Artificial intelligence (AI) has gained prominence in medical imaging, particularly in obstetrics and gynecology (OB/GYN), where ultrasound (US) is the preferred method. It is considered cost effective and easily accessible but is time consuming and hindered by the need for specialized training. To overcome these limitations, AI models have been proposed for automated plane acquisition, anatomical measurements, and pathology detection. This study aims to overview recent literature on AI applications in OB/GYN US imaging, highlighting their benefits and limitations. For the methodology, a systematic literature search was performed in the PubMed and Cochrane Library databases. Matching abstracts were screened based on the PICOS (Participants, Intervention or Exposure, Comparison, Outcome, Study type) scheme. Articles with full text copies were distributed to the sections of OB/GYN and their research topics. As a result, this review includes 189 articles published from 1994 to 2023. Among these, 148 focus on obstetrics and 41 on gynecology. AI-assisted US applications span fetal biometry, echocardiography, or neurosonography, as well as the identification of adnexal and breast masses, and assessment of the endometrium and pelvic floor. To conclude, the applications for AI-assisted US in OB/GYN are abundant, especially in the subspecialty of obstetrics. However, while most studies focus on common application fields such as fetal biometry, this review outlines emerging and still experimental fields to promote further research.

Despite a large number of studies previously conducted on educational concepts of ultrasound teaching in medical school, various controversial issues remain. Currently, recommendations for ultrasound curricula that aim to standardize ultrasound teaching are frequently based on expert panel advice instead of relying on valid evidence-based literature. In December 2022, a systematic literature review on the subject of undergraduate ultrasound education was conducted. All ultrasound studies listed in the PubMed and Google Scholar medical databases were filtered and analyzed with respect to various aspects of their methodological conduct and curricular implementation. A total of 259 publications were considered in the data synthesis, including 145 teaching studies in the field of undergraduate ultrasound education. The latter encompassed 58 (40%) studies that did not compare their ultrasound training to a control group. Furthermore, 84 (58%) of these studies did not assess knowledge prior to the applied ultrasound training, neglecting this factor’s potential influence on study outcomes. Despite a great interest in the development and further implementation of ultrasound education during medical school, this process is still compromised by significant deficiencies in studies that have been conducted in the past. In order to provide a valid basis for curricular decisions, teaching studies should fulfill essential methodological requirements despite the multifactorial framework in which they are conducted. In the future, a guide for the design of ultrasound studies could be a useful aid for ultrasound enthusiasts and promote scientific knowledge gain.

Purpose: The objective was to evaluate the feasibility of vesicoamniotic shunting (VAS) in the first trimester with the Somatex^® intrauterine shunt and report on complications and neonatal outcome. Methods: Retrospective cohort study of all VAS before 14 weeks at two tertiary fetal medicine centres from 2015 to 2018 using a Somatex^® intrauterine shunt. All patients with a first trimester diagnosis of megacystis in male fetuses with a longitudinal bladder diameter of at least 15 mm were offered VAS. All patients that opted for VAS after counselling by prenatal medicine specialists, neonatologists and pediatric nephrologists were included in the study. Charts were reviewed for complications, obstetric and neonatal outcomes. Results: Ten VAS were performed during the study period in male fetuses at a median GA of 13.3 (12.6–13.9) weeks. There were two terminations of pregnancy (TOP) due to additional malformations and one IUFD. Overall there were four shunt dislocations (40%); three of those between 25–30 weeks GA. Seven neonates were born alive at a median GA of 35.1 weeks (31.0–38.9). There was one neonatal death due to pulmonary hypoplasia. Neonatal kidney function was normal in the six neonates surviving the neonatal period. After exclusion of TOP, perinatal survival was 75%, and 85.7% if only live-born children were considered. Conclusion: VAS in the first trimester is feasible with the Somatex^® Intrauterine shunt with low fetal and maternal complication rates. Neonatal survival rates are high due to a reduction in pulmonary hypoplasia and the rate of renal failure at birth is very low. VAS can be safely offered from the late first trimester using the Somatex^® intrauterine shunt.

Point-of-care ultrasound (POCUS) integration into neonatology offers transformative potential for diagnostics and treatment, enhancing immediacy and precision of clinical decision-making in this vulnerable patient population. This systematic review aims to synthesize evidence on POCUS applications, benefits, challenges, and educational strategies in neonatology. Literature search was conducted using SPIDER scheme keywords and MeSH terms related to POCUS and neonatology. Studies focusing on POCUS applications, its impact on clinical outcomes, and educational interventions for skill acquisition were included and analyzed using standardized tools, followed by a narrative synthesis of the findings. The search yielded 68 relevant publications, encompassing original research, reviews, and guidelines. POCUS applications varied across cardiovascular, pulmonary, neurological, and abdominal assessments. Key benefits included a reduced need for invasive procedures and rapid bedside diagnosis. Challenges included steep learning curves for clinicians and the need for standardized training and guidelines. Educational strategies highlighted the effectiveness of simulation-based training in enhancing ultrasound proficiency among neonatal care providers. POCUS represents a significant advancement in neonatal medicine, offering benefits for patient care. Addressing identified challenges through comprehensive training programs and developing standardized guidelines is crucial for optimized use. Future research should focus on evaluating educational outcomes and long-term impacts of POCUS integration into neonatal care.

To apply Doppler US (DUS)-gated fetal cardiac cine MRI in clinical routine and investigate diagnostic performance in complex congenital heart disease (CHD) compared with that of fetal echocardiography. In this prospective study (May 2021 to March 2022), women with fetuses with CHD underwent fetal echocardiography and DUS-gated fetal cardiac MRI on the same day. For MRI, balanced steady-state free precession cine images were acquired in the axial and optional sagittal and/or coronal orientations. Overall image quality was assessed on a four-point Likert scale (from 1 = nondiagnostic to 4 = good image quality). The presence of abnormalities in 20 fetal cardiovascular features was independently assessed by using both modalities. The reference standard was postnatal examination results. Differences in sensitivities and specificities were determined by using a random-effects model. The study included 23 participants (mean age, 32 years ± 5 [SD]; mean gestational age, 36 weeks ± 1). Fetal cardiac MRI was completed in all participants. The median overall image quality of DUS-gated cine images was 3 (IQR, 2.5-4). In 21 of 23 participants (91%), underlying CHD was correctly assessed by using fetal cardiac MRI. In one case, the correct diagnosis was made by using MRI only (situs inversus and congenitally corrected transposition of the great arteries). Sensitivities (91.8% [95% CI: 85.7, 95.1] vs 93.6% [95% CI: 88.8, 96.2]; P = .53) and specificities (99.9% [95% CI: 99.2, 100] vs 99.9% [95% CI: 99.5, 100]; P > .99) for the detection of abnormal cardiovascular features were comparable between MRI and echocardiography, respectively. Using DUS-gated fetal cine cardiac MRI resulted in performance comparable with that of using fetal echocardiography for diagnosing complex fetal CHD.Keywords: Pediatrics, MR-Fetal (Fetal MRI), Cardiac, Heart, Congenital, Fetal Imaging, Cardiac MRI, Prenatal, Congenital Heart DiseaseClinical trial registration no. NCT05066399 Supplemental material is available for this article. © RSNA, 2023See also the commentary by Biko and Fogel in this issue.

(1) Background: The aim of this study was to compare perinatal outcomes and complication rates of vesicoamniotic shunting (VAS) before 17 + 0 weeks in isolated LUTO (lower urinary tract obstruction) with the Somatex^® intrauterine shunt vs. the Harrison fetal bladder shunt. (2) Methods: This is a retrospective cohort study in two tertiary fetal medicine centers. From 2004–2014, the Harrison fetal bladder shunt was used, and from late 2014–2017, the Somatex shunt. Obstetrics and pediatric charts were reviewed for complications, course of pregnancy, perinatal outcome, and postnatal renal function. (3) Results: Twenty-four fetuses underwent VAS with a Harrison (H) shunt and 33 fetuses with a Somatex (S) shunt. Live birth rates and survival to last follow-up were significantly higher in the Somatex group, at 84.8% and 81.8%, respectively, vs. 50% and 33.3% in the Harrison group (p = 0.007 and p < 0.001). The dislocation rate in the Somatex group (36.4%) was significantly lower than in the Harrison group (87.5%) (p < 0.001). The median time to dislocation was significantly different, at 20.6 days (H) vs. 73.9 days (S) (p = 0.002), as was gestational age at dislocation (17 (H) vs. 25 (S) weeks, p < 0.001). Renal function was normal in early childhood in 51% (S) vs. 29% (H) (p = 0.11). (4) Conclusions: VAS before 17 + 0 weeks gestational age with a Somatex shunt improves perinatal survival significantly and might even have a positive effect on renal function, probably due to the lower dislocation rates. A normal amount of amniotic fluid in the third trimester was the best predictor of normal renal function in early childhood.