Upper gastrointestinal anatomy detection with multi-task convolutional neural networks.

Esophagogastroduodenoscopy (EGD) has been widely applied for gastrointestinal (GI) examinations. However, there is a lack of mature technology to evaluate the quality of the EGD inspection process. In this Letter, the authors design a multi-task anatomy detection convolutional neural network (MT-AD-CNN) to evaluate the EGD inspection quality by combining the detection task of the upper digestive tract with ten anatomical structures and the classification task of informative video frames. The authors' model is able to eliminate non-informative frames of the gastroscopic videos and detect the anatomies in real time. Specifically, a sub-branch is added to the detection network to classify NBI images, informative and non-informative images. By doing so, the detected box will be only displayed on the informative frames, which can reduce the false-positive rate. They can determine the video frames on which each anatomical location is effectively examined, so that they can analyse the diagnosis quality. Their method reaches the performance of 93.74% mean average precision for the detection task and 98.77% accuracy for the classification task. Their model can reflect the detailed circumstance of the gastroscopy examination process, which shows application potential in improving the quality of examinations.

Intrathecal infection of TRESK overexpression adenovirus to relieve neuropathic pain via inhibiting JNK activation and neuronal apoptosis / 实用医学杂志

Objective To observe the effect of intrathecal injection of TRESK overexpression adenoviruson phosphorylation of JNK and apoptosis of neurons in neuropathic pain rats.Methods Seventy-two male SD rats were randomly divided into six groups:groups C,S,NP,T,V,and NS,12 for each group.SNI was administrated to rats in groups NP,T,V and NS.TRESK adenovirus and negative virus were intrathecally injected after use of SNI in groups T and V,while equal volume of NS was injected to rats in group NS.MWT and TWL were measured at 1 day before operation(baseline,BL)and at 1,3,7 and 14 days after operation (days 1,3,7,and 14).Six rats in each group were sacrificed at D7 to determinate the expression of TRESK protein of DRG.The other rats were sacrificed at D14 to determinate neural apoptosis and the expressions of caspase3 and p-JNK of DRG.Results As compared with groups C,S and T,the expression of TRESK protein was significantly decreased at D7 in groups NP,NS and V (P＜0.05).Compared with groups C and S,MWT was significantly decreased at days 1,3,7 and 14 (P＜0.05),phosphorylation of JNK in DRG was significantly increased at D14 (P＜0.05),neuronal apoptosis rate and expressions of Caspase3 of DRG were significantly increased at D14 (P＜0.05) in groups NP,T,NS and V.Compared with groups NP,V and NS,MWT was significantly increased at time points of days 1,3,7 and 14 in group T (P＜0.05),phosphorylation of JNK of in DRG was significantly decreased at D14 in group T (P＜0.05),neuronal apoptosis rate and expression of Caspase3 of DRG were significantly decreased at D14 in group T (P＜0.05).Intrathecal injection ofpAd/CMV/VS-DEST-TRESK obviously reduced mechanical hyperalgesia,upregulated TRESK expression,and lowered JNK phosphorylation and NP in SNI rat.Conclusions Intrathecal injection of TRESK over expression adenovirus relieves NP via inhibiting JNK activation and neuronal apoptosis.

Research situation and expectation of clinical healthcare big data / 医疗卫生装备

Objective To cxplore the research and application of big data mining technology in clinical healthcare environment.Methods The characteristics of clinical heahhcare data mining methods were expounded and the current research status of healthcare data mining technology was analyzed in clinical task according to the literature mining.Meanwhile,the application of healthcare data mining in clinical environment was introduced from the following four aspects:medicine research,personalized diagnosis,risk prediction and process mining.Results The necessity and importance of research and application of clinical healthcare data mining were illustrated.Moreover,the achicvements of healthcare data mining in clinical application,as well as existing problems and technical difficulties were summarized.Furthermore,the development tendencies of healthcare data mining were predicted.Conclusion The research and application of clinical healthcare data mining have improved the healthcare quality and promoted the medical advances,which is the developmcnt direction of clinical healthcare research.