Novices can attain mastery learning levels using simulation-based ultrasound training with less than, on average, 2 h of practice. However, we found large variations in the amount of training needed, which raises questions about the adequacy of current volume-based models for determining ultrasound competency.

In skilled clinical hands, internal hernia has a good prognosis in pregnant patients. Surgery may be performed subacutely or even electively, depending on the condition of patient and foetus, and straightforward clinical assessment is adequate, and imaging studies, e.g. CT, are not necessary.

The incidence of internal herniation during pregnancy was 1 % in our study. Internal herniation may be a serious complication in pregnant women, and both the diagnosis and treatment requires handling by experienced obstetrical, radiological, and surgical staff.

The performance of FAST examinations can be assessed in a simulated setting using defensible performance standards, which have both good reliability and validity.

Objective Exploring associations between antenatal detection of fetal growth restriction (FGR) and adverse outcome.

Objective To explore the effects of simulation‐based ultrasound training on the accuracy of fetal weight estimation in the third trimester among obstetricians with different levels of clinical experience. Methods This was a multicenter, randomized pre–post‐test practical trial conducted between March 2016 and January 2018. Obstetricians with different levels of clinical experience were randomized to either simulation‐based ultrasound training focusing on fetal weight scans or no intervention. Participants completed two scans in pregnant women at term to establish baseline accuracy of fetal weight estimation. Another two scans were performed at follow‐up. Accuracy was defined by the percentage difference between estimated fetal weight and actual birth weight. Ultrasound image quality was rated by two expert raters. Results Seventy participants with different levels of clinical experience completed the study. Adjusting for clinical experience, the intervention group demonstrated an improvement in measurement accuracy of 31.9% (95% CI, 6.9–50.1%) (P = 0.02), whereas the control group did not improve (relative difference, 13.1% (95% CI, −17.9 to 55.9%); P = 0.45). The change in accuracy was significantly different between the groups (P = 0.02) and independent of clinical experience (P = 0.54). Image‐quality scores improved by a mean of 1.2 (95% CI, 0.4–2.1) (P < 0.01) in the intervention group, with no change in the control group (mean difference, 0.1 (95% CI, −0.8 to 1.0); P = 0.78). There was a strong negative correlation between time spent using the simulator and clinical experience (r = −0.70, P = 0.0001). Conclusion Simulation‐based ultrasound training improved accuracy and image quality when performing fetal weight estimation in women at term, independent of obstetricians' clinical experience. Copyright © 2019 ISUOG. Published by John Wiley & Sons Ltd.

Orientation of the images bottom-up rather than top-down, led to a steeper learning curve, but had little or no impact on the subsequent transfer of skills.

The placenta is crucial to fetal well-being and it plays a significant role in the pathogenesis of hypertensive pregnancy disorders. Moreover, a timely diagnosis of placenta previa may save lives. Ultrasound is the primary imaging modality in pregnancy, but high-quality imaging depends on the access to equipment and staff, which is not possible in all settings. Convolutional neural networks may help standardize the acquisition of images for fetal diagnostics. Our aim was to develop a deep learning based model for classification and segmentation of the placenta in ultrasound images. We trained a model based on manual annotations of 7,500 ultrasound images to identify and segment the placenta. The model's performance was compared to annotations made by 25 clinicians (experts, trainees, midwives). The overall image classification accuracy was 81%. The average intersection over union score (IoU) reached 0.78. The model’s accuracy was lower than experts’ and trainees’, but it outperformed all clinicians at delineating the placenta, IoU = 0.75 vs 0.69, 0.66, 0.59. The model was cross validated on 100 2nd trimester images from Barcelona, yielding an accuracy of 76%, IoU 0.68. In conclusion, we developed a model for automatic classification and segmentation of the placenta with consistent performance across different patient populations. It may be used for automated detection of placenta previa and enable future deep learning research in placental dysfunction.