Search

Introduction Early judgment of the depth of burns is very important for the accurate formulation of treatment plans. In medical imaging the application of Artificial Intelligence has the potential for serving as a very experienced assistant to improve early clinical diagnosis. Due to lack of large volume of a particular feature, there has been almost no progress in burn field. Methods 484 early wound images are collected on patients who discharged home after a burn injury in 48 h, from five different levels of hospitals in Hunan Province China. According to actual healing time, all images are manually annotated by five professional burn surgeons and divided into three sets which are shallow(0–10 days), moderate(11–20 days) and deep(more than 21 days or skin graft healing). These ROIs were further divided into 5637 patches sizes 224 × 224 pixels, of which 1733 shallow, 1804 moderate, and 2100 deep. We used transfer learning suing a Pre-trained ResNet50 model and the ratio of all images is 7:1.5:1.5 for training:validation:test. Results A novel artificial burn depth recognition model based on convolutional neural network was established and the diagnostic accuracy of the three types of burns is about 80%. Discussion The actual healing time can be used to deduce the depth of burn involvement. The artificial burn depth recognition model can accurately infer healing time and burn depth of the patient, which is expected to be used for auxiliary diagnosis improvement.

Rationale:Esophageal duplication cyst (EDC) is a rare developmental aberration originated from the embryonic foregut. It may remain asymptomatic but produce local mass effect on surrounding organs if rapid enlarges. EDC may sometimes accompany with other congenital malformations. Congenital

ObjectiveTo investigate the results of emergency endovascular repair of complicated Stanford type B aortic dissections within 24 hours of symptom onset.MethodsA retrospective analysis of the clinical data of 30 patients with complicated Stanford type B aortic dissections who underwent emergency endovascular repair between June 2007 and October 2008. Endovascular repairs were performed within 24 hours of symptom onset. Stent-grafts were deployed at the first entry tear through the femoral artery under fluoroscopic guidance. Follow-up computed tomography scans were performed at 1, 3, 6, 12, and 18 months after treatment.ResultsThe mean patient age was 64 years (range, 43–83 years). There were 3 cases associated with rupture, 6 cases associated with refractory hypertension, 15 cases associated with persistent pain, 2 cases associated with retrograde dissection, and 4 cases associated with malperfusion. The technical success rate was 100%, and the incidence of immediate postoperative endoleaks was 13.4%. One patient died of dissection rupture within 30 days. The mean follow-up period was 12 ± 8 months. A small, persistent endoleak (

In this paper, we present a novel hybrid overlay, named as Together, for application multicast in heterogeneous environment. We analyze the reasons to cause bandwidth bottleneck in tree-based approach and correspondingly define a special set called Spare Capacity Set. Based on this definition, we further design a bandwidth adaptive auxiliary mesh which can be reconciled with a stable multiple trees structure under a coherent framework. The hybrid approach can achieve good performance as well as maximized utilization of node bandwidth, which is essential in heterogeneous environment.

Traditional encryption schemes are not suitable for the Wireless sensor networks (WSNS) due to some intrinsic features of nodes in WSNS such as low energy, limited computation ability and storage resources. This paper presented a novel block encryption scheme based on hybrid chaotic maps dynamically and proposed an integer digital random method, and the Feistel network structure, which is a kind of fast, secure, low resource consumption and suitable for WSNS nodes encryption scheme. The experimental tests show the new encryption scheme has follows prefect performance: the large key space, very good diffusion and disrupt performance, strict avalanche effect, excellent statistical balance and fast encryption speed of the new scheme, and the encryption scheme passes the SP800-22 test; meanwhile, the analysis and testing of speed, time and storage space on the simulator platform shows this new encryption scheme is well able to hide the data information the node in WSNS.