Estimate of fetal weight by ultrasound within two weeks of delivery in the detection of fetal macrosomia

M., Arvind K. S.. Predictive Assessment of Fetus Features Using Scanned Image Segmentation Techniques and Deep Learning Strategy

Fetus weight at various stages of pregnancy is a critical component in determining the health of the baby. Abnormalities arising early in the pregnancy may be prevented by preventive measures. A variety of techniques suggested to predict foetus weight. Computer vision is a capability that can estimate the weight of a baby based on ultra-sonograms taken at various stages of pregnancy. Using the scanned data, one may train an advanced convolutional neural network that helps in accurately forecasting the fetus's size, weight, and overall health. The research utilizes computer vision techniques with image clustering methods for preprocessing, to predict the foetus's health, training datasets defective foetus datasets and healthy foetus datasets. Developing an integrated computer vision and a deep neural network is the hour which decrease the cost of operations and manual processes This study estimate the fetus's weight with optimal accuracy range at varying gestation age.

Antenatal awareness and obstetric outcomes in large fetuses: A retrospective evaluation

INTRODUCTION

There is currently no consensus on the management of large fetuses in order to minimize fetal complications. The aim of this study was to assess whether antenatal recognition of large-for-gestational age (LGA) reduced poor obstetric newborn outcomes in a hospital where expectant management was used.

MATERIAL AND METHODS

A retrospective cohort study was made of two delivery units at Karolinska University Hospital, Stockholm, Sweden, using expectant management of LGA. All deliveries > 37⁺⁰ weeks of gestation during an 8-year period (2002-2009) were included. The main outcome was severe adverse outcome, a composite variable including neonatal trauma (brachial plexus birth palsy [BPBP] and fractures) and asphyxic sequelae (severe asphyxia, cerebral damage, and fetal/infant death).

RESULTS

The study population consisted of 63,542 appropriate-for-gestational age (AGA) and 3,343 LGA pregnancies (of which 21 % were identified before delivery). Compared to AGA, LGA pregnancies showed a five-fold increased risk of neonatal trauma (OR 5.1, 95 % CI 4.0 - 6.4), but no differences were seen regarding asphyxic sequelae. LGA fetuses identified antenatally had adverse outcomes in 3.7 % of all cases, compared to 3.5 % where LGA was not identified (OR 1.07 95 % CI 0.7 - 1.7). When adjusted for newborn weight deviation, the OR was 0.96, 95 % CI 0.6 - 1.5. There was a three-fold higher risk (OR 3.0, 95 % CI 1.2 - 7.4) of neonatal trauma among non-identified LGA cases > 41⁺⁰ gestational weeks. A total of 81 % of those with LGA were identified after a week 41 routine ultrasound. Out of 68 cases with planned vaginal delivery and expected birth weight > 5000 g, 7.4 % suffered BPBP, representing a 31-fold increase in risk, compared to 0% BPBP among those delivered by elective caesarean section.

CONCLUSION

Antenatal awareness of LGA did not lower the risk of severe adverse outcomes in a unit using expectant management, but those identified postdate were at a lower risk of neonatal trauma. For every 14 fetuses with an expected birth weight > 5000 g delivered by cesarean section, one case of BPBP could be avoided.

Identifying fetal growth disorders using ultrasound in obese nulliparous women

OBJECTIVE

We evaluated the ability of third trimester ultrasound to diagnose fetal growth disorders among obese women.

METHODS

This is a retrospective cohort study of obese nulliparous women who delivered term singleton neonates who had an ultrasound within 5 weeks of delivery. We characterized the sensitivity, specificity, positive predictive value and negative predictive value of ultrasound to detect large-for-gestational age (LGA) and small-for-gestational age (SGA) infants. Antenatally, LGA and SGA were defined as an ultrasound estimated fetal weight >90% or <10% based on the Hadlock formula. Postnatally, LGA or SGA designation was based on gestational age-based birthweight percentiles. Test characteristics were analyzed for the total cohort and by class of obesity (class II, body mass index [BMI] = 35.0-39.9 kg/m² versus class III, BMI ≥ 40 kg/m²). We compared the area under the curve for receiver-operating characteristic (ROC) curves for different classes of obesity.

RESULTS

Of 690 women, 13 (1.9%) screened positive for SGA and 19 (2.8%) delivered an SGA neonate. In contrast, 158 (22.9%) screened positive for LGA and 97 (14.1%) delivered an LGA neonate. The sensitivity of ultrasound for SGA was 26.3% and the specificity was 98.8%. The sensitivity for LGA was 75.3% and the specificity was 85.7%. The ROC curves did not differ significantly for different classes of obesity (p = .69 for SGA, p = .75 for LGA).

CONCLUSION

Ultrasound in obese women who delivered term pregnancies has a high specificity but poor sensitivity for SGA and a low positive predictive value for LGA.

Sonographic prediction of macrosomia in pregnancies complicated by maternal diabetes: finding the best formula

PURPOSE

To evaluate the best performing formula for macrosomia prediction in pregnancies complicated by diabetes.

METHODS

A retrospective analysis was performed of 1060 sonographic fetal biometrical measurements performed within 7 days of delivery in term pregnancies (37-42 gestational weeks) complicated by diabetes. Sonographic prediction of macrosomia (≥ 4000, ≥ 4250, and ≥ 4500 g) was evaluated utilizing ten previously published formulas by: (1) calculating for each macrosomia threshold the sensitivity, specificity, positive and negative predictive value, and ± likelihood ratio for macrosomia prediction; (2) comparing the systematic and random error and the proportion of estimates < 10% of birth weights between macrosomic and non-macrosomic neonates. Best performing formula was determined based on Euclidean distance.

RESULTS

97 (9.2%) macrosomic neonates (> 4000 g) were included. Median birth weight was 3380 (1866-3998) g for non-macrosomic and 4198 (4000-5180) g for macrosomic neonates. Higher macrosomia cutoff was associated with higher specificity and lower sensitivity. We found a considerable variation between formulas in different accuracy parameters. Hadlock's formula (1985), based on abdominal circumference, femur length, head circumference and biparietal diameter, had the shortest Euclidean distance, reflecting the highest accuracy.

CONCLUSION

Prediction of macrosomia among women with diabetes differs significantly between formulas. In our cohort, the best performing formula for macrosomia prediction was Hadlock's formula (1985).

Identifying Fetal Growth Disorders Using Ultrasonography in Women With Diabetes

OBJECTIVES

We evaluated the ability of third-trimester ultrasonography (US) to diagnose disorders of fetal growth among women with diabetes mellitus.

METHODS

This work was a retrospective cohort study of women with diabetes who delivered term singleton neonates at a single academic medical center and who had a US examination within 5 weeks of delivery. We characterized the sensitivity, specificity, positive predictive value, and negative predictive value of US to detect large-for-gestational age (LGA) and small-for-gestational age (SGA) infants. Large and small for gestational age were defined as a US estimated fetal weight of greater than 90% and less than 10%, respectively, based on the Hadlock formula (Radiology 1991; 181:129-133); US estimates of LGA or SGA were compared with postnatal findings of LGA or SGA based on gestational age-based weight percentiles. Test characteristics were analyzed for the total cohort and by the type of diabetes. We compared the areas under the curve for receiver operating characteristic curves for different types of diabetes.

RESULTS

Of 521 women, 3 (0.6%) screened positive for SGA, and 64 (12.3%) delivered an SGA neonate. In contrast, 129 (24.8%) screened positive for LGA, and 61 (11.7%) delivered an LGA neonate. The receiver operating characteristic curves did not differ significantly for different types of diabetes (P = .68).

CONCLUSIONS

Ultrasonography in women with diabetes and term or late preterm pregnancies has high specificity but poor sensitivity for SGA and a low positive predictive value for LGA. The diagnostic capability of US to detect fetal growth abnormalities did not differ significantly by the type of diabetes.

An obstetric sphincter injury risk identification system (OSIRIS): is this a clinically useful tool?

Introduction and hypothesis

To establish the contribution of maternal, fetal and intrapartum factors to the risk of incidence of obstetric anal sphincter injuries (OASIS) and assess the feasibility of an OASIS risk prediction model based on variables available to clinicians prior to birth.

Methods

This was a population-based, retrospective cohort study using single-site data from the birth database of Aarhus University Hospital, Denmark. The participants were all women who had a singleton vaginal birth during the period 1989 to 2006. Univariate and multivariate logistic regression analyses were performed using multiple imputations for missing data and internally validated using bootstrap methods. The main outcome measures were the contributions of maternal, fetal and intrapartum events to the incidence of OASIS.

Results

A total of 71,469 women met the inclusion criteria, of whom 1,754 (2.45 %) sustained OASIS. In the multivariate analysis of variables known prior to birth, maternal age 20 – 30 years (OR 1.65, 95 % CI 1.44 – 1.89) and ≥30 years (OR 1.60, 95 % CI 1.39 – 1.85), occipitoposterior fetal position (OR 1.34, 95 % CI 1.06 – 1.70), induction/augmentation of labour (OR 1.46, 95 % CI 1.32 – 1.62), and suspected macrosomia (OR 2.20, 95 % CI 1.97 – 2.45) were independent significant predictors of OASIS, with increasing parity conferring a significant protective effect. The ‘prebirth variable’ model showed a 95 % sensitivity and a 24 % specificity in predicting OASIS with 1 % probability, and a 3 % sensitivity and a 99 % specificity in predicting OASIS with a 10 % probability.

Conclusions

Our model identified several significant OASIS risk factors that are known prior to actual birth. The prognostic model shows potential for ruling out OASIS (high sensitivity with a low risk cut-off value), but is not useful for ruling in the event.

Electronic supplementary material

The online version of this article (doi:10.1007/s00192-016-3125-2) contains supplementary material, which is available to authorized users.