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.
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.
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.
The convolutional neural network (CNN) could be used on computer-aided diagnosis of lung tumor with positron emission tomography (PET)/computed tomography (CT), which can provide accurate quantitative analysis to compensate for visual inertia and defects in gray-scale sensitivity, and help doctors diagnose accurately. Firstly, parameter migration method is used to build three CNNs (CT-CNN, PET-CNN, and PET/CT-CNN) for lung tumor recognition in CT, PET, and PET/CT image, respectively. Then, we aimed at CT-CNN to obtain the appropriate model parameters for CNN training through analysis the influence of model parameters such as epochs, batchsize and image scale on recognition rate and training time. Finally, three single CNNs are used to construct ensemble CNN, and then lung tumor PET/CT recognition was completed through relative majority vote method and the performance between ensemble CNN and single CNN was compared. The experiment results show that the ensemble CNN is better than single CNN on computer-aided diagnosis of lung tumor.
The pathogenesis of Alzheimer's disease (AD), a common neurodegenerative disease, is still unknown. It is difficult to determine the atrophy areas, especially for patients with mild cognitive impairment (MCI) at different stages of AD, which results in a low diagnostic rate. Therefore, an early diagnosis model of AD based on 3-dimensional convolutional neural network (3DCNN) and genetic algorithm (GA) was proposed. Firstly, the 3DCNN was used to train a base classifier for each region of interest (ROI). And then, the optimal combination of the base classifiers was determined with the GA. Finally, the ensemble consisting of the chosen base classifiers was employed to make a diagnosis for a patient and the brain regions with significant classification capability were decided. The experimental results showed that the classification accuracy was 88.6% for AD vs. normal control (NC), 88.1% for MCI patients who will convert to AD (MCIc) vs. NC, and 71.3% for MCI patients who will not convert to AD (MCInc) vs. MCIc. In addition, with the statistical analysis of the behavioral domains corresponding to ROIs (i.e. brain regions), besides left hippocampus, medial and lateral amygdala, and left para-hippocampal gyrus, anterior superior temporal sulcus of middle temporal gyrus and dorsal area 23 of cingulate gyrus were also found with GA. It is concluded that the functions of the selected brain regions mainly are relevant to emotions, memory, cognition and the like, which is basically consistent with the symptoms of indifference, memory losses, mobility decreases and cognitive declines in AD patients. All of these show that the proposed method is effective.
The impeller, as a key component of artificial heart pumps, experiences high shear stress due to its rapid rotation, which may lead to hemolysis. To enhance the hemolytic performance of artificial heart pumps and identify the optimal combination of blade parameters, an optimization design for existing pump blades is conducted. The number of blades, outlet angle, and blade thickness were selected as design variables, with the maximum shear stress within the pump serving as the optimization objective. A back propagation (BP) neural network prediction model was established using existing simulation data, and a grey wolf optimization algorithm was employed to optimize the blade parameters. The results indicated that the optimized blade parameters consisted of 7 impeller blades, an outlet angle of 25 °, and a blade thickness of 1.2 mm; this configuration achieved a maximum shear stress value of 377 Pa—representing a reduction of 16% compared to the original model. Simulation analysis revealed that in comparison to the original model, regions with high shear stress at locations such as the outer edge, root, and base significantly decreased following optimization efforts, thus leading to marked improvements in hemolytic performance. The coupling algorithm employed in this study has significantly reduced the workload associated with modeling and simulation, while also enhancing the performance of optimization objectives. Compared to traditional optimization algorithms, it demonstrates distinct advantages, thereby providing a novel approach for investigating parameter optimization issues related to centrifugal artificial heart pumps.
Electrocardiogram (ECG) is a noninvasive, inexpensive, and convenient test for diagnosing cardiovascular diseases and assessing the risk of cardiovascular events. Although there are clear standardized operations and procedures for ECG examination, the interpretation of ECG by even trained physicians can be biased due to differences in diagnostic experience. In recent years, artificial intelligence has become a powerful tool to automatically analyze medical data by building deep neural network models, and has been widely used in the field of medical image diagnosis such as CT, MRI, ultrasound and ECG. This article mainly introduces the application progress of deep neural network models in ECG diagnosis and prediction of cardiovascular diseases, and discusses its limitations and application prospects.
A method was proposed to detect pulmonary nodules in low-dose computed tomography (CT) images by two-dimensional convolutional neural network under the condition of fine image preprocessing. Firstly, CT image preprocessing was carried out by image clipping, normalization and other algorithms. Then the positive samples were expanded to balance the number of positive and negative samples in convolutional neural network. Finally, the model with the best performance was obtained by training two-dimensional convolutional neural network and constantly optimizing network parameters. The model was evaluated in Lung Nodule Analysis 2016(LUNA16) dataset by means of five-fold cross validation, and each group's average model experiment results were obtained with the final accuracy of 92.3%, sensitivity of 92.1% and specificity of 92.6%.Compared with other existing automatic detection and classification methods for pulmonary nodules, all indexes were improved. Subsequently, the model perturbation experiment was carried out on this basis. The experimental results showed that the model is stable and has certain anti-interference ability, which could effectively identify pulmonary nodules and provide auxiliary diagnostic advice for early screening of lung cancer.
In order to overcome the shortcomings of high false positive rate and poor generalization in the detection of microcalcification clusters regions, this paper proposes a method combining discriminative deep belief networks (DDBNs) to automatically and quickly locate the regions of microcalcification clusters in mammograms. Firstly, the breast region was extracted and enhanced, and the enhanced breast region was segmented to overlapped sub-blocks. Then the sub-block was subjected to wavelet filtering. After that, DDBNs model for breast sub-block feature extraction and classification was constructed, and the pre-trained DDBNs was converted to deep neural networks (DNN) using a softmax classifier, and the network is fine-tuned by back propagation. Finally, the undetected mammogram was inputted to complete the location of suspicious lesions. By experimentally verifying 105 mammograms with microcalcifications from the Digital Database for Screening Mammography (DDSM), the method obtained a true positive rate of 99.45% and a false positive rate of 1.89%, and it only took about 16 s to detect a 2 888 × 4 680 image. The experimental results showed that the algorithm of this paper effectively reduced the false positive rate while ensuring a high positive rate. The detection of calcification clusters was highly consistent with expert marks, which provides a new research idea for the automatic detection of microcalcification clusters area in mammograms.