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.
OBJECTIVE:To investigate the value of psychophysical testing for the macular function in the diegnosis of diabetic retinopathy(DR). METHODS:To compare the testing results of macular light sensitivity and pattern visual evoked potential(P-VEP)of 30 eyes of 15 normal person with those of 82 eyes of 41 diabetic patients(27 eyes without DR,55 eyes with simple type DR ). RESULTS:The macular light sensitivity of diabetic patients is much lower than that of normal Control group(plt;0.05). In the diabetic group, 62.19% is abnormal in macular light sensitivity, 69.51% in P-VEP. CONCLUSION: Testing of macular light sensitivit y is helpful in finding of diabetic retinopathy and early deterioration of macular visual function in diabetics. （Chin J Ocul Fundus Dis,1996,12: 223-224）
Illumimaton intensities of 6 indirect opthalmoscopes and 5 slit lamps were measured and calculated. The results showed the retinal irradiance from these instruments is quite high with dilated pupils ahd clear media. Although such illuminating intensity is a potential risk factor for the human retina, with careful use and reduced intensity, they are relatively safe. We suggest that ophthalmologists try their best to avoid using brighter source beyond useful illumination and unnecessary wide slit. （Chin J Ocul Fundus Dis,1992,8:133-137）
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.
Wistar rats weaned were raised through 10 weeks under cyclic illumination of 12 hours light and 12 hours darkness,with four different fluorescent colour lighting condition:75 lx and 300lx blue light,300 lux white and 300lux pink light to study the change of superoxide dismutases(SOD)and lipid peroxied(LPO)in the retina.This paper shows that photic oxidative reaction reduces SOD in the retina and oxidizes polyunsaturated fatty acids to become LPO and that complex visible light oxidizes retina easier than simple wave lengths visible light does.The shorter the wave lengths of visible light is and the brighter the illumination is the more serious the oxidative damage of the retina is. （Chin J Ocul Fundus Dis,1993,9:14-16）
Animal localization and trajectory tracking are of great value for the study of brain spatial cognition and navigation neural mechanisms. However, traditional optical lens video positioning techniques are limited in their scope due to factors such as camera perspective. For pigeons with excellent spatial cognition and navigation abilities, based on the beacon positioning technology, a three-dimensional (3D) trajectory positioning and tracking method suitable for large indoor spaces was proposed, and the corresponding positioning principle and hardware structure were provided. The results of in vitro and in vivo experiments showed that the system could achieve centimeter-level positioning and trajectory tracking of pigeons in a space of 360 cm × 200 cm × 245 cm. Compared with traditional optical lens video positioning techniques, this system has the advantages of large space, high precision, and high response speed. It not only helps to study the neural mechanisms of pigeon 3D spatial cognition and navigation, but also has high reference value for trajectory tracking of other animals.
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.
To address the issue of a large number of network parameters and substantial floating-point operations in deep learning networks applied to image segmentation for cardiac magnetic resonance imaging (MRI), this paper proposes a lightweight dilated parallel convolution U-Net (DPU-Net) to decrease the quantity of network parameters and the number of floating-point operations. Additionally, a multi-scale adaptation vector knowledge distillation (MAVKD) training strategy is employed to extract latent knowledge from the teacher network, thereby enhancing the segmentation accuracy of DPU-Net. The proposed network adopts a distinctive way of convolutional channel variation to reduce the number of parameters and combines with residual blocks and dilated convolutions to alleviate the gradient explosion problem and spatial information loss that might be caused by the reduction of parameters. The research findings indicate that this network has achieved considerable improvements in reducing the number of parameters and enhancing the efficiency of floating-point operations. When applying this network to the public dataset of the automatic cardiac diagnosis challenge (ACDC), the dice coefficient reaches 91.26%. The research results validate the effectiveness of the proposed lightweight network and knowledge distillation strategy, providing a reliable lightweighting idea for deep learning in the field of medical image segmentation.
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)
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.