Spatial Prediction of Highway Slope Disasters Based on Convolution Neural Networks

In order to clarify the spatial differentiations of highway slope disasters (HSDs) in Boshan District, spatial prediction was carried out based on ECG-CNN with the support of GIS. Spatial prediction factors of HSDs were selected, the stabilities of the 147 highway slopes in Boshan District were determined. The spatial prediction model of HSDs was established by ECG-CNN, and the spatial susceptibility map of HSDs in Boshan District was drawn. Influences of the prediction factor combinations and the drill sample & verification sample combinations on the prediction success rates were verified. The results showed that low susceptible areas, medium susceptible areas and high susceptible areas account for 56.92%, 28.46% and 14.62% of the total areas of Boshan District respectively. Some sections of Binlai Expressway, G205, G309, S210 and S307 pass through high susceptible areas. The surface cutting depth has a small impact on the prediction success rate, while the elevation and gradient have great impacts on the prediction success rate. When the drill samples are small, network drill’s maturity has a great impact on the prediction success rate, while when there are many drill samples, the model’s logical structure itself has a large impact on the prediction success rate.

RapidNAM: generative manufacturing approach of nasoalveolar molding devices for presurgical cleft lip and palate treatment

Nasoalveolar molding (NAM) is an accepted treatment strategy in presurgical cleft therapy. The major drawbacks of the treatment listed in the literature relate to the time of the treatment and the coordination of the required interdisciplinary team of therapists, parents, and patients. To overcome these limitations, we present the automated RapidNAM concept that facilitates the design and manufacturing process of NAM devices, and that allows the virtual modification and subsequent manufacture of the devices in advance, with a growth prediction factor adapted to the patient’s natural growth. The RapidNAM concept involves (i) the prediction of three trajectories that envelope the fragmented alveolar segments with the goal to mimic a harmonic arch, (ii) the extrusion from the larger toward the smaller alveolar segment along the envelope curves toward the harmonic upper alveolar arch, and (iii) the generation of the NAM device with a ventilation hole, fixation pin, and fixation points for the nasal stents. A feasibility study for a vector-based approach was successfully conducted for unilateral and bilateral cleft lip and palate (CLP) patients. A comparison of the modified target models with the reference target models showed similar results. For further improvement, the number of landmarks used to modify the models was increased by a curve-based approach.

Treatment of hydrocephalus in premature infants with intraventricular hemorrhage - placing Omaya reservoir: A series of 30 patients

Introduction. We report a series of 30 patients with spontaneous intraventricular hemorrhage (IVH) and hydrocephalus, in which is placed subcutaneous (Omaya) tank at the University Children?s Hospital in Belgrade from March 2006 to March 2011. Results. Predictors of poor outcome in treatment in getting Omaya reservoirs are low birth weight (t=2.560, p=0.016), low Apgar score (t=3.059, p=0.005), an extended number of days on mechanical ventilation (Z=4,404 , p< 0.001), the presence of peripartal asphyxia (X2=9.977, p=0.002) and cardio-respiratory arrest (X2=12.804 , p< 0.001). Conclusion. The outcome of treatment of hydrocephalus caused by spontaneous intraventricular hemorrhage in premature infants is worst in perinatology. There is no consensus on the diagnosis and treatment of posthemorrhage hydrocephalus, our results suggest that the main prediction factor is preoperative condition of the child.