Background and Objective: Assessment of operative vaginal delivery feasibility remains partly subjective despite the availability of intrapartum ultrasound parameters. The study aims to provide an objective "Delivery Color Code" (Green, Yellow, Red) based on automated evaluation of ultrasound images to assist clinicians in predicting the feasibility of OVD.Methods: Single-centre prospective study conducted on women in the second stage of labor having an indication for operative delivery. Upon enrolment, transperineal ultrasound images were acquired on the axial plane to document three sonographic predictors of the outcome of OVD, namely the position of the fetal occiput, the head-perineum distance (HPD) and the midline angle (MLA). The methodology integrates three distinct automatic algorithms for the real-time extraction of such ultrasound parameters, which are processed through a five-layer Adaptive Neuro-Fuzzy Inference System (ANFIS) architecture that combines the learning capabilities of neural networks with the transparency of fuzzy logic aiming to predict the outcome of OVD as follows: green – high chance of successful and easy OVD; yellow – high chance of challenging OVD; red – high chance of failed or unfeasible instrumental delivery. The study analyzed a dataset of 265 patients (164 "Green" cases, 80 "Yellow" cases, and 21 “Red” cases) for system training, while validation was performed on a balanced cohort of 63 cases.Results: The model achieved a macro-average accuracy of 88.9% on the validation test set. The system demonstrated high discriminative reliability at the risk extremes, yielding a sensitivity of 0.905 for both "Success" (Green) and "Failure" (Red) outcomes. Notably, the "Red" risk category achieved a precision of 0.950 and a specificity of 0.976, effectively eliminating critical misclassifications between safe and high-risk scenarios. Errors were primarily confined to the "Borderline" (Yellow) transition zone, where the model maintained a conservative safety bias.Conclusions: The automated diagnostic pipeline offers a robust, Explainable AI (XAI) framework for decision making when delivery is to be expedited in the second stage of labor. By providing objective metrics for fetal station and position, the system may assist clinicians on how to perform fetal extraction in the second stage of labor aiming to reduce maternal-fetal morbidity associated with failed OVD.

BACKGROUND:Early skeletal growth represents a critical window for lifelong bone health and is influenced by genetic, nutritional, and environmental factors. However, the assessment of bone status during infancy remains challenging due to the limited feasibility of reference densitometric techniques for longitudinal use. Radiofrequency echographic multi-spectrometry (REMS) is an ultrasound-based technology validated for bone mineral density (BMD) assessment in adults, but its applicability to early infancy has not yet been established. This study aimed to explore a REMS-based approach for investigating femoral skeletal growth during early life. METHODS:Eighty-two healthy term infants underwent femoral REMS examinations at 3 and 6 months of age. Unfiltered radiofrequency ultrasound signals were analyzed using a multivariate framework combining fast Fourier transform (FFT) spectral analysis with partial least squares (PLS) regression. Body weight was used as an indirect surrogate marker of skeletal growth, with spectral features serving as predictors. RESULTS:Average power spectra stratified according to PLS-inferred body weight demonstrated distinct spectral patterns between lower- and higher-weight infants. The PLS-based spectral model showed longitudinal consistency, preserving relative skeletal status across time points. These findings indicate that REMS-derived spectral features vary systematically with growth-related physiological changes during infancy. CONCLUSIONS:REMS-derived spectral characteristics appear to be sensitive to early skeletal growth processes in infancy. Although further studies incorporating direct bone outcomes are required to disentangle the relative contributions of body size and mineralization, this work provides foundational evidence supporting the feasibility of extending REMS technology to early life. REMS may represent a promising non-invasive and radiation-free approach for longitudinal investigation of skeletal development in pediatric populations.

BACKGROUND:The potential preventive effect of mediolateral and lateral episiotomy on the risk of anal sphincter injury related to vacuum delivery in nullipara has been reported by different well-designed studies in the last years. OBJECTIVES:The aim of this systematic review and meta-analysis is to summarize the available evidence on the protective effect of mediolateral or lateral episiotomy towards the occurrence of obstetric anal sphincter injury (OASI) in nulliparous women who were submitted to vacuum-assisted delivery. SEARCH STRATEGY:PubMed, Embase, CINAHL, Cochrane Library and Scopus databases were retrospectively searched without any temporal restriction up to March 1st 2025. SELECTION CRITERIA:Randomized controlled trials, retrospective, prospective case-control or cohort studies investigating the incidence of perineal tears involving anal sphincter muscles and/or rectal mucosa after vacuum-assisted birth with and without mediolateral/lateral episiotomy in nulliparous women were included. DATA COLLECTION AND ANALYSIS:Risk of bias assessment was conducted for each included study by applying ROB2 score for RCTs and ROBINS-I score for non-randomized studies. Data were extracted and analyzed with Review Manager 5.4.1, results were reported by means of pooled Odd-ratios (ORs) and presented as Forest plots. MAIN RESULTS:31 studies (3 RCTs and 28 non-randomized studies) were included. Cumulative sample size consisted in 608,359 nulliparous women who were submitted to vacuum-assisted delivery. Mediolateral/lateral episiotomy was found to halve the incidence of OASI (OR 0.56 [95 % CI 0.42-0.73]) with high between-study heterogeneity reported (I2 = 99 %). At sensitivity analysis, a significant reduction in OASI incidence in case of mediolateral/lateral episiotomy was confirmed (OR 0.58 [95 %CI 0.44-0.78]); this analysis was conducted on low/moderate risk of bias studies (1RCT e 5 non-randomized studies, 15,799 patients) and associated with low heterogeneity (I2 = 42 %). CONCLUSIONS:This updated meta-analysis on the role of mediolateral/lateral episiotomy in nulliparous women submitted to vacuum assisted delivery confirms its protective role from OASI.

INTRODUCTION:Acute fatty liver of pregnancy (AFLP) is a rare but potentially life-threatening obstetric condition characterized by maternal hepatic dysfunction and risk of rapid clinical deterioration. In this setting, fetal hypoxia may develop through multiple mechanisms, including maternal metabolic acidosis, hypovolemia, and placental fatty acid accumulation. These factors may impair oxygen transfer, partly through alterations in the Bohr-Haldane effect, ultimately compromising fetal oxygenation. CASE PRESENTATION:We report a case of AFLP complicated by fetal heart rate abnormalities in the context of maternal hepatic failure. The clinical course was characterized by progressive maternal metabolic derangement and signs of fetal compromise. The observed fetal heart rate anomalies were interpreted in light of impaired maternal-fetal oxygen exchange, likely related to a combination of metabolic acidosis and reduced placental perfusion. CONCLUSION:This report highlights the pathophysiological mechanisms underlying fetal heart rate abnormalities in AFLP, emphasizing the role of maternal metabolic acidosis and placental hypoperfusion in the development of fetal hypoxia. Greater awareness of these mechanisms may facilitate earlier recognition and timely management of fetal compromise in this rare but critical condition.

Yawning is a phylogenetically preserved and highly stereotyped behavior observed across vertebrates.1 In humans, it emerges early in development, as it is already present prenatally.2,3 Qualitative studies show that fetal yawns display a structured motor pattern closely resembling adult yawns, suggesting a role in early sensorimotor organization,4,5 and they have been proposed to support the maturation of brainstem central pattern generators and early synaptic development.6,7 Due to its early emergence in development, prenatal yawning has largely been interpreted as driven by endogenous programs, whereas in postnatal life, yawning can also be shaped by the social context through contagion, a phenomenon linked to sensorimotor mirroring and affective attunement.8,9 Here, we tested whether prenatal yawning may also be modulated by maternal behavior. Using ultrasound recordings of fetal facial activity combined with controlled elicitation of maternal yawning, we show that fetal yawning selectively increases following maternal yawns but not during non-contagious control conditions. Temporal analyses reveal structured coordination between maternal and fetal yawning, and machine-learning classification identifies shared kinematic signatures across maternal and fetal yawns. These findings suggest that fetal yawning might also be embedded within a dyadic sensorimotor context in which maternal behavior shapes fetal expression, suggesting that forms of behavioral resonance and embodied alignment precede birth and contribute to the early foundations of social attunement.

The study aims to provide a comprehensive overview of the sociodemographic and lifestyle characteristics, as well as dietary habits, of Italian pregnant women. It also investigates their adherence to Italian food-based dietary guidelines (FBDGs), and factors associated with high adherence. An online survey was administered to a representative sample of Italian pregnant women. Data collection included sociodemographic, pregnancy-related and lifestyle information, such as use of supplements and physical activity (IPAQ-SF). Dietary habits and adherence to Italian dietary guidelines were assessed using the Adherence to Italian Dietary Guidelines Indicator (AIDGI). Non-parametric tests and logistic regression analyses were performed. A total of 589 participants completed the survey. More than half of the sample showed low adherence to the Italian dietary guidelines with an overall median AIDGI score of 18.0 (IQR: 15.0–23.0). Among the factors associated with high adherence, higher maternal age and the use of folic acid supplements during pregnancy were positively related. Conversely, having had a previous pregnancy, along with other sociodemographic and lifestyle factors, was negatively associated with adherence. Determinants of high adherence to Italian FBDGs in pregnant women include maternal age, employment status, parity, smoking habits and supplement use. These findings may inform national policies and public health interventions addressing sociodemographic and lifestyle determinants to improve maternal nutrition and the well-being of both the mother and child.

Purpose To develop a deep learning algorithm to automatically assess the posterior fossa on first-trimester US screening scans and identify open spina bifida (OSB) and cystic posterior fossa (CPF) anomalies. Materials and Methods This was the retrospective part of an international study involving 10 fetal medicine centers. Normal and abnormal (OSB, CPF anomaly) midsagittal fetal brain US images acquired between 11 and 14 weeks of gestation (July 2009-January 2024) with confirmed diagnosis at follow-up were evaluated. Images were manually annotated to delineate the posterior fossa. The dataset was split into a training/validation set (70%) and internal test set (30%). Three convolutional neural networks were trained via threefold cross-validation on the training/validation set, with predictions on the internal test set obtained by ensemble averaging across folds. Model performance in detecting OSB and CPF anomalies was evaluated for the whole cohort and for fetuses with OSB or CPF anomalies separately. Results Images from 251 fetuses were analyzed (mean gestational age [±SD], 12.7 weeks ± 0.65; 150 normal and 101 abnormal [43 OSB and 58 CPF anomalies] images). On the internal test, the MobileNetV3 Large Weights achieved the best performance: area under the receiver operating characteristic curve, 0.94 (95% CI: 0.88, 0.99); accuracy, 88% (67 of 76); recall, 81% (25 of 31); specificity, 93% (42 of 45); precision, 89% (25 of 28); negative predictive value, 88% (42 of 48); and F1 score, 0.85. OSB was classified more accurately (93% [52 of 56] vs 88% [57 of 65]; P = .38) and with higher recall (91% [10 of 11] vs 75% [15 of 20]), although the difference was not significant (P = .38). Conclusion MobileNetV3 Large Weights accurately assessed the fetal posterior fossa between 11 and 14 weeks of gestation, distinguishing normal images from those showing OSB or CPF anomalies. Clinical trial registration no. NCT0579047 Keywords: Artificial Intelligence, First Trimester Ultrasound Screening, Fetal Brain Anomalies, Deep Learning Supplemental material is available for this article. © RSNA, 2026 See also commentary by Rafful in this issue.

BACKGROUND:To report the implementation across Fetal Medicine units and the agreement between first and second trimester referral scans in the identification of fetal anomalies in cases referred for the expert assessment of the fetal anatomy in the first trimester following the publication of the national guidelines in Italy. METHODS:This multicenter, retrospective study aimed to evaluate the implementation and diagnostic performance of first-trimester referral ultrasound (US) in identifying fetal anomalies, following the introduction of national guidelines in Italy. The analysis included singleton pregnancies referred to nine specialized Fetal Medicine centers between 11+0 and 13+6 weeks' gestation due to increased risk for structural anomalies. Risk was defined as either a nuchal translucency (NT) measurement ≥ 3.5 mm or suspicion of a structural anomaly at initial screening. Only cases undergoing referral US within the specified gestational window were included. Diagnostic accuracy was assessed by comparing findings from first-trimester referral US with those from follow-up referral US performed either at 14-16 weeks or at 19-21 weeks. RESULTS:Out of 344 referred cases, 322 (93.6%) underwent first-trimester referral US within the appropriate timeframe. After excluding miscarriages and terminations, 136 cases were evaluated again at 19-21 weeks and 207 at 14-16 weeks. The agreement between the 11+0-13+6 week and 19-21 week scans was 85.3%, with a sensitivity of 82.0%, specificity of 88.0%, positive predictive value (PPV) of 84.7%, and negative predictive value (NPV) of 85.7%. Agreement between the early and 14-16 week scans was 91.3%, with sensitivity, specificity, PPV, and NPV of 90.7%, 92.1%, 93.9%, and 88.2%, respectively. CONCLUSION:The study demonstrates successful implementation of national first-trimester referral US guidelines in Italy. When performed by experienced operators using a standardized protocol, first-trimester anatomy assessment is feasible and provides high diagnostic accuracy, enabling early detection of structural fetal anomalies.

The efficacy of cervical cerclage (CC) in cases of asymptomatic mid-trimester short cervix, or the ultrasound finding of a cervical length<25 mm within 24 weeks of gestation, has been documented in women with a previous history of preterm birth (PTB). Conversely, no robust evidence supports the role of cervical cerclage in prolonging pregnancy and improving maternal-neonatal outcomes in pregnant patients with mid-trimester short cervix detected by sonography and no prior history of PTB. However, the limited effect of CC in this population may be partially explained by the lack of preprocedure diagnosis of underlying intra-amniotic inflammation/infection that could undermine the beneficial effect of mechanical continence exerted by cervical cerclage. Performing an amniocentesis in cases of mid-trimester short cervix and analyzing the amniotic fluid for inflammatory markers, including IL-6 and MMP-8 and the presence of pathogens in the amniotic cavity by standard culture techniques, digital polymerase chain reaction, or, more recently, third-generation sequencing techniques may offer the opportunity for a differential diagnosis between mechanical and inflammatory cervical insufficiency. In this review, we explore the available literature on intra-amniotic inflammation/infection in mid-trimester short cervix and discuss the potential role of analyzing amniotic fluid by amniocentesis before cervical cerclage to improve the selection of patients who may benefit from cerclage or alternative management strategies, including antibiotics in selected cases of intra-amniotic inflammation/infection. An individualized approach to maternal-fetal care in this context may represent a promising strategy for addressing cervical insufficiency and potentially improving the efficacy of therapeutic options to prevent PTB. VIDEO ABSTRACT.

The beneficial effects of Mediterranean Diet (MD) during pregnancy are well established. However, validated tools adapted to assess adherence to the MD during pregnancy and across different cultural contexts remain limited. This study aimed to translate, cross-culturally adapt, and validate an Italian version of the pregnancy-adapted Mediterranean Diet Adherence Screener (ITpreg-MEDAS), derived from the original Spanish preg-MEDAS questionnaire. We hypothesized that the ITpreg-MEDAS would show adequate construct validity and would be associated with markers of diet quality during pregnancy. The preg-MEDAS is a 17-item questionnaire designed to assess adherence to the MD among pregnant women. The Italian version was developed following a six steps process in accordance with established methodological guidelines: forward translation, synthesis I, blind-back translation, synthesis II, pre-testing, and validation. Psychometric properties were evaluated by assessing internal consistency, test-retest reliability, and construct validity, in a sample of Italian pregnant women. The preg-MEDAS was translated and cross-cultural adapted, requiring some semantic revisions. All 25 Italian pregnant women involved in the pre-testing in pre-testing found it clear and comprehensible. A total of 116 Italian pregnant women participated in the validation phase, with a mean ITpreg-MEDAS score of 7.2 ± 2.5 out of 17, indicating medium adherence to the MD. Reliability was confirmed by good test-retest correlation (r = 0.756) and acceptable internal consistency (Cronbach’s α = 0.623). The ITpreg-MEDAS is a reliable and valid Italian version of the preg-MEDAS questionnaire, providing a simple tool to assess adherence to the Mediterranean Diet during pregnancy in both clinical practice and research.

Purpose To develop and validate an anatomy-aware, two-stage, end-to-end deep learning pipeline for fetal brain abnormality automated detection on standardized second-trimester brain US images. Materials and Methods This retrospective multicenter study included 319 fetal brain images (218 normal, 101 abnormal) between 19 weeks ± 0 and 23 weeks ± 6 of gestation from nine international fetal medicine centers, each with paired standard transventricular and transcerebellar axial plane images acquired at second-trimester US between January 2010 and December 2022. Abnormalities were confirmed by neonatal imaging or autopsy. Images were annotated for six key brain regions by two experienced fetal medicine specialists. An anatomy-aware, two-stage deep learning pipeline was developed, consisting of a You Only Look Once version 5-based object detector followed by a classification network using a Mini-ResNet feature extractor within a HexaNet architecture. The pipeline classified each image as normal or abnormal. Object detection performance was evaluated using mean average precision at an intersection-over-union threshold of 0.5 (mAP@0.5). Classification performance was assessed using the area under the receiver operating characteristic curve, sensitivity, specificity, and F1 score. Results The object detection model achieved a mAP@0.5 of 0.93 (95% CI: 0.90, 0.96) on the test dataset. The classification model achieved an area under the receiver operating characteristic curve of 0.96 (95% CI: 0.90, 1.00), a sensitivity of 87% (95% CI: 67, 100 [13 of 15]), a specificity of 91% (95% CI: 79, 100 [29 of 32]), and an F1 score of 0.84 (95% CI: 0.67, 0.96) for distinguishing normal from abnormal fetal brain images. Conclusion The developed model achieved high diagnostic performance for the detection of brain anomalies at routine fetal second-trimester US. Keywords: Artificial Intelligence, Machine Learning, Fetal Neurology, Neurosonography, Fetal Brain Malformation, YOLOv5, Neural Networks Supplemental material is available for this article. © RSNA, 2026 See also commentary by Rafful in this issue.

Multisensory integration is a fundamental principle of brain function, yet its prenatal origins remain largely unknown. Using Doppler ultrasonography in 58 uncomplicated singleton pregnancies (28–32 weeks of gestation), we examined fetal cerebrovascular responses to unimodal visual, unimodal vibrotactile, and bimodal visuo-vibrotactile stimulation across the anterior, middle, and posterior cerebral arteries. Visuo-vibrotactile stimulation did not elicit a uniform response: it selectively reduced pulsatility index in the PCA while increasing it in the ACA, with MCA responses remaining close to baseline. This anterior-posterior dissociation was confirmed by a significantly negative PCA-ACA shift index and reproduced by end-diastolic velocity changes with the expected opposite sign. Multisensory benchmark analyses revealed an artery-specific profile consistent with selective non-additive modulation rather than nonspecific paired-stimulation effects, while fetal heart rate remained stable across conditions. The convergence of hemodynamic measures and the absence of cardiac or baseline differences suggest a genuine cerebrovascular response rather than generalized arousal. These findings reveal that convergent sensory input can shape fetal cerebral hemodynamics in utero, identifying a rudimentary but spatially organized form of prenatal cross-modal sensitivity and suggesting that the foundations of multisensory integration begin to emerge before birth.

BACKGROUND:Levator ani muscle (LAM) coactivation consists in the inappropriate contraction - i.e. shortening - of the LAM during pushing effort. The condition is reported to occur in up to 30% of pregnant women prior to active labor, and has been associated with increased duration of the second stage in the context of the so-called soft tissue dystocia. OBJECTIVE:This study aimed to evaluate the correlation between levator ani muscle coactivation and labor outcome in a cohort of nulliparous women with singleton pregnancy at term. STUDY DESIGN:This was a single-center prospective observational study that included nulliparous women with low-risk term pregnancy with a cephalic-presenting fetus who were enrolled between 39 and 40 weeks of gestation. During routine term obstetrical assessment, trained midwives performed transperineal ultrasound on the midsagittal plane to evaluate the anteroposterior diameter of the levator ani muscle. The minimal distance between the posteroinferior border of the pubic symphysis and the anterior border of the puborectalis muscle was evaluated at rest and at the acme of a pushing effort. Levator ani muscle coactivation was defined as a reduction in the anteroposterior diameter of the levator hiatus during the pushing efforts. The primary outcome was to compare the duration of the second stage of labor between coactivating and noncoactivating women and evaluate the occurrence of composite adverse labor outcome as defined by the occurrence of any of the following conditions: episiotomy, vacuum or cesarean delivery for second-stage dystocia, obstetrical anal sphincter injury, or severe postpartum hemorrhage. RESULTS:A total of 201 women were included, of whom 42 (20.9%) had levator ani muscle coactivation. Compared with women without levator ani muscle coactivation, those with levator ani muscle coactivation showed longer active second stage of labor duration (64±45 minutes vs 84±50, respectively; P=.02) and higher rates of composite adverse labor outcome (12.5% vs 31.0%, respectively; P<.01) and obstetrical anal sphincter injury (5.4% vs 0.0%, respectively; P<.01). Levator ani muscle coactivation only was associated with composite adverse labor outcomes (34.3% in women with levator ani muscle coactivation vs 18.1% in those without levator ani muscle coactivation; P<.01). CONCLUSION:Within a population of women with singleton term pregnancies at low risk, the antepartum demonstration of levator ani muscle coactivation at transperineal ultrasound was associated with an increased duration of the second stage of labor and a higher frequency of composite adverse labor outcomes, including obstetrical anal sphincter injury. VIDEO ABSTRACT.

Background/Objectives: This study aimed to compare the visualization rates of fetal anatomical structures with standard 2D ultrasound examination versus a single 3D volume acquired during the first trimester. Methods: This multicenter prospective study was performed in nine tertiary referral centers, by experienced sonographers. A standard protocol was adopted in both 2D and 3D modalities to assess the 17 anatomical structures listed in the national and international guidelines. The included cases were non-anomalous fetuses from women booked for combined screening test between 11 + 0 and 13 + 6 weeks. Results: Two hundred and thirty-nine women were included in the study. The mean gestational age at ultrasound examination was 12 weeks ± 5 days (±5.4 SD). All the 17 structures were seen in 155/239 fetuses (64.85%) at 2D evaluation and in 84/239 (35.15%) at 3D evaluation (p = 0.001). Comparing 2D and 3D visualization, the following anatomical structures showed a statistical difference: posterior fossa (92% vs. 74%, p < 0.005); neck (94.2% vs. 87.2%, p < 0.001); orbits (93% vs. 85.6%, p < 0.001); nasal bone (93% vs. 88.8%, p = 0.016); lung fields (99.5% vs 96.7%, p = 0.046); cardiac axis (99.5% vs. 83.9%; p < 0.001); bladder (97.5% vs. 91.7%, p < 0.001); abdominal wall (98.7% vs. 94.2%, p < 0.001). For the other anatomical portion, no statistically significant differences were found. Conclusions: Our study demonstrates that a full assessment of fetal anatomy is best performed using 2D ultrasound, while 3D ultrasound showed lower overall visualization rates, with comparable performance for selected structures, suggesting a potential supplementary use in specific clinical contexts.

Objective: To compare the sonographic measurement of the umbilical cord between women with or without repetitive decelerations during the first stage of labor. Study design: Prospective study including a non-consecutive cohort of women at term gestation carrying a normal sized fetus at term in cephalic presentation. The cross-sectional area of the umbilical cord, of its vessels and the amount of the Wharton's jelly were assessed at 2D ultrasound upon labor admission. The CTG traces recorded in labor were retrospectively evaluated and the biometric parameters of the umbilical cord were compared between women with or without repetitive decelerations during the first stage and their correlation with the total deceleration area/total length (stage I TDA/t) of the first stage of labor (overall and following the rupture of membrane) was assessed. Results: Overall, 113 women were included, of whom 21 (18.6 %) presented repetitive decelerations during the first stage of labor. In this latter group, the umbilical cord showed a significantly smaller total arterial area (24.4 +/- 10.7 vs. 19.6 +/- 9.0 mm(2); p = 0.02), vein area (46.8 +/- 13.6 vs. 34.1 +/- 13.3 mm(2); p < 0.001) as well Wharton's Jelly (WJ) area (122.7 +/- 32.1 vs. 79.3 +/- 11.1 mm(2); p < 0.001) compared with fetuses with a normal CTG. At logistic regression analysis the WJ area was associated with the occurrence of repetitive decelerations during the first stage of labor (p < 0.001). The I stage TDA/t overall and after the rupture of membranes was found to be negatively correlated with the WJA (Spearman's coefficient -0.40; p < 0.001 and -0.45; p < 0.001 respectively). Conclusion: In normal sized infants a reduced umbilical cord thickness is associated with an increased occurrence of repetitive decelerations during the first stage of labor. The severity of these decelerations is negatively correlated to the amount of WJ.