Lung cancer is one of the malignant tumors with the greatest threat to human health, and studies have shown that some genes play an important regulatory role in the occurrence and development of lung cancer. In this paper, a LightGBM ensemble learning method is proposed to construct a prognostic model based on immune relate gene (IRG) profile data and clinical data to predict the prognostic survival rate of lung adenocarcinoma patients. First, this method used the Limma package for differential gene expression, used CoxPH regression analysis to screen the IRG to prognosis, and then used XGBoost algorithm to score the importance of the IRG features. Finally, the LASSO regression analysis was used to select IRG that could be used to construct a prognostic model, and a total of 17 IRG features were obtained that could be used to construct model. LightGBM was trained according to the IRG screened. The K-means algorithm was used to divide the patients into three groups, and the area under curve (AUC) of receiver operating characteristic (ROC) of the model output showed that the accuracy of the model in predicting the survival rates of the three groups of patients was 96%, 98% and 96%, respectively. The experimental results show that the model proposed in this paper can divide patients with lung adenocarcinoma into three groups [5-year survival rate higher than 65% (group 1), lower than 65% but higher than 30% (group 2) and lower than 30% (group 3)] and can accurately predict the 5-year survival rate of lung adenocarcinoma patients.
The poor mechanical property and vulnerability to bacterial infections are the main problems in clinic for dental restoration resins. Based on this problem, the purpose of this study is to synthesize silver-titanium dioxide (Ag-TiO2) nanoparticles with good photocatalytic properties, and add them to the composite resin to improve the mechanical properties and photocatalytic antibacterial capability of the resin. The microstructure and chemical composition of Ag-TiO2 nanoparticles and composite resins were characterized. The results indicated that Ag existed in both metallic and silver oxide state in the Ag-TiO2, and Ag-TiO2 nanoparticles were uniformly dispersed in the resins. The results of mechanical experiments suggested that the mechanical properties of the composite resin were significantly improved due to the incorporation of Ag-TiO2 nanoparticles. The antibacterial results indicated that the Ag-TiO2 nanoparticle-filled composite resins exhibited excellent antibacterial activities under 660 nm light irradiation for 10 min due to the photocatalysis, and the Ag-TiO2 nanoparticle-filled composite resins could also exhibit excellent antibacterial activities after contact with bacteria for 24 h without light irradiation because of the release of Ag ions. In summary, this study provides a new antibacterial idea for the field of dental composite resins.
Objective To study the retinal light sensitivity of central visual field in normal children. Methods The QZS-Ⅱ automated perimetry was used to assess the visual field of centro-30deg;and centro-6deg; in normal or ametropic eyes in 60 eyes of 5～9 years old children. Results The mean sensitivity(MS)was not influenced by sex,age and laterality and ametropia of the eye.The normal type of dB distribution was obviously higher than the abnormal(P＜0.01).We set normal range as 30deg;MS＞19.3 dB, 6deg;MS＞22.5 dB.The abnormality of value or distribution didnprime;t appear in the same field. Conclusions In normal children,the dB distribution of visual field was mainly of the normal type.We suggest that in evaluating function of visual filed of the children,the dB distribution of centro-30deg;and centro-6deg;field and the value of MS should be included. (Chin J Ocul Fundus Dis, 1999, 15: 137-138)
PURPOSE:In search of the mechanism for photic retinal injury. METHODS:A visible light damage model was established in the primary cultured healthy,adult human RPE cells by using intense fluorescence light (2 400 Lx). RESULTS:Electron microscopy revealed swelling of the mitochondria and obscurity of nuclear membranous structure in the light damaged cells. The decrease or dissolution of organelle,vacuolization of cytoplasm and myelinic degeneration were found in some severely damaged cells. The level of intracellular SOD was decreased to 41% of that of the controls (P＜0.05). CONCLUSION:The structure of the RPE was damaged by the light radiation and the level of intracellular SOD was decreased. These suggested the light damage might be associated with the production of free radicals and the lipid perioxide reaction in membranous structure of cell. （Chin J Ocul Fundus Dis,1996,12: 174-175 ）
Objective To evaluate the efficacy of light cured composite resin and glass ionomer cement for wedge shaped defect filling. Methods PubMed, The Cochrane Library (Issue 3, 2016), EMbase, CNKI, CBM, VIP and WanFang Data were searched from inception to April 5th 2016, to collect randomized controlled trials (RCTs) of light cured composite resin versus glass ionomer cement for wedge shaped defect filling. According to the inclusion and exclusion criteria, two reviewers independently screened literature, extracted data and assessed the risk of bias of included studies. Then, meta-analysis was performed by RevMan 5.2 software. Results A total of 12 studies, involving 3 744 cases of teeth were included. Meta-analysis results showed that there was no significant difference in the two groups on the shedding rate after 2 years (OR=1.19, 95%CI 0.70 to 2.02,P=0.53). But the wear rate of the light cured composite resin group was significantly lower than that of the glass ionomer cement group (Peto OR=0.31, 95%CI 0.22 to 0.44,P<0.000 01). The light cured composite resin group had higher rate of micro leakage or secondary caries rate (OR=1.83, 95%CI 1.11 to 3.01,P=0.02) and incidence of endodontic or periapical lesions (Peto OR=2.84, 95%CI 1.82 to 4.45,P<0.000 01) than the glass ionomer cement group. Conclusion Glass ionomer cement for filling wedge-shaped defects of 2 years after the wear degree is higher than the light cured composite resin, but the occurrence probability of micro leakage or secondary caries and stimulation to pulp are lower than the light cured composite resin. Because of the limitations of the quality of the included studies, the above conclusion still needs to be verified by more high-quality studies.
Existing classification methods for myositis ultrasound images have problems of poor classification performance or high computational cost. Motivated by this difficulty, a lightweight neural network based on a soft threshold attention mechanism is proposed to cater for a better IIMs classification. The proposed network was constructed by alternately using depthwise separable convolution (DSC) and conventional convolution (CConv). Moreover, a soft threshold attention mechanism was leveraged to enhance the extraction capabilities of key features. Compared with the current dual-branch feature fusion myositis classification network with the highest classification accuracy, the classification accuracy of the network proposed in this paper increased by 5.9%, reaching 96.1%, and its computational complexity was only 0.25% of the existing method. The obtained results support that the proposed method can provide physicians with more accurate classification results at a lower computational cost, thereby greatly assisting them in their clinical diagnosis.
Objective:To observe the inhibited effect and its mechani sm of estro gen on lightinduced apoptosis of retinal photoreceptor cells. Methods:Twenty female Sprague-Dawley rats were randomly divided into two groups: ovariectomized (OV) group and OV and estrogen (E2) replacement (OV+E2) group, with 10 rats in each group. All of the rats were exposed to the cyclic illumination under 12 hou r light and 12 hour dark condition with the light intensity of (600plusmn;35.4) lx ( a total of 14 times). All of the right eyes were extracted and the thickness of r etinal outer nuclear layer (ONL) was measured. Terminal deoxynucleotidyl Transfe rasemediated dUTP nick end labeling (TUNEL) method was used to evaluate positi v e apoptosis cells in ONL. The expression of nitric oxide synthase (NOS) in retin al cells was detected by immunohistochemistry with image analysis method. Results:The thickness of ONL in OV group was obviously thinner than that in the OV+ E2 group. The number of positive apoptosis of the cells was (0.0275plusmn;0.0069) c el ls/mu;m2 in OV group and (0.0162plusmn;0.0054) cells/mu;m2 in OV+E2group; the di fferen ce between the two groups was significant (t=4.1370，P=0.0012). The values o f in tegral optical density of NOS positively stained cells in retinal inner nuclear layer was (0.3675plusmn;0.0662) in the OV group and (0.2941plusmn;0.0350) in OV+E2 group ; the difference between the two groups was significant (t=3.4885, P=0.0031). Conclusion:Estrogen can protect retina from light injuries by regu lating NOS synthesis and inhibiting apoptosis of photoreceptor cells.
Medical image registration plays an important role in medical diagnosis and treatment planning. However, the current registration methods based on deep learning still face some challenges, such as insufficient ability to extract global information, large number of network model parameters, slow reasoning speed and so on. Therefore, this paper proposed a new model LCU-Net, which used parallel lightweight convolution to improve the ability of global information extraction. The problem of large number of network parameters and slow inference speed was solved by multi-scale fusion. The experimental results showed that the Dice coefficient of LCU-Net reached 0.823, the Hausdorff distance was 1.258, and the number of network parameters was reduced by about one quarter compared with that before multi-scale fusion. The proposed algorithm shows remarkable advantages in medical image registration tasks, and it not only surpasses the existing comparison algorithms in performance, but also has excellent generalization performance and wide application prospects.
ObjectiveTo observe the diagnostic value of six classification intelligent auxiliary diagnosis lightweight model for common fundus diseases based on fundus color photography. MethodsA applied research. A dataset of 2 400 color fundus images from Nanjing Medical University Eye Hospital and Zhejiang Mathematical Medical Society Smart Eye Database was collected, which was desensitized and labeled by a fundus specialist. Of these, 400 each were for diabetic retinopathy, glaucoma, retinal vein occlusion, high myopia, age-related macular degeneration, and normal fundus. The parameters obtained from the classical classification models VGGNet16, ResNet50, DenseNet121 and lightweight classification models MobileNet3, ShuffleNet2, GhostNet trained on the ImageNet dataset were migrated to the six-classified common fundus disease intelligent aid diagnostic model using a migration learning approach during training as initialization parameters for training to obtain the latest model. 1 315 color fundus images of clinical patients were used as the test set. Evaluation metrics included sensitivity, specificity, accuracy, F1-Score and agreement of diagnostic tests (Kappa value); comparison of subject working characteristic curves as well as area under the curve values for different models. ResultCompared with the classical classification model, the storage size and number of parameters of the three lightweight classification models were significantly reduced, with ShuffleNetV2 having an average recognition time per sheet 438.08 ms faster than the classical classification model VGGNet16. All 3 lightweight classification models had Accuracy > 80.0%; Kappa values > 70.0% with significant agreement; sensitivity, specificity, and F1-Score for the diagnosis of normal fundus images were ≥ 98.0%; Macro-F1 was 78.2%, 79.4%, and 81.5%, respectively. ConclusionThe intelligent assisted diagnosis of common fundus diseases based on fundus color photography is a lightweight model with high recognition accuracy and speed; the storage size and number of parameters are significantly reduced compared with the classical classification model.
PURPOSE:To evaluate the activitv of protein kinase C(PKC) in response to retinal photochemical insult in rat. Furthermore, to investigate the effect of dexamethasone(DXM ) on PKC activity. METHODS :The experiments were performed on 48 SI') rats whieh were separated into two groups,control and treated groups,and the latter received daily intraperitoneal injections of DXM (1 mg/kg)for 5 consecutive days,starting 3 days before light exposure. The animals were continually exposed to green fluorescent light (510nm~560nm) with an illuminance level of (1 900plusmn;106.9)lx for 24 hrs.The retinal enzyme activity of PKC was tested at 6 hrs,1 day,3 days,7 days,and 14 days after light exposure respectively. RESULTS:In animal models,PKC activity showed a transient increase in both groups at 6 hrs after light exposure and then decrease persistently there alter. The activity of PKC was unresponsive to DXM intervention. CONCLUSIONS :These results suggested that the persistent lower PKC activity might result in disturbance of retinal function in rat retinal photochemical injury. （Chin J Ocul Fundus Dis,1997,13: 78-80）