Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 3 de 3
Filtrar
Mais filtros










Base de dados
Intervalo de ano de publicação
1.
Comput Biol Med ; 170: 107916, 2024 Mar.
Artigo em Inglês | MEDLINE | ID: mdl-38237237

RESUMO

In the medical field, the application of machine learning technology in the automatic diagnosis and monitoring of osteoporosis often faces challenges related to domain adaptation in drug therapy research. The existing neural networks used for the diagnosis of osteoporosis may experience a decrease in model performance when applied to new data domains due to changes in radiation dose and equipment. To address this issue, in this study, we propose a new method for multi domain diagnostic and quantitative computed tomography (QCT) images, called DeepmdQCT. This method adopts a domain invariant feature strategy and integrates a comprehensive attention mechanism to guide the fusion of global and local features, effectively improving the diagnostic performance of multi domain CT images. We conducted experimental evaluations on a self-created OQCT dataset, and the results showed that for dose domain images, the average accuracy reached 91%, while for device domain images, the accuracy reached 90.5%. our method successfully estimated bone density values, with a fit of 0.95 to the gold standard. Our method not only achieved high accuracy in CT images in the dose and equipment fields, but also successfully estimated key bone density values, which is crucial for evaluating the effectiveness of osteoporosis drug treatment. In addition, we validated the effectiveness of our architecture in feature extraction using three publicly available datasets. We also encourage the application of the DeepmdQCT method to a wider range of medical image analysis fields to improve the performance of multi-domain images.


Assuntos
Osteoporose , Humanos , Osteoporose/diagnóstico por imagem , Densidade Óssea , Tomografia Computadorizada por Raios X , Computadores , Aprendizado de Máquina , Processamento de Imagem Assistida por Computador
2.
Neural Regen Res ; 11(5): 771-8, 2016 May.
Artigo em Inglês | MEDLINE | ID: mdl-27335561

RESUMO

Cold-inducible RNA-binding protein (CIRP), a key regulatory protein, could be facilitated by mild hypothermia in the brain, heart and liver. This study observed the effects of mild hypothermia at 31 ± 0.5°C on traumatic brain injury in rats. Results demonstrated that mild hypothermia suppressed apoptosis in the cortex, hippocampus and hypothalamus, facilitated CIRP mRNA and protein expression in these regions, especially in the hypothalamus. The anti-apoptotic effect of mild hypothermia disappeared after CIRP silencing. There was no correlation between mitogen-activated extracellular signal-regulated kinase activation and CIRP silencing. CIRP silencing inhibited extracellular signal-regulated kinase-1/2 activation. These indicate that CIRP inhibits apoptosis by affecting extracellular signal-regulated kinase-1/2 activation, and exerts a neuroprotective effect during mild hypothermia for traumatic brain injury.

3.
Int J Infect Dis ; 16(2): e99-103, 2012 Feb.
Artigo em Inglês | MEDLINE | ID: mdl-22119269

RESUMO

OBJECTIVE: To evaluate the mass measles vaccination campaign of 2009 in Guangdong Province, China. METHODS: Data on the campaign implementation, measles surveillance, and serological surveillance were reviewed and analyzed by statistical methods. RESULTS: Rapid coverage surveys showed that 98.09% of children were vaccinated during the campaign. The coverage of migrant children increased significantly from 67.10% to 97.32% (p<0.01). From May to December 2009, after the campaign, the number of measles cases was reduced by 93.04% compared with the same period of 2008. The antibody positive rate in children aged less than 15 years reached above 95%. More than 1 million migrant children were identified and vaccinated during the campaign. Flyers, notices of information from doctors, and television programs were the best methods to inform parents of the campaign. Awareness of the campaign by residents increased significantly from 91.86% to 97.10% (p<0.01) through the use of social mobilization materials. CONCLUSIONS: A massive vaccination campaign approach for controlling measles in a developing region like Guangdong Province with a vast migrant population has proved effective. Comprehensive mobilization, communication with the mass media, and support from government departments were critical to the success of the campaign.


Assuntos
Vacina contra Sarampo/administração & dosagem , Sarampo/prevenção & controle , Adolescente , Criança , Pré-Escolar , China , Feminino , Humanos , Programas de Imunização/métodos , Imunoglobulina G/imunologia , Vigilância Imunológica/imunologia , Lactente , Masculino , Vacinação em Massa/efeitos adversos , Vacinação em Massa/métodos , Sarampo/imunologia , Vacina contra Sarampo/efeitos adversos , Vacina contra Sarampo/imunologia , Vacinação/métodos
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...