Monochorionic twin pregnancies complicated by severe twin-to-twin transfusion syndrome at midgestation can be treated by either serial amnioreduction (removal of large volumes of amniotic fluid) or selective fetoscopic laser coagulation of the communicating vessels on the chorionic plate. We conducted a randomized trial to compare the efficacy and safety of these two treatments. Pregnant women with severe twin-to-twin transfusion syndrome before 26 weeks of gestation were randomly assigned to laser therapy or amnioreduction. We assessed perinatal survival of at least one twin (a prespecified primary outcome), survival of at least one twin at six months of age, and survival without neurologic complications at six months of age on the basis of the number of pregnancies or the number of fetuses or infants, as appropriate. The study was concluded early, after 72 women had been assigned to the laser group and 70 to the amnioreduction group, because a planned interim analysis demonstrated a significant benefit in the laser group. As compared with the amnioreduction group, the laser group had a higher likelihood of the survival of at least one twin to 28 days of age (76 percent vs. 56 percent; relative risk of the death of both fetuses, 0.63; 95 percent confidence interval, 0.25 to 0.93; P=0.009) and 6 months of age (P=0.002). Infants in the laser group also had a lower incidence of cystic periventricular leukomalacia (6 percent vs. 14 percent, P=0.02) and were more likely to be free of neurologic complications at six months of age (52 percent vs. 31 percent, P=0.003). Endoscopic laser coagulation of anastomoses is a more effective first-line treatment than serial amnioreduction for severe twin-to-twin transfusion syndrome diagnosed before 26 weeks of gestation.

Convolutional neural networks (CNNs) have achieved state-of-the-art performance for automatic medical image segmentation. However, they have not demonstrated sufficiently accurate and robust results for clinical use. In addition, they are limited by the lack of image-specific adaptation and the lack of generalizability to previously unseen object classes (a.k.a. zero-shot learning). To address these problems, we propose a novel deep learning-based interactive segmentation framework by incorporating CNNs into a bounding box and scribble-based segmentation pipeline. We propose image-specific fine tuning to make a CNN model adaptive to a specific test image, which can be either unsupervised (without additional user interactions) or supervised (with additional scribbles). We also propose a weighted loss function considering network and interaction-based uncertainty for the fine tuning. We applied this framework to two applications: 2-D segmentation of multiple organs from fetal magnetic resonance (MR) slices, where only two types of these organs were annotated for training and 3-D segmentation of brain tumor core (excluding edema) and whole brain tumor (including edema) from different MR sequences, where only the tumor core in one MR sequence was annotated for training. Experimental results show that: 1) our model is more robust to segment previously unseen objects than state-of-the-art CNNs; 2) image-specific fine tuning with the proposed weighted loss function significantly improves segmentation accuracy; and 3) our method leads to accurate results with fewer user interactions and less user time than traditional interactive segmentation methods.

In 2010, the congenital diaphragmatic hernia (CDH) EURO Consortium published a standardized neonatal treatment protocol. Five years later, the number of participating centers has been raised from 13 to 22. In this article the relevant literature is updated, and consensus has been reached between the members of the CDH EURO Consortium. Key updated recommendations are: (1) planned delivery after a gestational age of 39 weeks in a high-volume tertiary center; (2) neuromuscular blocking agents to be avoided during initial treatment in the delivery room; (3) adapt treatment to reach a preductal saturation of between 80 and 95% and postductal saturation >70%; (4) target PaCO₂ to be between 50 and 70 mm Hg; (5) conventional mechanical ventilation to be the optimal initial ventilation strategy, and (6) intravenous sildenafil to be considered in CDH patients with severe pulmonary hypertension. This article represents the current opinion of all consortium members in Europe for the optimal neonatal treatment of CDH.

Objective: To assess the value of antenatally determined observed to expected fetal lung area to head circumference ratio (LHR) in the prediction of postnatal survival in isolated, congenital diaphragmatic hernia (CDH).Methods: Two groups of fetuses were examined. The first group included 650 normal fetuses at 12–32 weeks' gestation, and the data collected were used to establish a normal range of observed to expected LHR with gestational age. The second group included the data of a retrospective multicenter study of 354 fetuses with isolated CDH in which the LHR was measured on one occasion at 18–38 weeks' gestation. The patients were divided into those with left‐sided CDH with and without intrathoracic herniation of the liver and right‐sided CDH. Regression analysis was used to determine the significant predictors of postnatal survival.Results: In both the normal fetuses and those with CDH the LHR increased but the observed to expected LHR did not change significantly with gestational age. In normal fetuses the mean observed to expected LHR in the left lung was 100% (95% CI, 61–139%) and in the right lung it was 100% (95% CI, 67–133%). In fetuses with CDH the mean observed to expected LHR was 39% (range 7–79%). Regression analysis demonstrated that significant predictors of survival were the observed to expected LHR (odds ratio (OR) 1.09, 95% CI, 1.06–1.12), side of CDH (left side OR 11.14, 95% CI, 3.41–36.39) and gestational age at delivery (OR 1.18, 95% CI, 1.02–1.36).Conclusion: In CDH, the LHR increases while observed to expected LHR is independent of gestational age. In fetuses with both left‐ and right‐sided CDH, measurement of the observed to expected LHR provides a useful prediction of subsequent survival. Copyright © 2007 ISUOG. Published by John Wiley & Sons, Ltd.

Accurate medical image segmentation is essential for diagnosis, surgical planning and many other applications. Convolutional Neural Networks (CNNs) have become the state-of-the-art automatic segmentation methods. However, fully automatic results may still need to be refined to become accurate and robust enough for clinical use. We propose a deep learning-based interactive segmentation method to improve the results obtained by an automatic CNN and to reduce user interactions during refinement for higher accuracy. We use one CNN to obtain an initial automatic segmentation, on which user interactions are added to indicate mis-segmentations. Another CNN takes as input the user interactions with the initial segmentation and gives a refined result. We propose to combine user interactions with CNNs through geodesic distance transforms, and propose a resolution-preserving network that gives a better dense prediction. In addition, we integrate user interactions as hard constraints into a back-propagatable Conditional Random Field. We validated the proposed framework in the context of 2D placenta segmentation from fetal MRI and 3D brain tumor segmentation from FLAIR images. Experimental results show our method achieves a large improvement from automatic CNNs, and obtains comparable and even higher accuracy with fewer user interventions and less time compared with traditional interactive methods.