May all your femurs be long!

Segmentation and Estimation of Fetal Biometric Parameters using an Attention Gate Double U-Net with Guided Decoder Architecture

The fetus's health is evaluated with the biometric parameters obtained from the low-resolution ultrasound images. The accuracy of biometric parameters in existing protocols typically depends on conventional image processing approaches and hence, is prone to error. This study introduces the Attention Gate Double U-Net with Guided Decoder (ADU-GD) model specifically crafted for fetal biometric parameter prediction. The attention network and guided decoder are specifically designed to dynamically merge local features with their global dependencies, enhancing the precision of parameter estimation. The ADU-GD displays superior performance with Mean Absolute Error of 0.99 mm and segmentation accuracy of 99.1 % when benchmarked against the well-established models. The proposed model consistently achieved a high Dice index score of about 99.1 ± 0.8, with a minimal Hausdorff distance of about 1.01 ± 1.07 and a low Average Symmetric Surface Distance of about 0.25 ± 0.21, demonstrating the model's excellence. In a comprehensive evaluation, ADU-GD emerged as a frontrunner, outperforming existing deep-learning models such as Double U-Net, DeepLabv3, FCN-32s, PSPNet, SegNet, Trans U-Net, Swin U-Net, Mask-R2CNN, and RDHCformer models in terms of Mean Absolute Error for crucial fetal dimensions, including Head Circumference, Abdomen Circumference, Femur Length, and BiParietal Diameter. It achieved superior accuracy with MAE values of 2.2 mm, 2.6 mm, 0.6 mm, and 1.2 mm, respectively.

Short Femur in the Second Trimester Scan Is Related to Maternal Preeclampsia and Small for Gestational Age Newborns

OBJECTIVE

To determine the contribution of short femur diaphysis length (FDL) at 19-22 weeks of gestation in the prediction of adverse pregnancy outcomes.

METHODS

The study included singleton pregnant women who underwent a routine anomaly scan at 19-22 weeks of gestation at the Virgen de la Arrixaca University Clinical Hospital (Murcia, Spain) between August 2011 and August 2012. Fetal biometry and Doppler ultrasound of uterine arteries were assessed as part of the anomaly scan, and the mean pulsatility index of both uterine arteries was recorded. Maternal obstetric characteristics, such as ethnicity, age, weight, parity, cigarette smoking, and medical history including hypertension and diabetes mellitus were collected from our database system.

RESULTS

A total of 6,366 women were included in the study after excluding cases with abnormal karyotype, major fetal abnormalities, or termination of pregnancy. There were 88 cases of preeclampsia (PE) (1.4%). Logistic regression was performed including maternal and fetal characteristics. Short FDL at 19-22 weeks was significantly associated with subsequent development of PE (OR = 0.89, 95% CI: 0.80-0.99, p = 0.025). The best model to predict PE from our sample included gestational age at scan, parity, maternal weight, chronic hypertension, mean pulsatility index in the uterine arteries, and FDL (AUC = 0.78, 95% CI: 0.71-0.84). Regarding small for gestational age (SGA) neonates, there were also significant differences in FDL and FDL <5th centile between the control group and SGA newborns below the 3rd, 5th, and 10th centile. In the groups of preterm births (delivery before 32, 34, and 37 weeks), there were no differences in FDL compared with the control group (term births).

DISCUSSION

Our results suggest that FDL at 19-22 weeks of gestation is an independent predictor of PE and SGA newborns.

Risk of Adverse Outcomes in Euploid Pregnancies With Isolated Short Fetal Femur and Humerus on Second-Trimester Sonography

OBJECTIVES

The purpose of this study was to evaluate pregnancies with isolated short fetal femur and humerus on second-trimester sonography. Short fetal long bones are known to be associated with aneuploidy and structural anomalies. In this study, we wanted to show the risk of adverse pregnancy outcomes in euploid and nonanomalous pregnancies.

METHODS

Singleton pregnancies with short femur and humerus were included. Pregnancies with normal fetal bone lengths and age-matched mothers were selected as controls.

RESULTS

The study group included 30 pregnancies with short fetal femur and humerus, and the control group included 60 normal pregnancies. The overall odds ratio for an adverse pregnancy outcome in the study group was 24.9. Preterm delivery occurred significantly more frequently (odds ratio, 20.8; P < .001), and one-third of pregnancies were complicated by preeclampsia. In the group with short long bones, the odds ratio for a pathologic umbilical Doppler flow pattern was 45.2 (P < .001), and birth weight was significantly lower (P < .001). Also, 3 (10.3%) stillbirths and 4 (13.3%) cases of early neonatal death were recorded in this group. These complications were not recorded in the control group. The risk of emergency cesarean delivery was significantly higher in the group with short long bones (odds ratio, 11.8; P < .001).

CONCLUSIONS

The risk of adverse pregnancy outcomes is significant in euploid and nonanomalous pregnancies with isolated short long bones. Close follow-up is needed during pregnancy.

Isolated Short Fetal Femur Length in the Second Trimester and the Association with Adverse Perinatal Outcome: Experiences from a Tertiary Referral Center

Objective

To determine the association between isolated mid-trimester short fetal femur length and adverse perinatal outcome.

Methods

This is a retrospective cohort study of patients with singleton gestations routinely assessed by second trimester ultrasound examination during 2006-2013. A fetal isolated short femur was defined as a femur length (FL) below the 5^th percentile in a fetus with an abdominal circumference greater than the 10^th percentile. Cases of aneuploidy, skeletal dysplasia and major anomalies were excluded. Primary outcomes of interest included the risk of small for gestational age neonates, low birth weight and preterm birth (PTB). Secondary outcome parameters were a 5-min Apgar score less than 7 and a neonatal intensive care unit admission. A control group of 200 fetuses with FL ≥ 5th percentile was used to compare primary and secondary outcome parameters within both groups. Chi-square and Student’s t-tests were used where appropriate.

Results

Out of 608 eligible patients with a short FL, 117 met the inclusion criteria. Isolated short FL was associated with an increased risk for small for gestational age (19.7% versus 8.0%, p = 0.002) neonates, low birth weight (23.9% versus 8.5%, p<0.001), PTB (19.7% versus 6.0%, p<0.001) and neonatal intensive care unit admissions (13.7% versus 3.5%, p = 0.001). The incidence of a 5-min Apgar score less than 7 was similar in both groups.

Conclusion

Isolated short FL is associated with a subsequent delivery of small for gestational age and Low birth weight neonates as well as an increased risk for PTB. This information should be considered when counseling patients after mid-trimester isolated short FL is diagnosed.

Midtrimester Isolated Short Femur Length as a Predictor of Adverse Pregnancy Outcome

Objective: The aim of this study was to investigate whether midtrimester isolated short femur length is associated with pregnancy complications. Study Design: Retrospective analysis of pregnancies with a midtrimester femur length <5th percentile for gestational age compared to controls with a femur length ≥5th percentile. Outcome measures included hypertensive disorders, being small for gestational age, oligohydramnios and preterm delivery. Results: 2,105 women were eligible for this study, 85 (3.45%) of whom were in the study group and 2,020 were controls. Birth weight <10th percentile for gestational age (OR 4.4, 95% CI 2.5-7.8), birth weight <3rd percentile for gestational age (OR 31.0, 95% CI 13.3-72.3) and severe preeclampsia (OR 6.3, 95% CI 1.4-28.6) were significantly associated with midtrimester isolated short femur length. Conclusions: Midtrimester isolated short femur length is associated with higher rates of being small for gestational age and preeclampsia.

Prenatal diagnosis of congenital femoral deficiency and fibular hemimelia

OBJECTIVES

Routine ultrasonography can detect congenital femoral deficiency (CFD) and fibular hemimelia (FH), but prenatal detection rate and its relation to deformity severity have never been reported. Whether mothers prefer prenatal diagnosis is also unknown. We aimed to determine whether mothers prefer prenatal diagnosis, to report detection rates for CFD and/or FH, and to correlate detection rates to severity of limb shortening.

METHODS

Surveys were mailed to 171 mothers who gave birth to children with CFD/FH between 2000 and 2008. Bilateral femoral and tibial lengths were measured on postnatal radiographs. We calculated corresponding femoral/tibial lengths at gestational weeks 20 and 30.

RESULTS

Sixty-five surveys were returned, and 56 radiographs were reviewed. Most mothers (63%) preferred prenatal diagnosis as it enables prenatal counseling. Congenital limb shortening was detected in 24 cases (37%) and was not detected in 41 cases (63%). Detection rate was 52% (12 of 23) in CFD cases, 23% (three of 13) in FH cases, and 30% (six of 20) in combined cases. CFD cases with severe shortening had a higher detection rate.

CONCLUSIONS

Ultrasonographers should measure both femoral and tibial lengths. Unilateral shortening should result in pediatric orthopedic consultation to estimate limb-length discrepancy at maturity and discuss treatment.

Perinatal outcomes after sonographic detection of isolated short femur in the second trimester

PURPOSE

To determine the association of fetal isolated short femur in the second-trimester ultrasound (US) examination with perinatal outcomes such as small-for-gestational age (SGA) and low-birth weight (LBW) neonates.

METHODS

This is a retrospective cohort study in fetuses routinely assessed by US examination at 18 to 24 weeks during 2006-2009. A fetal isolated short femur was defined as femur length below the 5th percentile and with no chromosomal or structural abnormalities. Fetuses with abdominal circumference below the 5th percentile at the time of US examination were excluded. Each case of short femur was matched with three controls according to gestational age at the time of the US examination.

RESULTS

Sixty-one fetuses met the inclusion criteria. Both the group of women carrying a fetus with isolated short femur and that of women carrying a fetus with normal femur length had similar general and obstetric characteristics. Women carrying a fetus with isolated short femur were significantly more likely to deliver a SGA neonate (19.7% versus 8.7%, p < 0.05) and a LBW neonate (19.7% versus 7.1%, p < 0.05) than women carrying a fetus with normal femur length. Logistic regression analysis found odds ratios for SGA and LBW of 2.6 (95% confidence interval, 1.1-5.9) and 2.9 (95% confidence interval, 1.2-7.1), respectively.

CONCLUSIONS

Isolated short femur in the second-trimester US examination is associated with a subsequent delivery of SGA and LBW neonates.

Variation in fetal ultrasound biometry based on differences in fetal ethnicity

OBJECTIVE

The objective of the study was to evaluate whether fetal ultrasound biometry is affected by variation in fetal ethnicity compared with white controls.

STUDY DESIGN

This was a retrospective observational study of ultrasound biometry in pregnant women with accurate gestational age.

RESULTS

Three hundred five white, 370 Asian, 895 part Hawaiian, 76 Pacific Islander, and 311 white Asian fetuses were analyzed. At 18 weeks gestation femur length was significantly shorter in Asian and white Asian. Humerus length was significantly shorter in Asian, part Hawaiian, and white Asian. White genetic sonogram was positive 14% for femur and 15% for humerus. The following was found: Asian 29% femur (odds ratio [OR], 2.58; 95% confidence interval [CI], 1.70-3.92), 25% humerus (OR, 1.86; 95% CI, 1.23-2.82); part Hawaiian 21% femur (OR, 1.67; 95% CI, 1.14-2.45), 23% humerus (OR, 1.64; 95% CI, 1.13-2.38); Pacific Islander 27% femur (OR, 2.37; 95% CI, 1.23-4.54), 33% humerus (OR, 2.76; 95% CI, 1.47-5.14); and white Asian 20% femur (OR, 1.56; 95% CI, 1.01-2.46), 22% humerus (OR, 1.56; 95% CI, 1.01-2.42).

CONCLUSION

Genetic sonogram was screen positive more frequently because of shorter long bone measurements in all nonwhite ethnicities.