Optimizing Performance of Transformer-based Models for Fetal Brain MR Image Segmentation.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To test transformer-based models' performance when manipulating pretraining weights, dataset size, input size and comparing the best-model with reference standard and state-of-the-art models for a resting-state functional (rs-fMRI) fetal brain extraction task. Materials and Methods An internal retrospective dataset (fetuses = 172; images = 519; collected from 2018-2022) was used to investigate influence of dataset size, pretraining approaches and image input size on Swin-UNETR and UNETR models. The internal and an external (fetuses = 131; images = 561) datasets were used to cross-validate and to assess generalization capability of the best model against state-of-the-art models on different scanner types and number of gestational weeks (GW). The Dice similarity coefficient (DSC) and the Balanced average Hausdorff distance (BAHD) were used as segmentation performance metrics. GEE multifactorial models were used to assess significant model and interaction effects of interest. Results Swin-UNETR was not affected by pretraining approach and dataset size and performed best with the mean dataset image size, with a mean DSC of 0.92 and BAHD of 0.097. The Swin-UNETR was not affected by scanner type. Generalization results on the internal dataset showed that Swin-UNETR had lower performances compared with reference standard models and comparable performances on the external dataset. Cross-validation on internal and external test sets demonstrated better and comparable performance of Swin-UNETR versus convolutional neural network architectures during the late-fetal period (GWs > 25) but lower performance during the midfetal period (GWs ≤ 25). Conclusion Swin-UNTER showed flexibility in dealing with smaller datasets, regardless of pretraining approaches. For fetal brain extraction of rs-fMRI, Swin-UNTER showed comparable performance with reference standard models during the late-fetal period and lower performance during the early GW period. ©RSNA, 2024.

Etiologically Based Functional Taxonomy of the Preterm Birth Syndrome.

Preterm birth (PTB) is a complex syndrome traditionally defined by a single parameter, namely, gestational age at birth (ie, ˂37 weeks). This approach has limitations for clinical usefulness and may explain the lack of progress in identifying cause-specific effective interventions. The authors offer a framework for a functional taxonomy of PTB based on (1) conceptual principles established a priori; (2) known etiologic factors; (3) specific, prospectively identified obstetric and neonatal clinical phenotypes; and (4) postnatal follow-up of growth and development up to 2 years of age. This taxonomy includes maternal, placental, and fetal conditions routinely recorded in data collection systems.

Preterm birth in singleton pregnancies conceived by in vitro fertilization or intracytoplasmic sperm injection: an overview of systematic reviews.

BACKGROUND: The rate of preterm birth of singletons conceived through in vitro fertilization (IVF) or intracytoplasmic sperm injection (ICSI) is increased, being as high as 15% to 16% across Europe and the United States. However, the underlying etiology, phenotype, and mechanisms initiating preterm birth (PTB) are poorly understood. OBJECTIVE: To quantify the PTB risk and examine supposed etiology in IVF/ICSI singleton pregnancies compared to naturally conceived. STUDY DESIGN: Overview of reviews including all available systematic reviews with meta-analysis comparing PTB risk in IVF/ICSI and naturally conceived singletons. A comprehensive search of PubMed/MEDLINE, Embase, Scopus, and Cochrane Library databases was performed up to December 31, 2023. Information available on etiology, phenotype, initiation of PTB, and relevant moderators was retrieved and employed for subgroup analyses. Random-effects meta-analysis models were used for pooling effect measures. Estimates were presented as odds ratios (ORs) with 95% confidence intervals (CIs). The extent of overlap in the original studies was measured using the corrected covered area assessment. The quality of the included reviews was evaluated with the AMSTAR 2 tool. The Grading of Recommendations Assessment, Development and Evaluation approach was applied to rate evidence certainty. The protocol was registered on PROspective Register of Systematic Reviews (CRD42023411418). RESULTS: Twelve meta-analyses (16,522,917 pregnancies; ˃433,330 IVF/ICSI) were included. IVF/ICSI singletons showed a significantly higher PTB risk compared to natural conception (PTB ˂37 weeks: OR: 1.72, 95% CI: 1.57-1.89; PTB<32 weeks: OR: 2.19, 95% CI: 1.82-2.64). Influential analysis reinforced the strength of this association. Subgroup analyses investigating supposed etiology revealed a comparable risk magnitude for spontaneous PTB (OR: 1.79, 95% CI: 1.56-2.04) and a greater risk for iatrogenic PTB (OR: 2.28, 95% CI: 1.72-3.02). PTB risk was consistent in the subgroup of conventional IVF (OR: 1.95, 95% CI: 1.76-2.15) and higher in the subgroup of fresh only (OR: 1.79, 95% CI: 1.55-2.07) vs frozen-thawed embryo transfers (OR: 1.39, 95% CI: 1.34-1.43). There was minimal study overlap (13%). The certainty of the evidence was graded as low to very low. CONCLUSION: Singletons conceived through IVF/ICSI have a 2-fold increased risk of PTB compared to natural conception, despite the low certainty of the evidence. There is paucity of available data on PTB etiology, phenotype, or initiation. The greater risk increase is observed in fresh embryo transfers and involves iatrogenic PTB and PTB ˂32 weeks, likely attributable to placental etiology. Future studies should collect data on PTB etiology, phenotype, and initiation. IVF/ICSI pregnancies should undertake specialistic care with early screening for placental disorders, cervical length, and growth abnormalities, allowing appropriate timely follow-up, preventive measures, and therapeutic interventions strategies.

Commentary: Predicting adverse outcomes in pregnant patients positive for SARS-CoV-2 by a machine learning approach.

SARS-CoV-2 infection poses a significant risk increase for adverse pregnancy outcomes both from maternal and fetal sides. A recent publication in BMC Pregnancy and Childbirth presented a machine learning algorithm to predict this risk. This commentary will discuss potential implications and applications of this study for future global health policies.

Progesterone levels during ovarian stimulation in segmented ART cycles inversely correlate with normalized birthweight of neonates conceived through subsequent frozen-thawed embryo transfer.

PURPOSE: To evaluate the association between serum progesterone (P) at the day of ovulation trigger and neonatal birthweight in singletons born after frozen-thawed embryo transfer in segmented ART cycles. METHODS: A retrospective multicenter cohort study involving data from patients who achieved uncomplicated pregnancy and term delivery of ART-conceived singleton babies following a segmented GnRH antagonist cycle. The main outcome was birthweight's z-score of the neonate. Univariate and multivariate linear logistic regression analyses were made to investigate the relation of z-score with variables inherent to the patient and to the ovarian stimulation. The variable P per oocyte was created by dividing the value of progesterone at ovulation trigger by the number of oocytes retrieved at oocyte retrieval. RESULTS: A total of 368 patients were included in the analysis. At univariate linear regression, the birthweight z-score of the neonate appeared to be inversely related to both P levels at the ovulation trigger (- 0.101, p = 0.015) and P levels per oocyte at trigger (- 1.417, p = 0.001), while it was directly related to the height of the mother (0.026, p = 0.002) and to the number of previous live births (0.291, p = 0.016). In multivariate analysis, both serum P (- 0.1; p = 0.015) and P per oocyte (- 1.347, p = 0.002) maintained the significant inverse association with birthweight z-score after adjusting for height and parity. CONCLUSIONS: Serum progesterone level on the day of ovulation trigger inversely correlates with normalized birthweight of neonates in segmented GnRH antagonist ART cycles.

Endometriosis increases the risk of gestational diabetes: a meta-analysis stratified by mode of conception, disease localization and severity.

To review the current evidence on the risk of gestational diabetes mellitus (GDM) in women with endometriosis, taking into account relevant confounders such as the higher frequency of Assisted Reproductive Technologies (ART) conceptions. Database searches on PubMed, Medline, Embase and Scopus through June 2022, using combinations of relevant keywords. A total of 18 studies, involving N = 4,600,885 women, were included. The overall risk of GDM in endometriosis patients was significantly higher than in controls (OR, 1.23; 95% CI 1.07-1.51). This significant association persisted in natural pregnancies (OR, 1.08; 95% CI 1.04-1.12) but not in pregnancies conceived through ART (OR, 0.93;95% CI 0.70-1.24). Based on the limited number of studies that examined this association in relation to endometriosis phenotype, an increased risk was found in more severe stages (OR, 3.20; 95% CI 1.20-8.54) but independently from localization of the lesions. Endometriosis increases the risk of GDM, with a possible progressive effect in more advanced stages of the disease. Although the effect magnitude may be limited in some subgroups, this finding has a clinically relevant impact due to both the strong biological plausibility and to the relatively high incidence of both endometriosis and GDM.

Obstetric, neonatal, and child health outcomes following embryo biopsy for preimplantation genetic testing.

BACKGROUND: Preimplantation genetic testing (PGT) of embryos developed in vitro requires a biopsy for obtaining cellular samples for the analysis. Signs of cell injury have been described in association with this procedure. Thus, the consequences of the biopsy on obstetric and neonatal outcomes have been the subject of some quantitative analyses, although the reliability of data pooling may be limited by important issues in the various reports. OBJECTIVE AND RATIONALE: The present review identifies evidence for whether pregnancies conceived after embryo biopsy are associated with a higher risk of adverse obstetric, neonatal, and long-term outcomes. Available evidence has been summarized considering manipulation at various stages of embryo development. SEARCH METHODS: We used the scoping review methodology. Searches of article databases were performed with keywords pertaining to the embryo biopsy technique and obstetric, neonatal, and postnatal outcomes. Studies in which embryos were biopsied at different stages (i.e. both at the cleavage and blastocyst stages) were excluded. We included data on fresh and frozen embryo transfers. The final sample of 31 documents was subjected to qualitative thematic analysis. OUTCOMES: Sound evidence is lacking to fully address the issues on the potential obstetric, neonatal or long-term consequences of embryo biopsy. For polar body biopsy, the literature is too scant to draw any conclusion. Some data, although limited and controversial, suggest a possible association of embryo biopsy at the cleavage stage with an increased risk of low birthweight and small for gestational age neonates compared to babies derived from non-biopsied embryos. An increase in preterm deliveries and birth defects in cases of trophectoderm biopsy was suggested. For both biopsy methods (at the cleavage and blastocyst stages), an increased risk for hypertensive disorders of pregnancy was found. However, these findings may be explained by confounders such as other embryo manipulation procedures or by intrinsic patient or population characteristics. WIDER IMPLICATIONS: Since there is inadequate evidence to assess obstetric, neonatal, and long-term health outcomes following embryo biopsy, an invasive PGT strategy should be developed with a cautious approach. A non-invasive approach, based on the analysis of embryo cell-free DNA, needs to be pursued to overcome the potential limitations of embryo biopsy.

The cumulative incidence of neonatal metabolic acidemia after terminal bradycardia in the 2nd stage of labor: a survival-based model.

PURPOSE: The aim of the study was to estimate by a survival analysis model the hazard function (HF) for neonatal metabolic acidemia (MA) throughout the 2nd stage of labor (2STG) at the time of occurrence of a terminal bradycardia ≥ 10 min requiring expedited delivery, and the cumulative incidence function (CIF) for MA according with the duration of bradycardia stratified in 10-12 min and > 12 min. METHODS: Singleton pregnancies experiencing terminal fetal bradycardia requiring expedited delivery in the 2STG at 38 + 0-41 + 3 weeks and delivering in the year 2019, were identified. The presence of MA (pH < 7 and/or BE ≤ - 12 mmol/L) was determined based on the acid-base status in the umbilical artery cord blood. Survival analysis was used to assess the hazard function (HF) and the cumulative incidence function (CIF) for MA occurring after terminal fetal bradycardia, at the 2STG. RESULTS: Out of a non-consecutive population of 12,331 pregnancies, there were 52 cases that fit the inclusion criteria. Twenty-four (46.2%) of those develop MA. Abnormal quantitative pH values and the HF for MA correlated with the duration of 2STG at the time of bradycardia onset, but not with bradycardia duration. After 60 min of duration of 2STG, the HF (or instantaneous rate of failure) increased dramatically (from 1.2 to 20 about at 120 min). At paired duration of 2STG, a higher CIF was observed for the terminal bradycardia > 12 min. CONCLUSION: Forty-six percent of term fetuses with terminal bradycardia had MA at birth. Despite the low sensitivity and a non-significant association with quantitative pH values, the duration of terminal bradycardia in the 2STG is associated with a higher CIF for MA.

Hazard and cumulative incidence of umbilical cord metabolic acidemia at birth in fetuses experiencing the second stage of labor and pathologic intrapartum fetal heart rate requiring expedited delivery.

PURPOSE: The aim of the study was to determine the cause-specific hazard (CSH) and the cumulative incidence function (CIF) for umbilical cord metabolic acidemia at birth (MA; pH < 7.0 and/or BE [Formula: see text] - 12 mmol/L) at delivery in patients experiencing the 2nd stage of labor (2STG), stratified for both FIGO-2015 pathologic intrapartum cardiotocography requiring expedited delivery (CTG_RED) and duration of 2nd stage of labor. METHODS: 3459 pregnancies experiencing the 2nd stage of labor and delivering at the Division of Obstetrics and Prenatal Medicine, IRCCS Sant'Orsola-Malpighi Hospital, Bologna (Italy), were identified between 2018 and 2019. Survival analysis was used to assess CSH and CIF for MA, stratified for FIGO-2015 pathologic CTG and relevant covariates. RESULTS: FIGO-2015 pathological CTG with expedited operative delivery or urgent cesarean section within 10 or 20 min from diagnosis, respectively occurred in 282/3459 (8.20%). The rate of MA at delivery was 3.32% (115/3459). The spline of CSH for MA showed a direct correlation with the duration of 2STG always presenting higher values and greater slope in the presence of pathologic CTG, with plateau between 60 and 120 min and rapid increase after 120 min. The CIF at 180 min in the 2STG was 2.67% for nonpathological and 10.63% for pathological CTG_RED. Nulliparity, pathological CTG, and meconium-stained amniotic fluid resulted significant predictors of MA in our multivariable model. CONCLUSION: The risk for MA increases moderately across the 2STG with nonpathological CTG and quadruples with pathological CTG_RED. Adjustment for other predictors of MA including meconium-stained amniotic fluid and nulliparity reveals a significant hazard increase for MA associated with pathologic CTG_RED.

Recent Advances in the Diagnosis and Management of Congenital Heart Defects.

The prenatal assessment of congenital heart defects (CHD) and related fetal and maternal management is very challenging and delicate [...].

Epigenetics Beyond Fetal Growth Restriction: A Comprehensive Overview.

Fetal growth restriction is a pathological condition occurring when the fetus does not reach the genetically determined growth potential. The etiology of fetal growth restriction is expected to be multifactorial and include fetal, maternal, and placental factors, the latter being the most frequent cause of isolated fetal growth restriction. Severe fetal growth restriction has been related to both an increased risk of perinatal morbidity and mortality, and also a greater susceptibility to developing diseases (especially cardio-metabolic and neurological disorders) later in life. In the last decade, emerging evidence has supported the hypothesis of the Developmental Origin of Health and Disease, which states that individual developmental 'programming' takes place via a delicate fine tuning of fetal genetic and epigenetic marks in response to a large variety of 'stressor' exposures during pregnancy. As the placenta is the maternal-fetal interface, it has a crucial role in fetal programming, such that any perturbation altering placental function interferes with both in-utero fetal growth and also with the adult life phenotype. Several epigenetic mechanisms have been highlighted in modulating the dynamic placental epigenome, including alterations in DNA methylation status, post-translational modification of histones, and non-coding RNAs. This review aims to provide a comprehensive and critical overview of the available literature on the epigenetic background of fetal growth restriction. A targeted research strategy was performed using PubMed, MEDLINE, Embase, and The Cochrane Library up to January 2022. A detailed and fully referenced synthesis of available literature following the Scale for the Assessment of Narrative Review Articles guidelines is provided. A variety of epigenetic marks predominantly interfering with placental development, function, and metabolism were found to be potentially associated with fetal growth restriction. Available evidence on the role of environmental exposures in shaping the placental epigenome and the fetal phenotype were also critically discussed. Because of the highly dynamic crosstalk between epigenetic mechanisms and the extra level of complexity in interpreting the final placental transcriptome, a full comprehension of these phenomenon is still lacking and advances in multi-omics approaches are urgently needed. Elucidating the role of epigenetics in the developmental origins of health and disease represents a new challenge for the coming years, with the goal of providing early interventions and prevention strategies and, hopefully, new treatment opportunities.

Endometriosis and Impaired Placentation: A Prospective Cohort Study Comparing Uterine Arteries Doppler Pulsatility Index in Pregnancies of Patients with and without Moderate-Severe Disease.

The aim of this study was to evaluate if moderate-severe endometriosis impairs uterine arteries pulsatility index (UtA-PI) during pregnancy when compared to unaffected controls. In this prospective cohort study, pregnant women with stage III-IV endometriosis according to the revised American Fertility Society (r-AFS) classification were matched for body mass index and parity in a 1:2 ratio with unaffected controls. UtA-PIs were assessed at 11-14, 19-22 and 26-34 weeks of gestation following major reference guidelines. A General Linear Model (GLM) was implemented to evaluate the association between endometriosis and UtA-PI Z-scores. Significantly higher third trimester UtA-PI Z-scores were observed in patients with r-AFS stage III-IV endometriosis when compared to controls (p = 0.024). In the GLM, endometriosis (p = 0.026) and maternal age (p = 0.007) were associated with increased third trimester UtA-PI Z-scores, whereas conception by in-vitro fertilization with frozen-thawed embryo transfer significantly decreased UtA-PI measures (p = 0.011). According to these results, r-AFS stage III-IV endometriosis is associated with a clinically measurable impaired late placental perfusion. Closer follow-up may be recommended in pregnant patients affected by moderate-severe endometriosis in order to attempt prediction and prevention of adverse pregnancy and perinatal outcomes due to a defective late placental perfusion.

Prenatal Diagnosis and Postnatal Outcomes of Left Brachiocephalic Vein Abnormalities: Systematic Review.

Abnormalities of the left brachiocephalic vein (LBCVA) are rare and poorly studied prenatally. An association with congenital heart defects (CHD), extracardiac and genetic abnormalities was described. The aim of our study was to estimate the rate and summarize the available evidence concerning prenatal diagnosis, associated anomalies, and outcomes of these anomalies. A systematic literature review was carried out selecting studies reporting on prenatal diagnosis of LBCVA, including unpublished cases from our experience. Frequencies were pooled from cohort studies to calculate prenatal incidence. Pooled proportions were obtained from all the studies including rates of associated CHD, extracardiac or genetic abnormalities and neonatal outcomes. The search resulted in the selection of 16 studies with 311 cases of LBCVA, with an incidence of 0.4% from six cohort studies. CHD occurred in 235/311 (75.6%) fetuses: 23 (7.4%) were major in cases of double, retroesophageal or subaortic course and 212 (68.2%) were minor in cases of absence (always associated with a persistent left superior vena cava) or intrathymic course. Data on other associated outcomes were scarce showing rare extracardiac anomalies (3.5%), rare genetic abnormalities (RASopathies and microdeletions associated with the retroesophageal course), and neonatal outcomes favorable in most cases, particularly in intrathymic forms.