ABSTRACT
BACKGROUND: A convolutional neural network (CNN) is a deep learning algorithm based on the principle of human brain visual cortex processing and image recognition. AIM: To automatically identify the invasion depth and origin of esophageal lesions based on a CNN. METHODS: A total of 1670 white-light images were used to train and validate the CNN system. The method proposed in this paper included the following two parts: (1) Location module, an object detection network, locating the classified main image feature regions of the image for subsequent classification tasks; and (2) Classification module, a traditional classification CNN, classifying the images cut out by the object detection network. RESULTS: The CNN system proposed in this study achieved an overall accuracy of 82.49%, sensitivity of 80.23%, and specificity of 90.56%. In this study, after follow-up pathology, 726 patients were compared for endoscopic pathology. The misdiagnosis rate of endoscopic diagnosis in the lesion invasion range was approximately 9.5%; 41 patients showed no lesion invasion to the muscularis propria, but 36 of them pathologically showed invasion to the superficial muscularis propria. The patients with invasion of the tunica adventitia were all treated by surgery with an accuracy rate of 100%. For the examination of submucosal lesions, the accuracy of endoscopic ultrasonography (EUS) was approximately 99.3%. Results of this study showed that EUS had a high accuracy rate for the origin of submucosal lesions, whereas the misdiagnosis rate was slightly high in the evaluation of the invasion scope of lesions. Misdiagnosis could be due to different operating and diagnostic levels of endoscopists, unclear ultrasound probes, and unclear lesions. CONCLUSION: This study is the first to recognize esophageal EUS images through deep learning, which can automatically identify the invasion depth and lesion origin of submucosal tumors and classify such tumors, thereby achieving good accuracy. In future studies, this method can provide guidance and help to clinical endoscopists.
Subject(s)
Endosonography , Neural Networks, Computer , Algorithms , Endoscopy , Endosonography/methods , HumansABSTRACT
Objective: To conduct a two-dimensional analysis on the key issues that affect the promotion of hierarchical medical system in China, whereby the two dimensions being taken into consideration are the imminence and solvability of the issue, so as to provide reference for the future decision-making on the policy formulation. Methods : 77 papers were systematically collected and 20 issues that may be hindering the hierarchical medical system in China were summarized through the literature review. The imminence and solvability of each issue under cause were evaluated through Delphi method and analytic hierarchy process (AHP). Finally,the key issues hobbling hierarchical medical system were listed by using the variation coefficient method. Results : Research results confirmed that the three issues found to be the key issues include the acute shortage and insufficient service capacity of general practitioners,imperfect physician multi-point practice system which hinders the free flow of doctors, and the current financial input mechanism which is not conducive to the implementation of graded diagnosis and treatment in China. Conclusion : In order to promote hierarchical medical system, suggested are the general practice education reform, stopping the policy restrictions to the doctors' free flow,strongly advocating for the development of primary private healthcare institutions,and constructing the cooperative and restrictive relationship between primary healthcare institutions and higher level hospitals.
ABSTRACT
The medical alliance,as a new exploration of the joint structure of medical institutions at present,can promote the sinking of quality medical resources and promote the integration of medical resources in the region.Medical governance is one of the most important way for medical reform in China.In the paper,the path choice of the corporate governance of medical alliance is explored,and the corresponding policy suggestions are proposed.
ABSTRACT
At present,the functional positioning,service capabilities and resource allocation of various medical institutions differs in China,the tertiary public hospitals,which are rich in high-quality resources,are playing a significant role in integrating medical resources,improving the accessibility and affordability of services and achieving the Chinese national health goal.Through the analysis of the importance and key problems of leading hospitals in a variety of medical alliance,the paper explores the basic ideas and pathways of public hospitals' leading role in various forms of medical alliances.
ABSTRACT
OBJECTIVE: To understand the condition of antibiotics usage in children with upper respiratory tract infection in China, so as to evaluate the effectiveness of rational drug use policy since the new health care reform promulgated by the state. METHODS: Publications were extracted from China National Knowledge Infrastructure(CNKI), Chinese Science and Technology Journal Database(VIP), Wanfang Databases, PubMed, Ebsco, Web of Science and Embase, then Meta-analysis was carried out on them, at the same time, do comparative study on times, regions and categories. RESULTS: Thirty three papers were included for Meta-analysis with a total sample of 54 189.Meta-analysis showed that the combined rate of antibiotics usage in children with upper respiratory tract infection in China was 89.2%(95%CI=82.2%-96.2%.Before 2009, the antibiotics use rate was 92.2%, and it turned to be 87.6% after 2009. The antibiotics use rate of eastern, central and western children was 88.3%, 88.4% and 93.3%. Tertiary hospitals was 85.2%, secondary hospitals was 92.2% and primary medical institutions(including first level hospitals, community health service centers and township health centers) was 90.2%. CONCLUSION: Children's antibiotic use rate of upper upper respiratory tract infection is high in China and the rate is different at different times, regions and institutions. After the health care reform policy was enacted, the use rate of antibiotics fell, this may be related to the implementation of the policy.
ABSTRACT
<p><b>OBJECTIVE</b>To confirm the anticancer effect of total annonaceous acetogenins (TAAs) abstracted from Annona squamosa Linn. on human hepatocarcinoma.</p><p><b>METHODS</b>The inhibitory effect of TAAs was demonstrated in H22-bearing mice. The potency of TAAs was confirmed as its 50% inhibiting concentration (IC50) on Bel-7402 cell under Sulfur Rhodamine B staining. Both underlying mechanisms were explored as cellular apoptosis and cell cycle under flow cytometry. Mitochondrial and recipient apoptotic pathways were differentiated as mitochondrial membrane potential under flow cytometry and caspases activities under fluorescence analysis.</p><p><b>RESULTS</b>The inhibitory rate of TAAs in mice was 50.98% at 4 mg/kg dose. The IC50 of TAAs on Bel-7402 was 20.06 µg/mL (15.13-26.61µg/mL). Effective mechanisms of TAAs were confirmed as both of arresting cell cycle at G1 phase and inducing apoptosis dose- and time-dependently. Mitochondrial and recipient pathways involved in apoptotic actions of TAAs.</p><p><b>CONCLUSION</b>TAAs is effective for hepatocarcinoma, via inhibiting proliferation and inducing apoptosis.</p>
