Background—: Lung hypoplasia and persistent pulmonary hypertension of the newborn limit survival in congenital diaphragmatic hernia (CDH). Unlike other diseases resulting in persistent pulmonary hypertension of the newborn, infants with CDH are refractory to inhaled nitric oxide (NO). Nitric oxide mediates pulmonary vasodilatation at birth in part via cyclic GMP production. Phosphodiesterase type 5 (PDE5) limits the effects of NO by inactivation of cyclic GMP. Because of the limited success in postnatal management of CDH, we hypothesized that antenatal PDE5 inhibition would attenuate pulmonary artery remodeling in experimental nitrofen-induced CDH. Methods and Results—: Nitrofen administered at embryonic day 9.5 to pregnant rats resulted in a 60% incidence of CDH in the offspring and recapitulated features seen in human CDH, including structural abnormalities (lung hypoplasia, decreased pulmonary vascular density, pulmonary artery remodeling, right ventricular hypertrophy), and functional abnormalities (decreased pulmonary artery relaxation in response to the NO donor 2-( N , N -diethylamino)-diazenolate-2-oxide). Antenatal sildenafil administered to the pregnant rat from embryonic day 11.5 to embryonic day 20.5 crossed the placenta, increased fetal lung cyclic GMP and decreased active PDE5 expression. Antenatal sildenafil improved lung structure, increased pulmonary vessel density, reduced right ventricular hypertrophy, and improved postnatal NO donor 2-( N , N -diethylamino)-diazenolate-2-oxide–induced pulmonary artery relaxation. This was associated with increased lung endothelial NO synthase and vascular endothelial growth factor protein expression. Antenatal sildenafil had no adverse effect on retinal structure/function and brain development. Conclusions—: Antenatal sildenafil improves pathological features of persistent pulmonary hypertension of the newborn in experimental CDH and does not alter the development of other PDE5-expressing organs. Given the high mortality/morbidity of CDH, the potential benefit of prenatal PDE5 inhibition in improving the outcome for infants with CDH warrants further studies.

In echocardiography (echo), an electrocardiogram (ECG) is conventionally used to temporally align different cardiac views for assessing critical measurements. However, in emergencies or point-of-care situations, acquiring an ECG is often not an option, hence motivating the need for alternative temporal synchronization methods. Here, we propose Echo-SyncNet, a self-supervised learning framework to synchronize various cross-sectional 2D echo series without any human supervision or external inputs. The proposed framework takes advantage of two types of supervisory signals derived from the input data: spatiotemporal patterns found between the frames of a single cine (intra-view self-supervision) and interdependencies between multiple cines (inter-view self-supervision). The combined supervisory signals are used to learn a feature-rich and low dimensional embedding space where multiple echo cines can be temporally synchronized. Two intra-view self-supervisions are used, the first is based on the information encoded by the temporal ordering of a cine (temporal intra-view) and the second on the spatial similarities between nearby frames (spatial intra-view). The inter-view self-supervision is used to promote the learning of similar embeddings for frames captured from the same cardiac phase in different echo views. We evaluate the framework with multiple experiments: 1) Using data from 998 patients, Echo-SyncNet shows promising results for synchronizing Apical 2 chamber and Apical 4 chamber cardiac views, which are acquired spatially perpendicular to each other; 2) Using data from 3070 patients, our experiments reveal that the learned representations of Echo-SyncNet outperform a supervised deep learning method that is optimized for automatic detection of fine-grained cardiac cycle phase; 3) We go one step further and show the usefulness of the learned representations in a one-shot learning scenario of cardiac key-frame detection. Without any fine-tuning, key frames in 1188 validation patient studies are identified by synchronizing them with only one labeled reference cine. We do not make any prior assumption about what specific cardiac views are used for training, and hence we show that Echo-SyncNet can accurately generalize to views not present in its training set. Project repository: github.com/fatemehtd/Echo-SyncNet.

This paper presents U-LanD, a framework for automatic detection of landmarks on key frames of the video by leveraging the uncertainty of landmark prediction. We tackle a specifically challenging problem, where training labels are noisy and highly sparse. U-LanD builds upon a pivotal observation: a deep Bayesian landmark detector solely trained on key video frames, has significantly lower predictive uncertainty on those frames vs. other frames in videos. We use this observation as an unsupervised signal to automatically recognize key frames on which we detect landmarks. As a test-bed for our framework, we use ultrasound imaging videos of the heart, where sparse and noisy clinical labels are only available for a single frame in each video. Using data from 4,493 patients, we demonstrate that U-LanD can exceedingly outperform the state-of-the-art non-Bayesian counterpart by a noticeable absolute margin of 42% in ${R}^{{2}}$ score, with almost no overhead imposed on the model size.