RESUMO
Introductory paragraphThe pandemic of coronavirus Disease 2019 (COVID-19) caused enormous loss of life globally. 1-3 Case identification is critical. The reference method is using real-time reverse transcription PCR (rRT-PCR) assays, with limitations that may curb its prompt large-scale application. COVID-19 manifests with chest computed tomography (CT) abnormalities, some even before the onset of symptoms. We tested the hypothesis that application of deep learning (DL) to the 3D CT images could help identify COVID-19 infections. Using the data from 920 COVID-19 and 1,073 non-COVID-19 pneumonia patients, we developed a modified DenseNet-264 model, COVIDNet, to classify CT images to either class. When tested on an independent set of 233 COVID-19 and 289 non-COVID-19 patients. COVIDNet achieved an accuracy rate of 94.3% and an area under the curve (AUC) of 0.98. Application of DL to CT images may improve both the efficiency and capacity of case detection and long-term surveillance.
RESUMO
In order to optimize the data flow of subject datasets and to establish the service platform of medical image data, we developed a medical image database aiming at subject service of clinic research. Firstly, a novel integrated infrastructure was designed, which was based on the requirements of database system and the survey of data resource. Then, several standards and technologies had been used in the construction of this novel system, including "Subject dataset-Sample data-Image files" three-ties image information framework, DICOM-based data processing, Index & file hybrid structure of file management strategy, etc. The new system has been successfully deployed in our test-bed and has got satisfactory results.
Assuntos
Sistemas de Gerenciamento de Base de Dados , Bases de Dados Factuais , Padrões de Referência , Diagnóstico por Imagem , Processamento de Imagem Assistida por Computador , Sistemas de Informação em RadiologiaRESUMO
In this paper, the theory of complex adaptive system (CAS) and its modeling method are introduced. The complex characters of the hospital system is analyzed. The agile manufacturing and cell reconstruction technologies are used to reconstruct the hospital system. Then we set forth a research for simulation of hospital system based on the methodology of Multi-Agent technology and high level architecture (HLA). Finally, a simulation framework based on HLA for hospital system is presented.
