Pneumonia is part of the main diseases causing the death of children.It is generally diagnosed through chest Xray images.With the development of Deep Learning(DL),the diagnosis of pneumonia based on DL has received ex...Pneumonia is part of the main diseases causing the death of children.It is generally diagnosed through chest Xray images.With the development of Deep Learning(DL),the diagnosis of pneumonia based on DL has received extensive attention.However,due to the small difference between pneumonia and normal images,the performance of DL methods could be improved.This research proposes a new fine-grained Convolutional Neural Network(CNN)for children’s pneumonia diagnosis(FG-CPD).Firstly,the fine-grainedCNNclassificationwhich can handle the slight difference in images is investigated.To obtain the raw images from the real-world chest X-ray data,the YOLOv4 algorithm is trained to detect and position the chest part in the raw images.Secondly,a novel attention network is proposed,named SGNet,which integrates the spatial information and channel information of the images to locate the discriminative parts in the chest image for expanding the difference between pneumonia and normal images.Thirdly,the automatic data augmentation method is adopted to increase the diversity of the images and avoid the overfitting of FG-CPD.The FG-CPD has been tested on the public Chest X-ray 2017 dataset,and the results show that it has achieved great effect.Then,the FG-CPD is tested on the real chest X-ray images from children aged 3–12 years ago from Tongji Hospital.The results show that FG-CPD has achieved up to 96.91%accuracy,which can validate the potential of the FG-CPD.展开更多
Studies showed that exclusive breast feeding reduced infant morbidity and mortality. In low income countries such as Ethiopia where under-five mortality is very high, the role of exclusively breastfeeding could be eve...Studies showed that exclusive breast feeding reduced infant morbidity and mortality. In low income countries such as Ethiopia where under-five mortality is very high, the role of exclusively breastfeeding could be even more critical. However, studies assessing the place of exclusive breast freeing in the prevention of childhood illnesses in our area are scarce. The aim of the study was to identify determinant factors of childhood pneumonia and diarrhoea. An institution based case control study was conducted in Achefer District in July, 2012. The cases were 122 children of 7 - 24 months old who had repeated attack of diarrhoea or pneumonia over three months prior to the survey while controls were 122 children who visited well baby clinic for vaccination. Data were collected by using pre-tested and structured questionnaire, and analysed using SPSS version 16 for windows. Logistic regression was performed, and strength of associations was estimated using odds ratio and 95% confidence interval. About 83% of the controls and only 12.3% of the cases were exclusively breast fed. Children who were exclusively breast fed were 83 times less likely to develop pneumonia or diarrhea than those who were not exclusively fed. Marital status, monthly income, prelacteal feeding, and late initiation of breast feeding were found to have statistically significant association with childhood diarrhea and pneumonia. This study brought local evidence that exclusive breast feeding had a protective effect against common childhood infectious diseases—pneumonia and diarrhoea—in the study area. Therefore, culture sensitive and plausible health education is recommended to strengthen exclusive breast feeding practices in order to decrease mortality and morbidity of infants and children from pneumonia and diarrhoea.展开更多
Objective: To analyze the causes of childhood pneumonia Streptococcus pneumoniae resistance and clinical characteristics, and provide a basis for better and timely clinical therapy, and medication to reduce blind-ness...Objective: To analyze the causes of childhood pneumonia Streptococcus pneumoniae resistance and clinical characteristics, and provide a basis for better and timely clinical therapy, and medication to reduce blind-ness. Methods: MIC method in our hospital 114 under 2020 pediatric pneumococcal respiratory infection in children with lower respiratory tract specimens were isolated antimicrobial susceptibility testing, and analyzed retrospectively. Results: 84 male children, 30 female children, the largest of which 9 years old, the youngest two months, infants less than 1 year old, 90 people;suffering from bronchial pneumonia, 90 cases, 21 cases of pneumonia, wheezing, 3 cases of bronchitis, the average length of stay for about a week;improved in 79 cases, 33 cases were cured, 2 cases transferred to higher level hospitals. All children with throat congestion, swollen tonsils, lung breath sounds rough, smell and moist rales. 114 penicillin-resistant Streptococcus pneumoniae was 64.9%, erythromycin 97.4%, clindamycin 86.8%, tetracycline 87.7%, trimethoprim-sulfamethoxazole 82.5%, amoxicillin 21.9%, cefotaxime 49.1%, chloramphenicol 10.5%, was not found to levofloxacin and van-comycin. Conclusion: Penicillin, erythromycin, and clindamycin are not as pneumococcal pneumonia in children experience preferred medi-cation in children less than one year old child could easily cause lung chain Streptococcus pneumoniae. Therefore, the antimicrobial resistance of Streptococcus pneumoniae analysis provides a reference for experi-enced clinicians to adjust medication.展开更多
基金supported in part by the Natural Science Foundation of China(NSFC)underGrant No.51805192,Major Special Science and Technology Project of Hubei Province under Grant No.2020AEA009sponsored by the State Key Laboratory of Digital Manufacturing Equipment and Technology(DMET)of Huazhong University of Science and Technology(HUST)under Grant No.DMETKF2020029.
文摘Pneumonia is part of the main diseases causing the death of children.It is generally diagnosed through chest Xray images.With the development of Deep Learning(DL),the diagnosis of pneumonia based on DL has received extensive attention.However,due to the small difference between pneumonia and normal images,the performance of DL methods could be improved.This research proposes a new fine-grained Convolutional Neural Network(CNN)for children’s pneumonia diagnosis(FG-CPD).Firstly,the fine-grainedCNNclassificationwhich can handle the slight difference in images is investigated.To obtain the raw images from the real-world chest X-ray data,the YOLOv4 algorithm is trained to detect and position the chest part in the raw images.Secondly,a novel attention network is proposed,named SGNet,which integrates the spatial information and channel information of the images to locate the discriminative parts in the chest image for expanding the difference between pneumonia and normal images.Thirdly,the automatic data augmentation method is adopted to increase the diversity of the images and avoid the overfitting of FG-CPD.The FG-CPD has been tested on the public Chest X-ray 2017 dataset,and the results show that it has achieved great effect.Then,the FG-CPD is tested on the real chest X-ray images from children aged 3–12 years ago from Tongji Hospital.The results show that FG-CPD has achieved up to 96.91%accuracy,which can validate the potential of the FG-CPD.
文摘Studies showed that exclusive breast feeding reduced infant morbidity and mortality. In low income countries such as Ethiopia where under-five mortality is very high, the role of exclusively breastfeeding could be even more critical. However, studies assessing the place of exclusive breast freeing in the prevention of childhood illnesses in our area are scarce. The aim of the study was to identify determinant factors of childhood pneumonia and diarrhoea. An institution based case control study was conducted in Achefer District in July, 2012. The cases were 122 children of 7 - 24 months old who had repeated attack of diarrhoea or pneumonia over three months prior to the survey while controls were 122 children who visited well baby clinic for vaccination. Data were collected by using pre-tested and structured questionnaire, and analysed using SPSS version 16 for windows. Logistic regression was performed, and strength of associations was estimated using odds ratio and 95% confidence interval. About 83% of the controls and only 12.3% of the cases were exclusively breast fed. Children who were exclusively breast fed were 83 times less likely to develop pneumonia or diarrhea than those who were not exclusively fed. Marital status, monthly income, prelacteal feeding, and late initiation of breast feeding were found to have statistically significant association with childhood diarrhea and pneumonia. This study brought local evidence that exclusive breast feeding had a protective effect against common childhood infectious diseases—pneumonia and diarrhoea—in the study area. Therefore, culture sensitive and plausible health education is recommended to strengthen exclusive breast feeding practices in order to decrease mortality and morbidity of infants and children from pneumonia and diarrhoea.
文摘Objective: To analyze the causes of childhood pneumonia Streptococcus pneumoniae resistance and clinical characteristics, and provide a basis for better and timely clinical therapy, and medication to reduce blind-ness. Methods: MIC method in our hospital 114 under 2020 pediatric pneumococcal respiratory infection in children with lower respiratory tract specimens were isolated antimicrobial susceptibility testing, and analyzed retrospectively. Results: 84 male children, 30 female children, the largest of which 9 years old, the youngest two months, infants less than 1 year old, 90 people;suffering from bronchial pneumonia, 90 cases, 21 cases of pneumonia, wheezing, 3 cases of bronchitis, the average length of stay for about a week;improved in 79 cases, 33 cases were cured, 2 cases transferred to higher level hospitals. All children with throat congestion, swollen tonsils, lung breath sounds rough, smell and moist rales. 114 penicillin-resistant Streptococcus pneumoniae was 64.9%, erythromycin 97.4%, clindamycin 86.8%, tetracycline 87.7%, trimethoprim-sulfamethoxazole 82.5%, amoxicillin 21.9%, cefotaxime 49.1%, chloramphenicol 10.5%, was not found to levofloxacin and van-comycin. Conclusion: Penicillin, erythromycin, and clindamycin are not as pneumococcal pneumonia in children experience preferred medi-cation in children less than one year old child could easily cause lung chain Streptococcus pneumoniae. Therefore, the antimicrobial resistance of Streptococcus pneumoniae analysis provides a reference for experi-enced clinicians to adjust medication.
