Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 2 de 2
Filter
Add filters








Language
Year range
1.
Chinese Journal of Nuclear Medicine and Molecular Imaging ; (6): 403-407, 2019.
Article in Chinese | WPRIM | ID: wpr-755283

ABSTRACT

Objective To develop a diagnostic model based on deep neural network for intelligent discrimination of thyroid function. Methods A total of 1616 patients ( 283 males, 1333 females, average age:52 years) who underwent thyroid imaging between May 2016 and June 2018 were selected. According to the clinical diagnosis, the 1616 cases included 299 normal thyroid cases, 876 hyperthyroidism cases and 441 hypothyroidism cases. Feature extraction and learning training were performed on 1000 training set sam-ples by two deep neural network models ( AlexNet;deep convolution generative adversarial networks ( DCGAN) ) using deep learning algorithm. Performance verifications were implemented on 616 test set samples. The con-sistency between the verification results of the two models and the clinical diagnosis was analyzed by Kappa test. Meanwhile, the time advantage of the intelligent diagnosis models was analyzed. Results The average diagnostic time of AlexNet model was 1 s/case, and the classification accuracy for normal thyroid, hyperthy-roidism, hypothyroidism were 82.29%(79/96), 94.62%(369/390), 100%(130/130), respectively. The Kappa value between results of AlexNet model and clinical diagnosis was 0.886 ( P<0.05) . The average di-agnostic time of DCGAN model was 1 s/case, and the classification accuracy for normal thyroid, hyperthy-roidism, hypothyroidism were 85.42%(82/96), 95.64%(373/390), 99.23%(129/130), respectively. The Kappa value between results of DCGAN model and clinical diagnosis was 0.904 ( P<0.05) . Conclusion The deep neural network intelligent diagnosis model can quickly determine the functional status of thyroid gland in thyroid imaging, and it has a high recognition accuracy, thus providing a new method for thyroid image review.

2.
International Journal of Traditional Chinese Medicine ; (6): 1059-1064, 2018.
Article in Chinese | WPRIM | ID: wpr-732844

ABSTRACT

Objective To explore the effect of sinomenine on the expression of tumor necrosis factor-α (TNF-α),cathepsin G (Cat-G) and cathepsin S (Cat-S) in rats with collagen induced arthritis (CIA).Methods The 60 SPF male Wistar rats were randomly divided into normal group,model group,high dose group,medium dose group,low dose group,and dexamethasone group (with 1 0 in each group).In the normal control group,the rats were given ordinary feed.For the other five groups,the rats were used to build a CIA model and give pharmacologic intervention in the following 20 days.After 20 days of inflammation,sinomenine would be divided into three different dose groups,with 120 mg/kg,90 mg/kg and 60 mg/kg,respectively,and each group was given a gavage daily.For the dexamethasone group,7.5 mg/kg dexamethasone was given for gavage once a day.In terms of the model group and normal group,the rats were perfused with the same volume of saline once daily.Then,taken the pictures of foot paw X-ray and foot paw pictures of rats in each group,measured the content of TNF-α,Cat-G,Cat-S in blood serum,observed the pathological changes in the synovial tissue of rats in each group by tissue section,measured the content of TNF-α,Cat-G,Cat-S in in spleen of rats by Immunohistochemical staining.Results The results of X-ray showed that there were obvious soft tissue swelling,joint deformity and osteolysis in the paws of the model group,and the above symptoms were alleviated in different degrees in each treatment group compared with the model group.Compared with the model group,the expression of TNF-α (376.48 ± 22.21 pg/ml,369.45 ± 82.68 pg/ml,425.17 ± 153.51 pg/ml vs.457.63 ± 152.67 pg/ml),Cat-G (1 398.05 ± 167.32 pg/ml,1 337.65 ± 209.34 pg/ml,1 412.78 ± 67.65 pg/ml vs.2 283.03 ± 185.21 pg/ml),and Cat-S (662.18 ± 169.66 pg/ml,406.80 ± 41.93 pg/ml,452.76 ± 50.49 pg/ml vs.838.11 ± 141.86 pg/ml) in blood serum of sinomenine high dose group,medium dose group and low dose group significantly decreased (P<0.05).The expression of TNF-α (0.28 ± 0.05,0.21 ± 0.03,0.34 ± 0.04 vs.0.50 ± 0.04),Cat-G (0.28 ± 0.02,0.18 ± 0.06,0.27 ± 0.02 vs.0.37 ± 0.03),and Cat-S (0.22 ± 0.02,0.18 ± 0.03,0.27 ± 0.02 vs.0.35 ± 0.03) in spleen tissue significantly decreased (P<0.05).The results of HE staining showed that the synovial tissue of normal rats was normal,the synovial tissue cells of model rats were damaged,the expression of inflammatory cells was significantly increased,and pannus hyperplasia was observed.Inflammatory cell infiltration and pannus hyperplasia were decreased in each group after administration.Conclusions Sinomenine has a sound and comprehensive intervention effect on rheumatoid arthritis,and the mechanism may be related to the inhibition of the expression ofTNF-α,Cat-G and Cat-S.

SELECTION OF CITATIONS
SEARCH DETAIL