Microaneurysm is the initial symptom of diabetic retinopathy. Eliminating this lesion can effectively prevent diabetic retinopathy in the early stage. However, due to the complex retinal structure and the different brightness and contrast of fundus image because of different factors such as patients, environment and acquisition equipment, the existing detection algorithms are difficult to achieve the accurate detection and location of the lesion. Therefore, an improved detection algorithm of you only look once (YOLO) v4 with Squeeze-and-Excitation networks (SENet) embedded was proposed. Firstly, an improved and fast fuzzy c-means clustering algorithm was used to optimize the anchor parameters of the target samples to improve the matching degree between the anchors and the feature graphs; Then, the SENet attention module was embedded in the backbone network to enhance the key information of the image and suppress the background information of the image, so as to improve the confidence of microaneurysms; In addition, an spatial pyramid pooling was added to the network neck to enhance the acceptance domain of the output characteristics of the backbone network, so as to help separate important context information; Finally, the model was verified on the Kaggle diabetic retinopathy dataset and compared with other methods. The experimental results showed that compared with other YOLOv4 network models with various structures, the improved YOLOv4 network model could significantly improve the automatic detection results such as F-score which increased by 12.68%; Compared with other network models and methods, the automatic detection accuracy of the improved YOLOv4 network model with SENet embedded was obviously better, and accurate positioning could be realized. Therefore, the proposed YOLOv4 algorithm with SENet embedded has better performance, and can accurately and effectively detect and locate microaneurysms in fundus images.
Network meta-analysis may be performed by fitting multivariate meta-analysis models with Stata software mvmeta command; however, there are various challenges such as preprocessing the data, parameterising the model, and making good graphical displays of results. A suite of Stata programs, network, may meet these challenges. In this article, we introduce how to use the network commands to implement network meta-analysis by the example of continuous data.
Multi-layer perceptron (MLP) neural network belongs to multi-layer feedforward neural network, and has the ability and characteristics of high intelligence. It can realize the complex nonlinear mapping by its own learning through the network. Bipolar disorder is a serious mental illness with high recurrence rate, high self-harm rate and high suicide rate. Most of the onset of the bipolar disorder starts with depressive episode, which can be easily misdiagnosed as unipolar depression and lead to a delayed treatment so as to influence the prognosis. The early identification of bipolar disorder is of great importance for patients with bipolar disorder. Due to the fact that the process of early identification of bipolar disorder is nonlinear, we in this paper discuss the MLP neural network application in early identification of bipolar disorder. This study covered 250 cases, including 143 cases with recurrent depression and 107 cases with bipolar disorder, and clinical features were statistically analyzed between the two groups. A total of 42 variables with significant differences were screened as the input variables of the neural network. Part of the samples were randomly selected as the learning sample, and the other as the test sample. By choosing different neural network structures, all results of the identification of bipolar disorder were relatively good, which showed that MLP neural network could be used in the early identification of bipolar disorder.
In recent years, exploring the physiological and pathological mechanisms of brain functional integration from the neural network level has become one of the focuses of neuroscience research. Due to the non-stationary and nonlinear characteristics of neural signals, its linear characteristics are not sufficient to fully explain the potential neurophysiological activity mechanism in the implementation of complex brain functions. In order to overcome the limitation that the linear algorithm cannot effectively analyze the nonlinear characteristics of signals, researchers proposed the transfer entropy (TE) algorithm. In recent years, with the introduction of the concept of brain functional network, TE has been continuously optimized as a powerful tool for nonlinear time series multivariate analysis. This paper first introduces the principle of TE algorithm and the research progress of related improved algorithms, discusses and compares their respective characteristics, and then summarizes the application of TE algorithm in the field of electrophysiological signal analysis. Finally, combined with the research progress in recent years, the existing problems of TE are discussed, and the future development direction is prospected.
The construction of brain functional network based on resting-state functional magnetic resonance imaging (fMRI) is an effective method to reveal the mechanism of human brain operation, but the common brain functional network generally contains a lot of noise, which leads to wrong analysis results. In this paper, the least absolute shrinkage and selection operator (LASSO) model in compressed sensing is used to reconstruct the brain functional network. This model uses the sparsity of L1-norm penalty term to avoid over fitting problem. Then, it is solved by the fast iterative shrinkage-thresholding algorithm (FISTA), which updates the variables through a shrinkage threshold operation in each iteration to converge to the global optimal solution. The experimental results show that compared with other methods, this method can improve the accuracy of noise reduction and reconstruction of brain functional network to more than 98%, effectively suppress the noise, and help to better explore the function of human brain in noisy environment.
The in-vivo electron paramagnetic resonance (EPR) method can be used for on-site, rapid, and non-invasive detection of radiation dose to casualties after nuclear and radiation emergencies. For in-vivo EPR spectrum analysis, manual labeling of peaks and calculation of signal intensity are often used, which have problems such as large workload and interference by subjective factors. In this study, a method for automatic classification and identification of in-vivo EPR spectra was established using support vector machine (SVM) technology, which can in-batch and automatically identify and screen out invalid spectra due to vibration and dental surface water interference during in-vivo EPR measurements. In this study, a spectrum analysis method based on genetic algorithm optimization neural network (GA-BPNN) was established, which can automatically identify the radiation-induced signals in in-vivo EPR spectra and predict the radiation doses received by the injured. The experimental results showed that the SVM and GA-BPNN spectrum processing methods established in this study could effectively accomplish the automatic spectra classification and radiation dose prediction, and could meet the needs of dose assessment in nuclear emergency. This study explored the application of machine learning methods in EPR spectrum processing, improved the intelligence level of EPR spectrum processing, and would help to enhance the efficiency of mass EPR spectra processing.
The background of abdominal computed tomography (CT) images is complex, and kidney tumors have different shapes, sizes and unclear edges. Consequently, the segmentation methods applying to the whole CT images are often unable to effectively segment the kidney tumors. To solve these problems, this paper proposes a multi-scale network based on cascaded 3D U-Net and DeepLabV3+ for kidney tumor segmentation, which uses atrous convolution feature pyramid to adaptively control receptive field. Through the fusion of high-level and low-level features, the segmented edges of large tumors and the segmentation accuracies of small tumors are effectively improved. A total of 210 CT data published by Kits2019 were used for five-fold cross validation, and 30 CT volume data collected from Suzhou Science and Technology Town Hospital were independently tested by trained segmentation models. The results of five-fold cross validation experiments showed that the Dice coefficient, sensitivity and precision were 0.796 2 ± 0.274 1, 0.824 5 ± 0.276 3, and 0.805 1 ± 0.284 0, respectively. On the external test set, the Dice coefficient, sensitivity and precision were 0.817 2 ± 0.110 0, 0.829 6 ± 0.150 7, and 0.831 8 ± 0.116 8, respectively. The results show a great improvement in the segmentation accuracy compared with other semantic segmentation methods.
Electrical impedance tomography (EIT) plays a crucial role in the monitoring of pulmonary ventilation and regional pulmonary function test. However, the inherent ill-posed nature of EIT algorithms results in significant deviations in the reconstructed conductivity obtained from voltage data contaminated with noise, making it challenging to obtain accurate distribution images of conductivity change as well as clear boundary contours. In order to enhance the image quality of EIT in lung ventilation monitoring, a novel approach integrating the EIT with deep learning algorithm was proposed. Firstly, an optimized operator was introduced to enhance the Kalman filter algorithm, and Tikhonov regularization was incorporated into the state-space expression of the algorithm to obtain the initial lung image reconstructed. Following that, the imaging outcomes were fed into a generative adversarial network model in order to reconstruct accurate lung contours. The simulation experiment results indicate that the proposed method produces pulmonary images with clear boundaries, demonstrating increased robustness against noise interference. This methodology effectively achieves a satisfactory level of visualization and holds potential significance as a reference for the diagnostic purposes of imaging modalities such as computed tomography.
In order to more accurately and effectively understand the intermuscular coupling of different temporal and spatial levels from the perspective of complex networks, a new multi-scale intermuscular coupling network analysis method was proposed in this paper. The multivariate variational modal decomposition (MVMD) and Copula mutual information (Copula MI) were combined to construct an intermuscular coupling network model based on MVMD-Copula MI, and the characteristics of intermuscular coupling of multiple muscles of upper limbs in different time-frequency scales during reaching exercise in healthy subjects were analyzed by using the network parameters such as node strength and clustering coefficient. The experimental results showed that there are obvious differences in the characteristics of intermuscular coupling in the six time-frequency scales. Specifically, the triceps brachii (TB) had relatively high coupling strength with the middle deltoid (MD) and posterior deltoid (PD), and the intermuscular function was closely connected. However, the biceps brachii (BB) was independent of other muscles. The intermuscular coupling network had scale differences. MVMD-Copula MI can quantitatively describe the relationship of multi-scale intermuscular coupling strength, which has good application prospects.
Existing near-infrared non-invasive blood glucose detection modelings mostly detect multi-spectral signals with different wavelength, which is not conducive to the popularization of non-invasive glucose meter at home and does not consider the physiological glucose dynamics of individuals. In order to solve these problems, this study presented a non-invasive blood glucose detection model combining particle swarm optimization (PSO) and artificial neural network (ANN) by using the 1 550 nm near-infrared absorbance as the independent variable and the concentration of blood glucose as the dependent variable, named as PSO-2ANN. The PSO-2ANN model was based on two sub-modules of neural networks with certain structures and arguments, and was built up after optimizing the weight coefficients of the two networks by particle swarm optimization. The results of 10 volunteers were predicted by PSO-2ANN. It was indicated that the relative error of 9 volunteers was less than 20%; 98.28% of the predictions of blood glucose by PSO-2ANN were distributed in the regions A and B of Clarke error grid, which confirmed that PSO-2ANN could offer higher prediction accuracy and better robustness by comparison with ANN. Additionally, even the physiological glucose dynamics of individuals may be different due to the influence of environment, temper, mental state and so on, PSO-2ANN can correct this difference only by adjusting one argument. The PSO-2ANN model provided us a new prospect to overcome individual differences in blood glucose prediction.