and in cases with limited human resources in diagnostic departments have been provided. Using the given information in daily practice will ensure the epidemiological safety and clinical effectiveness of the diagnostic departments in our country during COIVID-19 pandemic.

Ultrasound Core Laboratories (UCL) are used in multicenter trials to assess imaging biomarkers to define robust phenotypes, to reduce imaging variability and to allow blinded independent review with the purpose of optimizing endpoint measurement precision. The Household Air Pollution Intervention Network, a multicountry randomized controlled trial (Guatemala, Peru, India and Rwanda), evaluates the effects of reducing household air pollution on health outcomes. Field studies using portable ultrasound evaluate fetal, lung and vascular imaging endpoints. The objective of this report is to describe administrative methods and training of a centralized clinical research UCL. A comprehensive administrative protocol and training curriculum included standard operating procedures, didactics, practical scanning and written/practical assessments of general ultrasound principles and specific imaging protocols. After initial online training, 18 sonographers (three or four per country and five from the UCL) participated in a 2 wk on-site training program. Written and practical testing evaluated ultrasound topic knowledge and scanning skills, and surveys evaluated the overall course. The UCL developed comprehensive standard operating procedures for image acquisition with a portable ultrasound system, digital image upload to cloud-based storage, off-line analysis and quality control. Pre- and post-training tests showed significant improvements (fetal ultrasound: 71% ± 13% vs. 93% ± 7%, p < 0.0001; vascular lung ultrasound: 60% ± 8% vs. 84% ± 10%, p < 0.0001). Qualitative and quantitative feedback showed high satisfaction with training (mean, 4.9 ± 0.1; scale: 1 = worst, 5 = best). The UCL oversees all stages: training, standardization, performance monitoring, image quality control and consistency of measurements. Sonographers who failed to meet minimum allowable performance were identified for retraining. In conclusion, a UCL was established to ensure accurate and reproducible ultrasound measurements in clinical research. Standardized operating procedures and training are aimed at reducing variability and enhancing measurement precision from study sites, representing a model for use of portable digital ultrasound for multicenter field studies.

In the Maternal Vitamin D Osteoporosis Study (MAVIDOS) randomized trial, vitamin D supplementation in pregnancy did not lead to greater neonatal bone mass across the trial as a whole, but, in a prespecified secondary analysis by season of birth, led to greater neonatal bone mass among winter-born babies. Demonstrating persistence of this effect into childhood would increase confidence in a long-term benefit of this intervention. We investigated whether antenatal vitamin D supplementation increases offspring bone mineralization in early childhood in a prespecified, single-center follow-up of a double-blinded, multicenter, randomized controlled clinical trial based in the UK (MAVIDOS). A total of 1123 women in early pregnancy with a baseline 25-hydroxyvitamin D level 25–100 nmol/L from three research centers (2008–2014) were randomized to 1000 IU/d cholecalciferol or matched placebo from 14 weeks of gestation to delivery. Offspring born at the Southampton, UK research center were assessed at age 4 years (2013–2018). Anthropometry and dual-energy X-ray absorptiometry (DXA) were performed (yielding whole body less head [WBLH] bone mineral content [BMC], areal bone mineral density [aBMD], bone area [BA], and body composition). Of 723 children, 564 (78.0%) children attended the 4-year visit, 452 of whom had a useable DXA. Maternal vitamin D supplementation led to greater WBLH aBMD in the children compared with placebo (mean [95% confidence interval {CI}]: supplemented group: 0.477 (95% CI, 0.472–0.481) g/cm2; placebo group: 0.470 (95% CI, 0.466–0.475) g/cm2, p = 0.048). Associations were consistent for BMC and lean mass, and in age- and sex-adjusted models. Effects were observed across the whole cohort irrespective of season of birth. Maternal-child interactions were observed, with a greater effect size among children with low milk intake and low levels of physical activity. Child weight, height, and body mass index (BMI) were similar by maternal randomization group. These findings suggest a sustained beneficial effect of maternal vitamin D supplementation in pregnancy on offspring aBMD at age 4 years, but will require replication in other trials.