Novel artificial intelligence approach for automatic differentiation of fetal occiput anterior and non-occiput anterior positions during labor.

OBJECTIVES: To describe a newly developed machine-learning (ML) algorithm for the automatic recognition of fetal head position using transperineal ultrasound (TPU) during the second stage of labor and to describe its performance in differentiating between occiput anterior (OA) and non-OA positions. METHODS: This was a prospective cohort study including singleton term (> 37 weeks of gestation) pregnancies in the second stage of labor, with a non-anomalous fetus in cephalic presentation. Transabdominal ultrasound was performed to determine whether the fetal head position was OA or non-OA. For each case, one sonographic image of the fetal head was then acquired in an axial plane using TPU and saved for later offline analysis. Using the transabdominal sonographic diagnosis as the gold standard, a ML algorithm based on a pattern-recognition feed-forward neural network was trained on the TPU images to discriminate between OA and non-OA positions. In the training phase, the model tuned its parameters to approximate the training data (i.e. the training dataset) such that it would identify correctly the fetal head position, by exploiting geometric, morphological and intensity-based features of the images. In the testing phase, the algorithm was blinded to the occiput position as determined by transabdominal ultrasound. Using the test dataset, the ability of the ML algorithm to differentiate OA from non-OA fetal positions was assessed in terms of diagnostic accuracy. The F1 -score and precision-recall area under the curve (PR-AUC) were calculated to assess the algorithm's performance. Cohen's kappa (κ) was calculated to evaluate the agreement between the algorithm and the gold standard. RESULTS: Over a period of 24 months (February 2018 to January 2020), at 15 maternity hospitals affiliated to the International Study group on Labor ANd Delivery Sonography (ISLANDS), we enrolled into the study 1219 women in the second stage of labor. On the basis of transabdominal ultrasound, they were classified as OA (n = 801 (65.7%)) or non-OA (n = 418 (34.3%)). From the entire cohort (OA and non-OA), approximately 70% (n = 824) of the patients were assigned randomly to the training dataset and the rest (n = 395) were used as the test dataset. The ML-based algorithm correctly classified the fetal occiput position in 90.4% (357/395) of the test dataset, including 224/246 with OA (91.1%) and 133/149 with non-OA (89.3%) fetal head position. Evaluation of the algorithm's performance gave an F1 -score of 88.7% and a PR-AUC of 85.4%. The algorithm showed a balanced performance in the recognition of both OA and non-OA positions. The robustness of the algorithm was confirmed by high agreement with the gold standard (κ = 0.81; P < 0.0001). CONCLUSIONS: This newly developed ML-based algorithm for the automatic assessment of fetal head position using TPU can differentiate accurately, in most cases, between OA and non-OA positions in the second stage of labor. This algorithm has the potential to support not only obstetricians but also midwives and accoucheurs in the clinical use of TPU to determine fetal occiput position in the labor ward. © 2021 International Society of Ultrasound in Obstetrics and Gynecology.

Postpartum Spontaneous Subcapsular Hepatic Hematoma (SSHH)- Conservative Management. Case Report and Review of Literature.

Spontaneous subcapsular hematoma of the liver, with no history of preeclampsia and HELLP syndrome (Hemolysis, Elevated Liver enzymes, and Low Platelet count.), represents an exceptionally rare clinical condition in pregnancy and postpartum. The complications can be devastating in terms of fetal and maternal mortality. We hereby present a case of a 33-year-old female that underwent an emergency Cesarean section (C-section) at term with the extraction of a live foetus. Few hours after delivery, she complained of intense epigastric and abdominal pain. The diagnostic work-up suggested a SSHH. The condition was managed conservatively in a multidisciplinary team.

Ultrasound Evaluation of Fetal Biometry and Doppler Parameters in the Third Trimester of Pregnancy Suspected of Intrauterine Growth Restriction.

PURPOSE: The purpose of this study was to investigate fetal biometry and Doppler parameters in the third trimester of pregnancy with suspected restriction of fetal growth as potential predictors of unfavorable neonatal status. MATERIAL/METHODS: The uterine artery, umbilical and middle cerebral artery, cerebroplacental ratio (CPR), and estimated fetal weight (EFW) were evaluated in a cohort of 126 pregnancies that resulted in the birth of a fetus <10 percentiles (SGA). RESULTS: The demographic data of the studied cases did not show a significant difference between the parameters studied in the two study groups: Late SGA fetuses and Early SGA fetuses. Analyzing fetal biometry we found a significant difference for some parameters in relation to the two study groups. Our study showed that the Early SGA fetuses group had a lower birth weight, a lower gestational age at birth, an increase in the incidence of premature birth with an increase in Doppler abnormal incidence. CONCLUSIONS: Ultrasound examination and Doppler monitoring provide a non-invasive repetitive method for supervising fetuses with growth restriction in order to apply an adequate management.

A Severe Case of Aneurysmal Malformation of the Vein of Galen, Cardiac Failure and Intrauterine Fetal Death.

Aneurism of the vein of Galen is a rare congenital anomaly, where complex arteriovenous malformation are identified between multiple choroidal arteries and the median prosencephalic vein of Markowski, which is a precursor of the vein of Galen, with subsequent aneurysmal enlargement of the respective arteriovenous system. The congenital malformation develops during week 6 to 11 of fetal development. Infants often die from high-output congestive heart failure. We present a case of a 40 years old patient, presented the first time at hospital at 28 weeks of gestation for lower perception of fetal movements. The patient was referred to our Prenatal Diagnosis Unit for a suspected cardiac malformation. We diagnosed cardiomegaly along vein of Galen aneurysmal malformation (VGAM) with severe cardiac failure, ascites, and critical fetal distress. Fetal demise was noted 24 hours later, during the corticosteroid procedures for fetal maturation. A stillborn weighting 2000g with a severe hydropic aspect was born after labor induction. Autopsy was performed following injection of colored gelatin in carotid vessels. The aneurysmal defect was evident in the vein of Galen and straight sinus. We also found the transverse, sagittal and the occipital sinus seriously dilated. We could not highlight the communication with the middle cerebral artery, because of the degradation of the cerebral tissue, despite an optimal preparation.

Utility of Cerebroplacental Ratio in IUGR Fetuses from Pregnancy with Preeclampsia in Prediction the Risk for Perinatal Complications.

PURPOSE: The aim of this study was to show that is the incidence of intrauterine growth restriction (IUGR) in women with preeclampsia (PE), assessment of cerebroplacental ratio (CPR) to establish the diagnostic value of CPR in fetuses with preeclampsia with/without IUGR. MATERIAL AND METHODS: We performed an analysis of 49 cases with gestational hypertension and PE and 16 cases with normal pregnancy for control lot, study in Obstetrics and Gynecology Clinic of the Municipal Hospital Filantropia, Craiova, between October 2013 and October 2015. It was performed clinical and laboratory evaluation and management of each case. CPR ratio was measured in the third trimester in all cases, being studied according to the normal and abnormal values obtained, following the evolution of the newborn. RESULTS: Mild PE cases were predominant with 21 cases (19.27%), severe PE accounted for 16 cases (14.68%) and gestational hypertension was found in 16 cases in our study. Distribution of IUGR cases presented interesting and contradictory data, because we met cases of IUGR in pregnancies without PE, at a rate of only 1.54%. The incidence of IUGR was significantly higher in cases with severe early-onset PE (10.20%). Cases of severe PE, but with late-onset, had IUGR in only 2.04% of cases. We found a significant statistical significance (p <0.005) on the incidence of IUGR in cases with severe early-onset PE. CPR identified adverse perinatal outcomes in 18.46% of cases with CPR <1.08. CONCLUSIONS: This study shows that early onset severe PE and concomitantly IUGR affects a significant proportion of pregnancies. CPR can be used to identify fetuses with an increased risk of intrauterine compromise.

Fetal Kidneys Ultrasound Appearance in the First Trimester - Clinical Significance and Limits of Counseling.

OBJECTIVE: The objective of this study was to determine the visualizing rate of fetal kidneys at various gestational ages in late first trimester (FT) and to establish the clinical significance of their two-dimensional ultrasound (2DUS) appearance in the FT. METHODS: In a prospective cross-sectional study, 1456 women from an unselected population underwent a detailed assessment of fetal anatomy at 11+0 -13+4 weeks of gestation with the use of transabdominal sonography. Information on the ultrasound findings, antenatal course and perinatal outcome was obtained in 1331 cases. RESULTS: 44 cases in which a congenital kidney disease was detected by ultrasound in the prenatal period were identified. The renal pathology was suspected in the FT in 8 cases, and confirmed by a standard test (postmortem autopsy or second-trimester scan) in 4 cases. The standard detailed second-trimester scan at 18-22 weeks diagnosed another 23 cases but refuted suspicion in 4 FT positive cases. The third trimester added another 17, all confirmed by the postpartum scan. For FT presence or absence of congenital renal anomalies, sensitivity, specificity, +LRs and -LRs of 2DUS were 9.09%, 99.69%, 29.25, and 0.91. CONCLUSION: FT prenatal kidneys' visualization is critically dependent on the gestational age. FT diagnosis holds uncertainty. An early diagnosis carries a risk of providing a false-positive or a false-negative result, because the differentiation of the renal system is delayed or the diagnosis is not amenable yet to prenatal ultrasound. No FT findings can exclude the mid-trimester follow-up ultrasound scan. Second and third trimester scan are relevant for congenital kidney diseases.

Acceptability of Intrapartum Ultrasound Monitoring - Experience from a Romanian Longitudinal Study.

OBJECTIVES: To assess the acceptability of intrapartum ultrasound (IPUS) labor monitoring in unselected Romanian women attending a tertiary maternity unit and the patients' experience of the examination (i.e. the perceived difficulty regarding the evaluation protocol). METHODS: The research was a prospective longitudinal observational study on unselected low-risk women that delivered in our unit. IPUS monitoring of active labor was proposed for observational purposes in low-risk population. Transabdominal and transperineal scans were performed hourly in the first stage of labor and at every 15 minutes in the second stage. The second day after birth, consenting women were invited to take part in a questionnaire survey with features regarding the patient's impression about the ultrasound monitoring scans during labor, and the acceptability of having an IPUS protocol for labor monitoring in the future. RESULTS: From 200 parturient women questioned, 98% of them agreed to IPUS investigation protocol. The demographic characteristics did not influence the acceptance. However, due to the small number of women declining IPUS we were not able to compare the characteristics and perceptions of women who declined the scan with those who accepted it. Most of the women (93% of accepters and 75% of decliners) had little difficulty deciding whether or not to have the scan protocol. All laboring women who had the IPUS scan found it an acceptable experience; 21% of women without epidural anesthesia rated the perceived difficulty as "mild" or "discomforting". Women rated having the IPUS scan as being significantly less difficult than having a cervical smear, transvaginal scan or having a digital clinical evaluation. 67% of the studied patients expressed increased confidence while being able to follow along the medical personnel the progression of the labor on the ultrasound screen. 97% of the consenting women who had the IPUS scans and all the 4 decliners said they would definitely or probably agree such ultrasound monitoring in a future labor, if this technique is proven useful for the labor outcome. CONCLUSIONS: IPUS protocol for labor monitoring was overwhelmingly acceptable in our population of women, despite the fact that they were learning about the procedure for the first time. The demographic characteristics did not influence acceptance, but due to the high rate of acceptance, predictors of acceptance could not be analyzed. More than two thirds of the patients expressed increased confidence while being able to follow along the medical personnel the progression of the labor on the ultrasound screen and almost all the participants were willing to have the procedure again in future, further reinforcing their favorable attitude to the procedure.

Agenesis of ductus venosus in sequential first and second trimester screening.

OBJECTIVE: The goal of this study is to evaluate the potential of first trimester (FT) screening in the diagnosis of agenesis of the ductus venosus (ADV) and to study its prevalence in a low-risk population, the associated conditions, and pregnancy outcome. METHOD: Prospective, sequential screening study at two tertiary units with morpho-functional evaluation of the ductus venosus during the first and second trimester screening. We quantified the FT detection rate, prevalence, and associated conditions: umbilical shunting type, concomitant anomalies, and outcome. RESULTS: In 6114 consecutive pregnancies, we identified 11 cases of ADV. Ten (91%) were identified during the FT examination. The prevalence was 1 in 556, similar for both centers (1/478 vs. 1/691). Major structural defects and fetal effusions were detected in 8 (73%). twenty two percent had a major chromosomal abnormality. In 3 cases, the anomaly was isolated and had normal outcome, independent of liver by-pass, caliber of the shunt, and NT thickness. CONCLUSIONS: Agenesis of the ductus venosus can be detected during FT. The early detection of ADV is important given its high association with major abnormalities.

Importance of Laparoscopic Assessment of the Uterine Adnexa in a Mayer-Rokitansky-Kuster-Hauser Syndrome Type II Case.

In the case reported, diagnosed with Mayer-Rokitansky-Kuster-Hauser (MRKH) syndrome, the presence of normal ovaries proved to be challenging to confirm due to unusual high positioned (ectopic) ovaries. MRKH syndrome is a rare pathological condition characterized by a spectrum of the Mullerian duct abnormalities resulting in congenital aplasia of the uterus and of the upper part (2/3) of the vagina, developed during embryogenesis. At the same time, the mullerian development is interdependent with the Wolffian (mesonephric) duct and this explains the associated renal abnormalities (MRKH type II). Laparoscopic assessment was of great importance in defining the exact anatomic characteristics of MRKH syndrome.

First trimester two- and four-dimensional cardiac scan: intra- and interobserver agreement, comparison between methods and benefits of color Doppler technique.

OBJECTIVE: To evaluate intra- and interobserver agreement for first-trimester fetal cardiac structural assessment, using two-dimensional (2D) ultrasound (2D-US) and 4D-US (4D spatiotemporal image correlation (STIC) technology), to compare the methods and to assess the advantages of adding color Doppler to each technique. METHODS: Digital videoclips (B-mode and color Doppler) and 4D-STIC volumes (gray-scale and color Doppler) from 632 pregnancies with normal fetal hearts were acquired and stored at the time of detailed first-trimester ultrasound examination. Later analysis on a randomized sample of 100 cases was performed, targeting 11 cardiac structures and features. We compared visualization of fetal heart parameters using 2D-US vs 4D-US and gray-scale vs color Doppler imaging. RESULTS: STIC volumes were considered satisfactory (adequate visualization of at least 8/11 parameters) in 78% of cases and 2D-US acquisitions in 89% of cases. The intra- and interobserver agreement was good for both 2D and 4D methods (kappa > 0.6), and the percentage overall agreement was very high using both methods (95%). 2D- and 4D-US identification of the fetal cardiac parameters did not differ significantly. The differences between gray-scale and color Doppler imaging were statistically significant in identifying similar key cardiac parameters, for both 2D- and 4D-US (P < 0.05). CONCLUSION: Both 2D and 4D methods for assessing first-trimester heart parameters are feasible and repeatable within and between observers. Color Doppler adds valuable information to both methods.