Objective To assess the consistency of diagnostic results using optical coherence tomography angiography(OCTA) and fundus fluorescein angiography(FFA) in the central retinal vein occlusion(CRVO). Methods A retrospective case series of 26 eyes of 26 patients with CRVO. Simultaneous OCTA and FFA were performed in all patients by using 7-standard field of ETDRS to evaluate the microaneurysms, nonperfused areas, optical disc/retinal neovascularization and macular edema. The consistency was evaluated using weightedKappa statistic values.Kappa≥0.75, consistency is excellent; 0.60≤Kappa＜0.75, consistency is good; 0.40≤Kappa＜0.60, consistency is general;Kappa＜0.40, consistency is poor. Results Examined by OCTA, microaneurysms were found in 23 eyes, nonperfused areas in 16 eyes, optical disc/retinal neovascularization in 8 eyes and macular edema in 21eyes. Performed with FFA, 23 eyes were diagnosed to have microaneurysms, 16 eyes have nonperfused, 8 eyes have optical disc/retinal neovascularization, 22 eyes have macular edema. The consistency was excellent for microaneurysms(Kappa=0.772，P<0.01) and optical disc/retinal neovascularization(Kappa=0.766，P<0.01), good for nonperfused areas (Kappa=0.703，P<0.01) and macular edema(Kappa=0.60，P<0.01). Conclusion There is high consistency between OCTA and FFA in the diagnosis of CRVO, OCTA is an effective method in the examination of CRVO.
Lung cancer is the most threatening tumor disease to human health. Early detection is crucial to improve the survival rate and recovery rate of lung cancer patients. Existing methods use the two-dimensional multi-view framework to learn lung nodules features and simply integrate multi-view features to achieve the classification of benign and malignant lung nodules. However, these methods suffer from the problems of not capturing the spatial features effectively and ignoring the variability of multi-views. Therefore, this paper proposes a three-dimensional (3D) multi-view convolutional neural network (MVCNN) framework. To further solve the problem of different views in the multi-view model, a 3D multi-view squeeze-and-excitation convolution neural network (MVSECNN) model is constructed by introducing the squeeze-and-excitation (SE) module in the feature fusion stage. Finally, statistical methods are used to analyze model predictions and doctor annotations. In the independent test set, the classification accuracy and sensitivity of the model were 96.04% and 98.59% respectively, which were higher than other state-of-the-art methods. The consistency score between the predictions of the model and the pathological diagnosis results was 0.948, which is significantly higher than that between the doctor annotations and the pathological diagnosis results. The methods presented in this paper can effectively learn the spatial heterogeneity of lung nodules and solve the problem of multi-view differences. At the same time, the classification of benign and malignant lung nodules can be achieved, which is of great significance for assisting doctors in clinical diagnosis.
The gait acquisition system can be used for gait analysis. The traditional wearable gait acquisition system will lead to large errors in gait parameters due to different wearing positions of sensors. The gait acquisition system based on marker method is expensive and needs to be used by combining with the force measurement system under the guidance of rehabilitation doctors. Due to the complex operation, it is inconvenient for clinical application. In this paper, a gait signal acquisition system that combines foot pressure detection and Azure Kinect system is designed. Fifteen subjects are organized to participate in gait test, and relevant data are collected. The calculation method of gait spatiotemporal parameters and joint angle parameters is proposed, and the consistency analysis and error analysis of the gait parameters of proposed system and camera marking method are carried out. The results show that the parameters obtained by the two systems have good consistency (Pearson correlation coefficient r ≥ 0.9, P < 0.05) and have small error (root mean square error of gait parameters is less than 0.1, root mean square error of joint angle parameters is less than 6). In conclusion, the gait acquisition system and its parameter extraction method proposed in this paper can provide reliable data acquisition results as a theoretical basis for gait feature analysis in clinical medicine.