At the international level, a major effort is being made to optimizethe flow of data and information for health systems management. The studiesshow that medical and economic efficiency is strongly influenced by the le...At the international level, a major effort is being made to optimizethe flow of data and information for health systems management. The studiesshow that medical and economic efficiency is strongly influenced by the levelof development and complexity of implementing an integrated system of epidemiological monitoring and modeling. The solution proposed and describedin this paper is addressed to all public and private institutions involved inthe fight against the COVID-19 pandemic, using recognized methods andstandards in this field. The Green-Epidemio is a platform adaptable to thespecific features of any public institution for disease management, based onopen-source software, allowing the adaptation, customization, and furtherdevelopment of “open-source” applications, according to the specificities ofthe public institution, the changes in the economic and social environment andits legal framework. The platform has a mathematical model for the spreadof COVID-19 infection depending on the location of the outbreaks so thatthe allocation of resources and the geographical limitation of certain areascan be parameterized according to the number and location of the real-timeidentified outbreaks. The social impact of the proposed solution is due to theplanned applications of information flow management, which is a first stepin improving significantly the response time and efficiency of people-operatedresponse services. Moreover, institutional interoperability influences strategicsocietal factors.展开更多
The task of segmentation of brain regions affected by ischemic stroke is help to tackle important challenges of modern stroke imaging analysis.Unfortunately,at the moment,the models for solving this problem using mach...The task of segmentation of brain regions affected by ischemic stroke is help to tackle important challenges of modern stroke imaging analysis.Unfortunately,at the moment,the models for solving this problem using machine learning methods are far from ideal.In this paper,we consider a modified 3D UNet architecture to improve the quality of stroke segmentation based on 3Dcomputed tomography images.We use the ISLES 2018(Ischemic Stroke Lesion Segmentation Challenge 2018)open dataset to train and test the proposed model.Interpretation of the obtained results,as well as the ideas for further experiments are included in the paper.Our evaluation is performed using the Dice or f1 score coefficient and the Jaccard index.Our architecture may simply be extended to ischemia segmentation and computed tomography image identification by selecting relevant hyperparameters.The Dice/f1 score similarity coefficient of our model shown58%and results close to ground truth which is higher than the standard 3D UNet model,demonstrating that our model can accurately segment ischemic stroke.The modified 3D UNet model proposed by us uses an efficient averaging method inside a neural network.Since this set of ISLES is limited in number,using the data augmentation method and neural network regularization methods to prevent overfitting gave the best result.In addition,one of the advantages is the use of the Intersection over Union loss function,which is based on the assessment of the coincidence of the shapes of the recognized zones.展开更多
基金This research received no grant funding and the APC was funded by “Stefan cel Mare” University of Suceava,Romania.
文摘At the international level, a major effort is being made to optimizethe flow of data and information for health systems management. The studiesshow that medical and economic efficiency is strongly influenced by the levelof development and complexity of implementing an integrated system of epidemiological monitoring and modeling. The solution proposed and describedin this paper is addressed to all public and private institutions involved inthe fight against the COVID-19 pandemic, using recognized methods andstandards in this field. The Green-Epidemio is a platform adaptable to thespecific features of any public institution for disease management, based onopen-source software, allowing the adaptation, customization, and furtherdevelopment of “open-source” applications, according to the specificities ofthe public institution, the changes in the economic and social environment andits legal framework. The platform has a mathematical model for the spreadof COVID-19 infection depending on the location of the outbreaks so thatthe allocation of resources and the geographical limitation of certain areascan be parameterized according to the number and location of the real-timeidentified outbreaks. The social impact of the proposed solution is due to theplanned applications of information flow management, which is a first stepin improving significantly the response time and efficiency of people-operatedresponse services. Moreover, institutional interoperability influences strategicsocietal factors.
文摘The task of segmentation of brain regions affected by ischemic stroke is help to tackle important challenges of modern stroke imaging analysis.Unfortunately,at the moment,the models for solving this problem using machine learning methods are far from ideal.In this paper,we consider a modified 3D UNet architecture to improve the quality of stroke segmentation based on 3Dcomputed tomography images.We use the ISLES 2018(Ischemic Stroke Lesion Segmentation Challenge 2018)open dataset to train and test the proposed model.Interpretation of the obtained results,as well as the ideas for further experiments are included in the paper.Our evaluation is performed using the Dice or f1 score coefficient and the Jaccard index.Our architecture may simply be extended to ischemia segmentation and computed tomography image identification by selecting relevant hyperparameters.The Dice/f1 score similarity coefficient of our model shown58%and results close to ground truth which is higher than the standard 3D UNet model,demonstrating that our model can accurately segment ischemic stroke.The modified 3D UNet model proposed by us uses an efficient averaging method inside a neural network.Since this set of ISLES is limited in number,using the data augmentation method and neural network regularization methods to prevent overfitting gave the best result.In addition,one of the advantages is the use of the Intersection over Union loss function,which is based on the assessment of the coincidence of the shapes of the recognized zones.
