Search

This work is aimed to develop the key algorithms used in medical robots, which can detect alcohol use disorder from structural magnetic resonance imaging of brains. We enrolled 30 alcoholic participants and 30 nonalcoholic participants. In the algorithm stage, we suggested to use Hu moment invariant to extract global features, and use single-hidden layer neural-network as the classifier. Afterwards, we proposed a novel predator–prey adaptive-inertia chaotic particle swarm optimization algorithm to train the classifier. The ten-fold stratified cross validation showed that our method achieves a sensitivity of 90.67 ± 3.16%, a specificity of 91.33 ± 3.06%, and an accuracy of 91.00 ± 1.41%. Our results are better than genetic algorithm, firefly algorithm, and particle swarm optimization. This proposes algorithm is effective in alcoholism detection. It can be installed on medical robots.

It is of enormous significance to detect abnormal brains automatically. This paper develops an efficient pathological brain detection system based on the artificial intelligence method. We first extract brain edges by a Canny edge detector. Next, we estimated the fractal dimension using box counting method with grid sizes of 1, 2, 4, 8, and 16, respectively. Afterward, we employed the single-hidden layer feedforward neural network. Finally, we proposed an improved particle swarm optimization based on three-segment particle representation, time-varying acceleration coefficient, and chaos theory. This three-segment particle representation encodes the weights, biases, and number of hidden neuron. The statistical analysis showed the proposed method achieves the detection accuracies of 100%, 98.19%, and 98.08% over three benchmark data sets. Our method costs merely 0.1984 s to predict one image. Our performance is superior to the 11 state-of-the-art approaches.

Several resting-state neuroimaging studies have indicated abnormal regional homogeneity (ReHo) in chronic schizophrenia; however, little work has been conducted to investigate naive patients with first-episode schizophrenia (FES). Even less investigated is the association between ReHo measures and clinical symptom severity in naive patients with FES. The current study evaluated ReHo alterations in whole brain, and assessed the correlations between ReHo measures and clinical variables in naive patients with FES. Forty-four naive patients with FES and 26 healthy controls (HC) underwent resting-state functional magnetic resonance imaging (rs-fMRI). Group-level analysis was utilized to analyze the ReHo differences between FES and HC in a voxel-by-voxel manner. Severity of symptoms was evaluated using a five-factor model of the Positive and Negative Syndrome Scale (PANSS). The correlation between the severity of symptoms and ReHo map was examined in patients using voxel-wise correlation analyses within brain areas that showed a significant ReHo alteration in patients compared with controls. Compared with the healthy control group, the FES group showed a significant decrease in ReHo values in the left medial frontal gyrus (MFG), right precentral gyrus, left superior temporal gyrus (STG), left left middle temporal gyrus (MTG), left thalamus, and significant increase in ReHo values in the left MFG, left inferior parietal lobule (IPL), left precuneus, and right lentiform nucleus (LN). In addition, the correlation analysis showed the PANSS total score negatively correlated with ReHo in the right precentral gyrus and positively correlated with ReHo in the left thalamus, the positive factor positively correlated with ReHo in the right thalamus, the disorganized/concrete factor positively correlated with ReHo in left posterior cingulate gyrus (PCG), the excited factor positively correlated with ReHo in the left precuneus, and the depressed factor negatively correlated with ReHo in the right postcentral gyrus and positively correlated with ReHo in the right thalamus. Our results indicate that widespread ReHo abnormalities occurred in an early stage of schizophrenic onset, suggesting a potential neural basis for the pathogenesis and symptomatology of schizophrenia.

Alcohol use disorder (AUD) is an important brain disease. It alters the brain structure. Recently, scholars tend to use computer vision based techniques to detect AUD. We collected 235 subjects, 114 alcoholic and 121 non-alcoholic. Among the 235 image, 100 images were used as training set, and data augmentation method was used. The rest 135 images were used as test set. Further, we chose the latest powerful technique-convolutional neural network (CNN) based on convolutional layer, rectified linear unit layer, pooling layer, fully connected layer, and softmax layer. We also compared three different pooling techniques: max pooling, average pooling, and stochastic pooling. The results showed that our method achieved a sensitivity of 96.88%, a specificity of 97.18%, and an accuracy of 97.04%. Our method was better than three state-of-the-art approaches. Besides, stochastic pooling performed better than other max pooling and average pooling. We validated CNN with five convolution layers and two fully connected layers performed the best. The GPU yielded a 149× acceleration in training and a 166× acceleration in test, compared to CPU.

In order to detect cerebral microbleed more efficiently, we developed a novel computer-aided detection method based on susceptibility-weighted imaging. We enrolled five CADASIL patients and five healthy controls. We used a 20x20 neighboring window to generate samples on each slice of the volumetric brain images. The sparse autoencoder (SAE) was used to unsupervised feature learning. Then, a deep neural network was established using the learned features. The results over 10x10-fold cross validation showed our method yielded a sensitivity of 93.20±1.37%, a specificity of 93.25±1.38%, and an accuracy of 93.22±1.37%. Our result is better than Roy's method, which was proposed in 2015.

In this paper, the influences of applied magnetic field on flow state during electroforming of the high-aspect-ratio (HAR) blind micro-hole were numerically analyzed using the Fluent software. The results showed that, when microelectroforming of nickel without external agitation, three vortexes could form due to the magnetohydrodynamic (MHD) effect within the HAR micro-hole with magnetic field in parallel to cathode-electrode surface, and the flow rate in the micro-hole increased with the increase of the magnetic field and current density. The MHD effect helped to enhance mass transfer during the microelectroforming of HAR microstructures.