Rationale:Wooden transorbital penetrating injury is an uncommon and serious trauma that may cause multiply complications.Patient concerns:Here we describe a 62-year-old Chinese woman with a transorbital penetrating injury caused by a long bamboo branch.Diagnosis:Computed tomography scan and magnetic resonance imaging showed the presence of a wooden foreign body.Interventions:Cerebrovascular digital subtraction angiography and temporary balloon occlusion were performed with general anesthesia. Anti-inflammatory therapy was subsequently administered.Outcomes:Retention of wooden foreign body, orbital cellulitis, and traumatic aneurysm at the right internal carotid artery were diagnosed 1 month later. Coil embolization of the right internal carotid artery aneurysm and endoscopic sinus surgery were then performed, and postoperative condition was monitored and recorded.Lessons:Penetrating transorbital injury complications may occur because of retained wooden foreign bodies near the intracranial arteries. Reasonable surgical intervention and special attention should be performed in this kind of trauma.

The running of high-speed electrically driven feed pump has a direct impact on the safety of personnel equipment and economic benefits of power plant, as the result, intelligent condition monitoring and fault diagnosis of electrically driven feed pump becomes an urgent need. In the practical process of electrically driven feed pump fault diagnosis, the running of the equipment is in normal state for a long time, occasionally, with faults, which makes the fault data very rare in a large number of monitoring data, and makes it difficult to extract the internal fault features behind the original time series data, When the deep learning theory is used in practice, the imbalance between the fault data and the normal data occurs in the operation data set. In order to solve the problem of data imbalance, this paper proposes a fault diagnosis method of GAN-SAE. This method first makes compensation for the imbalance of sample data based on the Generative Adversarial Network (GAN), and then uses the Stacked Auto Encoder (SAE) method to extract the signal features. By designing the fault diagnosis program, compared with only using SAE, back propagation neural networks (BP) and multi-hidden layer neural networks(MNN) method, the GAN-SAE method can offer better capability of extracting features, and the accuracy of fault diagnosis of electrically driven feed pump could be improved to 98.89%.

ObjectiveWe wanted to evaluate the feasibility and usefulness of a newly designed balloon sheath for gastrointestinal guidance and access by conducting a phantom study.Materials and MethodsThe newly designed balloon sheath consisted of an introducer sheath and a supporting balloon. A coil catheter was advanced over a guide wire into two gastroduodenal phantoms (one was with stricture and one was without stricture); group I was without a balloon sheath, group ll was with a deflated balloon sheath, and groups III and IV were with an inflated balloon and with the balloon in the fundus and body, respectively. Each test was performed for 2 minutes and it was repeated 10 times in each group by two researchers, and the positions reached by the catheter tip were recorded.ResultsBoth researchers had better performances with both phantoms in order of group IV, III, II and I. In group IV, both researchers advanced the catheter tip through the fourth duodenal segment in both the phantoms. In group I, however, the catheter tip never reached the third duodenal segment in both the phantoms by both the researchers. The numeric values for the four study groups were significantly different for both the phantoms (p < 0.001). A significant difference was also found between group III and IV for both phantoms (p < 0.001).ConclusionThe balloon sheath seems to be feasible for clinical use, and it has good clinical potential for gastrointestinal guidance and access, particularly when the inflated balloon is placed in the gastric body.