Search

Background Parkinson disease is a neurodegenerative disease and is characterized by resting tremor, dementia, and gait disorder. Previous studies have indicated that long noncoding RNA participates in the regulation of the pathogenesis of Parkinson disease. The study aimed to reveal the effects of long noncoding RNA nuclear paraspeckle assembly transcript 1 (NEAT1) on 1-methyl-4-phenylpyridine (MPP+)–induced human neuroblastoma cell injury and the underlying mechanism. Methods The expressions of NEAT1, microRNA (miR)-519a-3p, and transcription factor specific protein 1 (SP1) were detected by quantitative real-time polymerase chain reaction. The protein expressions of SP1 and inflammation-related factors were determined by Western blot. Cell viability was determined by 3-(4,5-dimethylthazol-2-yl)-2,5-diphenyltetrazolium bromide assay. Cell apoptosis was investigated by flow cytometry analysis. The targeting relationship between miR-519a-3p and NEAT1 or SP1 was predicted by starBase online database and verified by a dual-luciferase reporter assay. Results NEAT1 and SP1 expressions were significantly upregulated, whereas miR-519a-3p was downregulated in MPP+-treated neuroblastoma cells in a dose- and time-dependent manner when compared with control groups. NEAT1 knockdown restrained MPP+-induced repression of cell viability and promotion of cell apoptosis and inflammation. Additionally, NEAT1 served as a sponge of miR-519a-3p and regulated MPP+-caused cell injury by interacting with miR-519a-3p. Also, SP1, a target gene of miR-519a-3p, rescued miR-519a-3p–mediated actions under MPP+ treatment. Importantly, NEAT1 stimulated SP1 expression through interaction with miR-519a-3p. Conclusions NEAT1 silencing protected against MPP+-induced neuroblastoma cell injury by regulating the miR-519a-3p/SP1 pathway. This finding provides a novel direction for the development of therapeutic strategies for Parkinson disease.

Background Individuals with psychiatric disorders perceive the world differently. Previous studies indicated impaired color vision and weakened color discrimination ability in psychotic patients. Examining the paintings from psychotic patients can measure the visual-motor function. However, few studies examined the potential changes in the color painting behavior in these individuals. The current study aims to discriminate schizophrenia patients from healthy controls (HCs) and predict PANSS scores of schizophrenia patients according to their paintings. Methods In the present study, we retrospectively analyzed the paintings colored by 281 chronic schizophrenia patients and 35 HCs. The images were scanned and processed using series of computational analyses. Results The results showed that schizophrenia patients tend to use less color and exhibit different strokes compared to HCs. Using a deep learning residual neural network (ResNet), we were able to discriminate patients from HCs with over 90% accuracy. Further, we developed a novel convolutional neural network to predict PANSS positive, negative, general psychopathology, and total scores. The Root Mean Square Error (RMSE) of the prediction was low, which indicates higher accuracy of prediction. Conclusion In conclusion, the deep learning paradigm showed the large potential to discriminate schizophrenia patients from HCs based on color paintings. Besides, this color painting-based paradigm can effectively predict clinical symptom severity for chronic schizophrenia patients. The color paintings by schizophrenia patients show potential as a tool for clinical diagnosis and prognosis. These findings show potential as a tool for clinical diagnosis and prognosis among schizophrenia patients.

Affective computing is one of the key technologies to achieve advanced brain-machine interfacing. It is increasingly concerning research orientation in the field of artificial intelligence. Emotion recognition is closely related to affective computing. Although emotion recognition based on electroencephalogram (EEG) has attracted more and more attention at home and abroad, subject-independent emotion recognition still faces enormous challenges. We proposed a subject-independent emotion recognition algorithm based on dynamic empirical convolutional neural network (DECNN) in view of the challenges. Combining the advantages of empirical mode decomposition (EMD) and differential entropy (DE), we proposed a dynamic differential entropy (DDE) algorithm to extract the features of EEG signals. After that, the extracted DDE features were classified by convolutional neural networks (CNN). Finally, the proposed algorithm is verified on SJTU Emotion EEG Dataset (SEED). In addition, we discuss the brain area closely related to emotion and design the best profile of electrode placements to reduce the calculation and complexity. Experimental results show that the accuracy of this algorithm is 3.53 percent higher than that of the state-of-the-art emotion recognition methods. What's more, we studied the key electrodes for EEG emotion recognition, which is of guiding significance for the development of wearable EEG devices.

Most intelligent algorithms used for recognizing epilepsy electroencephalogram (EEG) have two major deficiencies. The one is the lack of interpretability and the other is unsatisfactory recognition results. In response to these challenges, we propose a dedicated model called multi-view Takagi–Sugeno–Kang (TSK) fuzzy system (MV-TSK-FS) for the epilepsy EEG detection. Our contributions lie in three aspects. First, TSK-FS is selected as the basic model. As one of the most famous fuzzy systems, TSK-FS has the advantage of nice interpretability and thus meets the requirement of clinic trials and applications. Second, MV-TSK-FS uses a multi-view framework to collaboratively handle the collective feature data extracted from diverse extraction perspectives, which strives to avoid the potential performance degradation commonly incurred with single feature extraction. Third, we propose a view-weighted mechanism based on the quadratic regularization to distinguish the importance of each view. The more important the view, the larger the corresponding weight is. The final decision is consequently figured out with the weighted outputs of all views. Experimental results demonstrate that, compared with other epilepsy EEG detection ones, our proposed method has better classification performance as well as more satisfied interpretability on results.

In the clinical study of Alzheimer’s Disease (AD) with neuroimaging data, it is challenging to identify the progressive Mild Cognitive Impairment (pMCI) subjects from the stableMCI (sMCI) subjects (i.e., the pMCI/sMCI classification) in an individual level because of small inter-group differences between two groups (i.e., pMCIs and sMCIs) as well as high intra-group variations within each group. Moreover, there are a very limited number of subjects available, which cannot guarantee to find informative and discriminative patterns for achieving high diagnostic accuracy. In this paper, we propose a novel sparse regression method to fuse the auxiliary data into the predictor data for the pMCI/sMCI classification, where the predictor data is structural Magnetic Resonance Imaging (MRI) information of both pMCI and sMCI subjects and the auxiliary data includes the ages of the subjects, the Positron Emission Tomography (PET) information of the predictor data, and the structural MRI information of AD and Normal Controls (NC). Specifically, we incorporate the auxiliary data and the predictor data into a unified framework to jointly achieve the following objectives: i) jointly selecting informative features from both the auxiliary data and the predictor data; ii) robust to outliers from both the auxiliary data and the predictor data; and iii) reducing the aging effect due to the possible cause of brain atrophy induced by both the normal aging and the disease progression. As a result, our proposed method jointly selects the useful features from the auxiliary data and the predictor data by taking into account the influence of outliers and the age of the two kinds of data, i.e., the pMCI and sMCI subjects as well as the AD and NC subjects. We further employ the linear Support Vector Machine (SVM) with the selected features of the predictor data to conduct the pMCI/sMCI classification. Experimental results on the public data of Alzheimer’s Disease Neuroimaging Initiative (ADNI) show the proposed method achieved the best classification performance, compared to the best comparison method, in terms of four evaluation metrics.

Here, we use multi-type feature fusion and selection to predict COVID-19 infections on chest computed tomography (CT) scans The scheme operates in four steps Initially, we prepared a database containing COVID-19 pneumonia and normal CT scans These images were retrieved from the Radiopaedia COVID-19 website The images were divided into training and test sets in a ratio of 70:30 Then, multiple features were extracted from the training data We used canonical correlation analysis to fuse the features into single vectors;this enhanced the predictive capacity We next implemented a genetic algorithm (GA) in which an Extreme Learning Machine (ELM) served to assess GA fitness Based on the ELM losses, the most discriminatory features were selected and saved as an ELM Model Test images were sent to the model, and the best-selected features compared to those of the trained model to allow final predictions Validation employed the collected chest CT scans The best predictive accuracy of the ELM classifier was 93 9%;the scheme was effective

We propose a new method for hearing loss classification from magnetic resonance image (MRI), which can automatically detect tissue-specific features in a given MRI. Sensorineural hearing loss (SHNL) is highly prevalent in our society. Early diagnosis and intervention have a profound impact on patient outcomes. A solution to provide early diagnosis is the use of automated diagnostic systems. In this study, we propose a novel Deep-HLNet framework, based on few-shot learning, for the automated classification of SNHL. This research involves magnetic resonance (MRI) images from 60 participants of three balanced categories: left-sided SNHL, right-sided SNHL, and healthy controls. A convolutional neural network was employed for feature extraction from individual categories, while a neural network and a comparison classifier strategy constituted a tri-classifier for SNHL classification. In terms of experiment results and practicability of the algorithm, the classification performance was significantly better than the standard deep learning methods or other conventional methods, with an overall accuracy of 96.62%.

Melanoma skin cancer is one of the most common diseases in the world. It is essential to diagnose melanoma at an early stage. Visual inspection during the medical examination of skin lesions is not a simple task, as there is a similarity between lesions. Also, medical experience and disposition can result in inaccurate diagnoses. Technologies such as the Internet of Things (IoT) have helped to create effective health systems. Doctors can use them anywhere, with the guarantee that more people can be diagnosed without prejudice to subjective factors. Transfer Learning and Deep Learning are increasingly significant in the clinical diagnosis of different diseases. This work proposes the use of Transfer Learning and Deep Learning in an IoT system to assist doctors in the diagnosis of common skin lesions, typical nevi, and melanoma. This work uses Convolutional Neural Networks (CNNs) as resource extractors. The CNN models used were: Visual Geometry Group (VGG), Inception, Residual Networks (ResNet), Inception-ResNet, Extreme Inception (Xception), MobileNet, Dense Convolutional Network (DenseNet), and Neural Architecture Search Network (NASNet). For the classification of injuries, the Bayes, Support Vector Machines (SVM), Random Forest (RF), Perceptron Multilayer (MLP), and the K-Nearest Neighbors (KNN) classifiers are used. This study used two datasets: the first provided by the International Skin Imaging Collaboration (ISIC) at the International Biomedical Imaging Symposium (ISBI); the second is PH2. For ISBI-ISIC, this study examined lesions between nevi and melanomas. In PH2, this work analyzed the diagnosis based on lesions of common nevus, atypical nevi, and melanomas. The DenseNet201 extraction model, combined with the KNN classifier achieved an accuracy of 96.805% for the ISBI-ISIC dataset and 93.167% for the PH2. Thus, an approach focused on the IoT system is reliable and efficient for doctors who assist in the diagnosis of skin lesions.

Gliomas are characterized by high morbidity and high mortality in primary tumors. The identification of glioma type is helpful for radiologists to facilitate correct medical judgments and better prognosis for patients. In order to avoid harm to patients caused by a biopsy, radiologists attempt to classify Magnetic Resonance Images(MRI) using deep learning methods. In the present paper, we propose a deep learning convolutional neural network ResNet based on the pyramid dilated convolution for Gliomas classification. The pyramid dilated convolution is integrated into the bottom of Resnet to increase the receptive field of the original network and improve the classification accuracy. After adding the pyramid dilated convolution model, the receptive field of the original network underlying convolution was improved. A clinical dataset is used to test the pyramid dilated convolution ResNet neural network model proposed in this paper. The experimental results demonstrate that the proposed method can effectively improve glioma classification performance.

Glomerulosclerosis is a pathomorphological feature of glomerular lesions. Early detection, accurate judgement and effective prevention of the glomeruli is crucial not only for people with kidney disease, but also for the general population. We proposed a method in combination of traditional image analysis with modern machine learning diagnosis system model based on GoogLeNet for recognizing and distinguishing different categories of glomerulus in order to efficiently capture the important structures as well as to minimize manual effort and supervision. We proposed a novel deep learning model based on GoogLeNet with added batch-normalization layers to extract useful features and subsequently entered the features into SoftMax for classification. We also incorporated Bayesian Optimization algorithm and k-fold cross validation in this system for achieving a more reliable result. Our method has eventually achieved an overall accuracy of 95.04±4.99%, and F1 score of 94.44±3.11% for no glomerulus category, 96.73±5.23% for normal glomerulus category and 93.66±7.82% for globally sclerosed glomerulus category, which means this method can accurately determine the degree of glomerulosclerosis with little supervision. The experimental result also shows that this method has better performance when compared with other state-of art methods.

As neuroimaging scanners grow in popularity in hospitals and institutes, the tasks of radiologists are increasing. Emotion, fatigue, and other factors may influence the manual interpretation of results. This manual interpretation suffers from inter- and intra-radiologist variance. Computer-aided medical diagnosis (CAMD) are procedures in medicine that assist radiologists and doctors in the interpretation of medical images, which may come from CT, X-ray, ultrasound, thermography, MRI, PET, SPECT, etc. In practice, CAMD can help radiologists to interpret medical images within seconds. Conventional CAMD tools are built on top of handcrafted features. Recent progress on deep learning opens a new era in which features can be automatically built from a large amount of data. Many important medical projects were launched during the last decade (Human brain project, Blue brain project, Brain Initiative, etc.) that provide massive amounts of data. This emerging big medical data can support the use of deep learning.

Simple Summary One of the hottest areas in deep learning is computerized tumor diagnosis and treatment. The identification of tumor markers, the outline of tumor growth activity, and the staging of various tumor kinds are frequently included. There are several deep learning models based on convolutional neural networks that have high performance and accurate identification, with the potential to improve medical tasks. Breakthroughs and updates in computer algorithms and hardware devices, and intelligent algorithms applied in medical images have a diagnostic accuracy that doctors cannot match in some diseases. This paper reviews the progress of tumor detection from traditional computer-aided methods to convolutional neural networks and demonstrates the potential of the practical application of convolutional neural networks from practical cases to transform the detection model from experiment to clinical application. Abstract Tumors are new tissues that are harmful to human health. The malignant tumor is one of the main diseases that seriously affect human health and threaten human life. For cancer treatment, early detection of pathological features is essential to reduce cancer mortality effectively. Traditional diagnostic methods include routine laboratory tests of the patient’s secretions, and serum, immune and genetic tests. At present, the commonly used clinical imaging examinations include X-ray, CT, MRI, SPECT scan, etc. With the emergence of new problems of radiation noise reduction, medical image noise reduction technology is more and more investigated by researchers. At the same time, doctors often need to rely on clinical experience and academic background knowledge in the follow-up diagnosis of lesions. However, it is challenging to promote clinical diagnosis technology. Therefore, due to the medical needs, research on medical imaging technology and computer-aided diagnosis appears. The advantages of a convolutional neural network in tumor diagnosis are increasingly obvious. The research on computer-aided diagnosis based on medical images of tumors has become a sharper focus in the industry. Neural networks have been commonly used to research intelligent methods to assist medical image diagnosis and have made significant progress. This paper introduces the traditional methods of computer-aided diagnosis of tumors. It introduces the segmentation and classification of tumor images as well as the diagnosis methods based on CNN to help doctors determine tumors. It provides a reference for developing a CNN computer-aided system based on tumor detection research in the future.

Brain tumors are among the leading human killers. There are over 120 different types of brain tumors, but they mainly fall into two groups: primary brain tumors and metastatic brain tumors. Primary brain tumors develop from normal brain cells. Early and accurate detection of primary brain tumors is vital for the treatment of this disease. Magnetic resonance imaging is the most common method to diagnose brain diseases, but the manual interpretation of the images suffers from high inter-observer variance. In this paper, we presented a new computer-aided diagnosis system named PBTNet for detecting primary brain tumors in magnetic resonance images. A pre-trained ResNet-18 was selected as the backbone model in our PBTNet, but it was fine-tuned only for feature extraction. Then, three randomized neural networks, Schmidt neural network, random vector functional-link, and extreme learning machine served as the classifiers in the PBTNet, which were trained with the features and their labels. The final predictions of the PBTNet were generated by the ensemble of the outputs from the three classifiers. 5-fold cross-validation was employed to evaluate the classification performance of the PBTNet, and experimental results demonstrated that the proposed PBTNet was an effective tool for the diagnosis of primary brain tumors.

Diffusion tensor imaging (DTI) is a non-invasive magnetic resonance imaging technique and a special type of magnetic resonance imaging, which has been widely used to study the diffusion process in the brain. The signal-to-noise ratio of DTI data is relatively low, the shape and direction of the noisy tensor data are destroyed. This limits the development of DTI in clinical applications. In order to remove the Rician noise and preserve the diffusion tensor geometry of DTI, we propose a DTI denoising algorithm based on Riemann nonlocal similarity. Firstly, DTI tensor is mapped to the Riemannian manifold to preserve the structural properties of the tensor. The Riemann similarity measure is used to search for non-local similar blocks to form similar patch groups. Then the Gaussian mixture model is used to learn the prior distribution of patch groups. Finally, the noisy patch group is denoised by Bayesian inference and the denoised patch group is reconstructed to obtain the final denoised image. The denoising experiments of real and simulated DTI data are carried out to verify the feasibility and effectiveness of the proposed algorithm. The experimental results show that our algorithm not only effectively removes the Rician noise in the DTI image, but also preserves the nonlinear structure of the DTI image. Comparing to the existing denoising algorithms, our algorithm has better improvement of the principal diffusion direction, lower absolute error of fractional anisotropy and higher peak signal-to-noise ratio.

People suffering from mild cognitive impairment (MCI) are at an increased risk of developing Alzheimer's disease (AD) or another dementia. High prevalence will possibly be reduced if early interventions could be applied to the stage of early MCI (eMCI). In network-based classification, brain functional networks are often constructed, relying on the entire time series. It can lead to the neglect of the complex and dynamic interaction relationships among brain regions. As a result, the features derived from this type of functional network may fail to serve as an effective disease biomarker. To address this problem, we proposed a multi-scale feature combination framework for the eMCI classification. In this framework, global static features, time-varying features, and more refined features could be able to flexibly extract from static functional networks, dynamic functional networks, and high-order functional networks, respectively. Then, they are utilized to train and test the classification model in the form of feature combination. The experimental results have verified that the proposed method achieves superior classification accuracy than other competed methods in the eMCI classification, indicating a great potential in understanding the dysfunction of the brain regions.

Magnetic resonance imaging (MRI), which assists doctors in determining clinical staging and expected surgical range, has high medical value. A large number of MRI images require a large amount of storage space and the transmission bandwidth of the PACS system in offline storage and remote diagnosis. Therefore, high-quality compression of MRI images is very research-oriented. Current compression methods for MRI images with high compression ratio cause loss of information on lesions, leading to misdiagnosis; compression methods for MRI images with low compression ratio does not achieve the desired effect. Therefore, a fast fractal-based compression algorithm for MRI images is proposed in this paper. First, three-dimensional (3D) MRI images are converted into a two-dimensional (2D) image sequence, which facilitates the image sequence based on the fractal compression method. Then, range and domain blocks are classified according to the inherent spatiotemporal similarity of 3D objects. By using self-similarity, the number of blocks in the matching pool is reduced to improve the matching speed of the proposed method. Finally, a residual compensation mechanism is introduced to achieve compression of MRI images with high decompression quality. The experimental results show that compression speed is improved by 2-3 times, and the PSNR is improved by nearly 10. It indicates the proposed algorithm is effective and solves the contradiction between high compression ratio and high quality of MRI medical images.

Aim. This study proposes a new artificial intelligence model based on cardiovascular computed tomography for more efficient and precise recognition of Tetralogy of Fallot (TOF). Methods. Our model is a structurally optimized stochastic pooling convolutional neural network (SOSPCNN), which combines stochastic pooling, structural optimization, and convolutional neural network. In addition, multiple-way data augmentation is used to overcome overfitting. Grad-CAM is employed to provide explainability to the proposed SOSPCNN model. Meanwhile, both desktop and web apps are developed based on this SOSPCNN model. Results. The results on ten runs of 10-fold crossvalidation show that our SOSPCNN model yields a sensitivity of 92.25 ± 2.19 , a specificity of 92.75 ± 2.49 , a precision of 92.79 ± 2.29 , an accuracy of 92.50 ± 1.18 , an F1 score of 92.48 ± 1.17 , an MCC of 85.06 ± 2.38 , an FMI of 92.50 ± 1.17 , and an AUC of 0.9587. Conclusion. The SOSPCNN method performed better than three state-of-the-art TOF recognition approaches.

Epilepsy is a prevalent neurological disorder that threatens human health in the world. The most commonly used method to detect epilepsy is using the electroencephalogram (EEG). However, epilepsy detection from the EEG is time-consuming and error-prone work because of the varying levels of experience we find in physicians. To tackle this challenge, in this paper, we propose a multi-scale non-local (MNL) network to achieve automatic EEG signal detection. Our MNL-Network is based on 1D convolution neural network involving two specific layers to improve the classification performance. One layer is named the signal pooling layer which incorporates three different sizes of 1D max-pooling layers to learn the multi-scale features from the EEG signal. The other one is called a multi-scale non-local layer, which calculates the correlation of different multi-scale extracted features and outputs the correlative encoded features to further enhance the classification performance. To evaluate the effectiveness of our model, we conduct experiments on the Bonn dataset. The experimental results demonstrate that our MNL-Network could achieve competitive results in the EEG classification task.

Cerebral microbleeds are important biomarkers of many cerebrovascular diseases and cognitive dysfunctions. Their distribution patterns can indicate some underlying aetiologies. Hitherto, few researches tried to detect cerebral microbleeds accurately and automatically. Some improvements have been achieved via traditional machine learning methods. In this paper, we proposed a method based on convolutional neural network (CNN) for further improving the performance. Firstly, sliding neighborhood processing method was applied to generate the input and target datasets based on 10 3D brain images of cerebral autosomal-dominant arteriopathy with subcortical infarcts and Leukoencephalopathy scanned by susceptibility-weighted imaging (SWI). Then, CNN was used to classify the cerebral microbleeds. To exert the full-power of convolutional neural network, almost all hyperparameters of CNN structure that could affect the performance were tested, such as the number of layers, type of activation function, pooling method, and filter size. A fully-optimized convolutional neural network structure for cerebral microbleeds classification was obtained. It performed better than four existed state-of-the-art approaches with a sensitivity of 99.74%, a specificity of 96.89% and an accuracy of 98.32%.

Traditional sensorineural hearing loss identification use the framework of feature extraction and classification. Nevertheless, this framework needs manual feature engineering. In this study, we proposed an improved convolutional neural network model to identify hearing loss. Our nine-layer deep convolutional neural network contains six conv layers and three fully-connected layers. We used batch normalization to reduce the impact caused by Internal Covariate shift and dropout techniques to prevent over-fitting to increase the performance in terms of accuracy. Data augmentation was used to enlarge the size of training set. The average results of 10 runs on test set show our method secured sensitivities of left-sided hearing loss, right-sided hearing loss, and healthy controls are 96.33 ± 2.46%, 96.67 ± 2.22%, and 96.67 ± 2.72%, respectively. The overall accuracy of all three classes was 96.56 ± 0.63%. Deep learning can effectively build the identification model. The performance of our proposed nine-layer convolutional neural network model yields better performance than five state-of-the-art approaches.

Conventional brain functional networks are constructed by extracting the entire time series from functional Magnetic Resonance Imaging (fMRI). Yet such a method is easy to ignore the dynamic interaction patterns of brain regions that essentially change across time. In this study, we analyze the functional connectivity characteristics of Rich Club in resting-state brain functional networks, and study the dynamic functional differences of core brain regions at different time periods. First, the time series is extracted from resting-state fMRI to construct a dynamic brain functional network. Then, Rich Clubs of different time periods are determined by the Rich Club coefficients. In particular, the efficiency of each Rich Club is calculated to examine the influences of the Rich Connections, Feeder Connections and Local Connections. Finally, the node degree, clustering coefficient and efficiency for Rich Club nodes are calculated to quantify the dynamic processes of Rich Clubs, and the functional connectivity of Rich Clubs are compared with those of the functional networks constructed by the entire fMRI time series. Experimental results demonstrate that the distribution of Rich Clubs in the dynamic brain functional network is consistent with that from the entire fMRI time series, while the composition and functional connectivity of Rich Club dynamically change across time. Moreover, Rich connection and Local connection in the brain functional networks show a significant correlation with the efficiency of Rich Club, and the local and the global efficiency of Rich Clubs are greater than that of the global network. These results further illustrate the viewpoint that Rich Clubs have significant influence on the functional characteristics of global brain functional networks.

Hubs in complex networks can greatly influence the integration of network functions, and recognition of hubs helps to better understand the interaction between pairs of network nodes. This paper proposes a new hub recognition method with multiple-feature combination for the brain functional networks constructed by resting-state functional Magnetic Resonance Imaging (fMRI). Three single-feature methods, including degree centrality, betweenness centrality and closeness centrality, are used to calculate hubs of the brain functional network separately. For reordering the nodes, a composite equation is constructed based on the three recognition parameters. Network vulnerability and average shortest path length are used to evaluate the importance of the hubs recognized by above four methods. Experimental result demonstrates that, the hubs recognized by multiple-feature combination have more significant differences from ordinary nodes than those by single-feature methods, and they have an important impact on the global efficiency of brain functional networks.

Aim: Sensorineural hearing loss is correlated to massive neurological or psychiatric disease. Materials: T1-weighted volumetric images were acquired from fourteen subjects with right-sided hearing loss (RHL), fifteen subjects with left-sided hearing loss (LHL), and twenty healthy controls (HC). Method: We treated a three-class classification problem: HC, LHL, and RHL. Stationary wavelet entropy was employed to extract global features from magnetic resonance images of each subject. Those stationary wavelet entropy features were used as input to a single-hidden layer feedforward neuralnetwork classifier. Results: The 10 repetition results of 10-fold cross validation show that the accuracies of HC, LHL, and RHL are 96.94%, 97.14%, and 97.35%, respectively. Conclusion: Our developed system is promising and effective in detecting hearing loss.

It is important to detect cerebral microbleed voxels from the brain image of cerebral autosomal-dominant arteriopathy with subcortical infarcts and Leukoencephalopathy (CADASIL) patients. Traditional manual method suffers from intra-observe and inter-observe variability. In this study, we used the susceptibility weighted imaging (SWI) to scan 10 CADASIL patients and 10 healthy controls. We used slicing neighborhood processing (SNP) to extract “input” and “target” dataset from the 20 brain volumetric images. Afterwards, the undersampling technique was employed to handle the class-imbalanced problem. The single-hidden layer feedforward neural-network with scaled conjugate gradient was used as the classifier. We compared three activation functions: logistic sigmoid (LOSI), rectified linear unit (ReLU), and leaky rectified linear unit (LReLU). Early stopping and K-fold cross validation (CV) was used to avoid overfitting and statistical analysis. In the experiment, we generated 68,847 CMB voxels, and 68,829 non-CMB voxels. We observed that LReLU achieved the best result with a sensitivity of 93.05%, a specificity of 93.06%, and an accuracy of 93.06%. We also observed the effect of early stopping and K-fold CV. We found the optimal number of hidden neuron was 10 by grid searching method. Besides, our method performs better than three state-of-the-art methods. The results show our method is promising. In addition, LReLU is a better activation function that may replace traditional logistic sigmoid function in other applications.

Background Metabolic syndrome (MS) is a major global health concern comprising a cluster of co-occurring conditions that increase the risk of heart disease, stroke and type 2 diabetes. MS is usually diagnosed using a combination of physiochemical indexes (such as BMI, abdominal circumference and blood pressure) but largely ignores clinical symptoms when investigating prevention and treatment of the disease. Exploring predictors of MS using multiple diagnostic indicators may improve early diagnosis and treatment of MS. Traditional Chinese medicine (TCM) attaches importance to the etiology of disease symptoms and indications using four diagnostic methods, which have long been used to treat metabolic disease. Therefore, in this study, we aimed to develop predictive indicators for MS using both physiochemical indexes and TCM methods. Methods Clinical information (including both physiochemical and TCM indexes) was obtained from a cohort of 586 individuals across 4 hospitals in China, comprising 136 healthy controls and 450 MS cases. Using this cohort, we compared three classic machine learning methods: decision tree (DT), support vector machine (SVM) and random forest (RF) towards MS diagnosis using physiochemical and TCM indexes, with the best model selected by comparing the accuracy, specificity and sensitivity of the three models. In parallel, the best proportional partition of the training data to the test data was confirmed by observing the changes in evaluation indexes using each model. Next, three subsets containing different categories of variables (including both TCM and physicochemical indexes combined – termed the “fused indexes”, only physicochemical indexes, and TCM indexes only) were compared and analyzed using the best performing model and optimum training to test data proportion. Next, the best subset was selected through comprehensive comparative analysis, and then the important prediction variables were selected according to their weight. Results When comparing the three models, we found that the RF model had the highest average accuracy (average 0.942, 95%CI [0.925, 0.958]) and sensitivity (average 0.993, 95%CI [0.990, 0.996]). Besides, when the training set accounted for 80% of the cohort data, the specificity got the best value and the accuracy and sensitivity were also very high in RF model. In view of the performance of the three different subsets, the prediction accuracy and sensitivity of models analyzing the fused indexes and only physicochemical indexes remained at a high level. Further, the mean value of specificity of the model using fused indexes was 0.916, which was significantly higher than the model with only physicochemical indexes (average 0.822) and the model with only TCM indexes (average 0.403). Based on the RF model and data allocation ratio (8:2), we further extracted the top 20 most significant variables from the fused indexes, which included 14 physicochemical indexes and 6 TCM indexes including wiry pulse, chest tightness, spontaneous perspiration, greasy tongue coating etc. Conclusion Compared with SVM and DT models, the RF model showed the best performance, especially when the ratio of the training set to test set is 8:2. Compared with single predictive indexes, the model constructed by combining physiochemical indexes with TCM indexes (i.e. the fused indexes) exhibited better predictive ability. In addition to common physicochemical indexes, some TCM indexes, such as wiry pulse, chest tightness, spontaneous perspiration, greasy tongue coating, can also improve diagnosis of MS.

Aim In a pilot study to improve detection of malignant lesions in breast mammograms, we aimed to develop a new method called BDR-CNN-GCN, combining two advanced neural networks: (i) graph convolutional network (GCN); and (ii) convolutional neural network (CNN). Method We utilised a standard 8-layer CNN, then integrated two improvement techniques: (i) batch normalization (BN) and (ii) dropout (DO). Finally, we utilized rank-based stochastic pooling (RSP) to substitute the traditional max pooling. This resulted in BDR-CNN, which is a combination of CNN, BN, DO, and RSP. This BDR-CNN was hybridized with a two-layer GCN, and yielded our BDR-CNN-GCN model which was then utilized for analysis of breast mammograms as a 14-way data augmentation method. Results As proof of concept, we ran our BDR-CNN-GCN algorithm 10 times on the breast mini-MIAS dataset (containing 322 mammographic images), achieving a sensitivity of 96.20±2.90%, a specificity of 96.00±2.31% and an accuracy of 96.10±1.60%. Conclusion Our BDR-CNN-GCN showed improved performance compared to five proposed neural network models and 15 state-of-the-art breast cancer detection approaches, proving to be an effective method for data augmentation and improved detection of malignant breast masses.

Detection of Alzheimer's disease (AD) from magnetic resonance images can help neuroradiologists to make decision rapidly and avoid missing slight lesions in the brain. Currently, scholars have proposed several approaches to automatically detect AD. In this study, we aimed to develop a novel AD detection system with better performance than existing systems. 28 ADs and 98 HCs were selected from OASIS dataset. We used inter-class variance criterion to select single slice from the 3D volumetric data. Our classification system is based on three successful components: wavelet entropy, multilayer perceptron, and biogeography-base optimization. The statistical results of our method obtained an accuracy of 92.40 ± 0.83%, a sensitivity of 92.14 ± 4.39%, a specificity of 92.47 ± 1.23%. After comparison, we observed that our pathological brain detection system is superior to latest 6 other approaches.

In the past, scholars used various computer vision and artificial intelligence methods to detect brain diseases via magnetic resonance imaging (MRI). In this paper, we proposed a novel system to detect sensorineural hearing loss (SNHL). First, we used three-level bior4.4 wavelet to decompose original brain image. Second, principal component analysis (PCA) was utilized for dimensionality reduction. Third, the generalized eigenvalue proximal support vector machine (GEPSVM) with Tikhonov regularization was employed as the classifier. The 10 repetitions of five-fold cross validation showed our method achieved an overall accuracy of 95.71 %. Our sensitivities over healthy control, left-sided SNHL, and right-sided SNHL are 96.00 %, 95.33 %, and 95.71 %, respectively. The proposed system is promising and effective in SNHL detection. It gives better performance than four state-of-the-art methods.

In order to detect multiple sclerosis (MS) subjects from healthy controls (HCs) in magnetic resonance imaging, we developed a new system based on machine learning. The MS imaging data was downloaded from the eHealth laboratory at the University of Cyprus, and the HC imaging data was scanned in our local hospital with volunteers enrolled from community advertisement. Inter-scan normalization was employed to remove the gray-level difference. We adjust the misclassification costs to alleviate the effect of unbalanced class distribution to the classification performance. We utilized two-level stationary wavelet entropy (SWE) to extract features from brain images. Then, we compared three machine learning based classifiers: the decision tree, k-nearest neighbors (kNN), and support vector machine. The experimental results showed the kNN performed the best among all three classifiers. In addition, the proposed SWE+kNN approach is superior to four state-of-the-art approaches. Our proposed MS detection approach is effective.

Aim: To develop an automatic magnetic resonance (MR) brain classification that can assist physicians to make a diagnosis and reduce wrong decisions. Method: This article investigated the binary particle swarm optimization (BPSO) approach and proposed its three new variants: BPSO with mutation and time-varying acceleration coefficients (BPSO-MT), BPSO with mutation (BPSO-M), and BPSO with time-varying acceleration coefficients (BPSO-T). We first extracted wavelet entropy (WE) features from both approximation and detail sub-bands of eight-level decomposition. Afterwards, we used the proposed BPSO-M, BPSO-T, and BPSO-MT to select features. Finally, the selected features were fed into a probabilistic neural network (PNN). Results: The proposed BPSO-MT performed better than BPSO-T and BPSO-M. It finally selected two features of entropies of the following two sub-bands (V1, D1). The proposed system “WE + BPSO-MT + PNN” yielded perfect classification on Data160 and Data66. In addition, it yielded 99.53% average accuracy for the Data255, over 10 repetitions of k-fold stratified cross validation (SCV), higher than state-of-the-art approaches. Conclusions: The proposed method is effective for MR brain classification.

Magnetic resonance (MR) imaging is widely used in daily medical treatment. It could help in pre-surgical, diagnosis, prognosis, and postsurgical processes. It could be beneficial for diagnosis to classify MR images of brain into healthy or abnormal automatically and accurately, since the information set MRIs generate is too large to interpret with manual methods. We propose a new approach with wavelet-entropy as the features and the kernel based extreme learning machine (K-ELM) to be the classifier. Our method employs 2D-discreet wavelet transform (DWT), and calculates the entropy as features. Then, a K-ELM is trained to classify images as pathological or healthy. A 10 × 10-fold cross validation is conducted to prevent overfitting. The method achieves the sensitivity as 97.48 %, the specificity as 94.44 %, and the overall accuracy as 97.04 % based on 125 MR images. The performance suggests the classifier is robust and effective by comparison with the recently published approaches.

An accurate diagnosis is important for the medical treatment of patients suffering from brain diseases. Magnetic resonance (MR) images are commonly used by technicians to assist preclinical diagnosis. The classification of MR images of normal and pathological brains poses a challenge from the technological point of view, since MR imaging generates a large information set that reflects the conditions of the brain. In this paper, we present a computer-assisted diagnosis method based on wavelet entropy (WE) of the feature space approach and a feed-forward neural network (FNN) classification method for improving the brain diagnosis accuracy by means of MR images. The most relevant image feature is selected as the WE, which is used to train an FNN classifier. The results using tenfold cross validation of 64 images show that the average accuracy attainable is 100.00%. It can be easily seen from the data that the proposed classifier can detect abnormal brains from normal controls with excellent performance, which can compete with the latest methods. © 2016 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

Background: We proposed a new automatic and rapid computer-aided diagnosis system to detect pathological brain images obtained in the scans of magnetic resonance imaging (MRI). Methods: For simplification, we transformed the problem to a binary classification task (pathological or normal). It consisted of two steps: first, Hu moment invariants (HMI) were extracted from a specific MR brain image; then, seven HMI features were fed into two classifiers: twin support vector machine (TSVM) and generalised eigenvalue proximal SVM (GEPSVM). Results: Then, a 5 × 5-fold cross validation on a data set containing 90 MR brain images, demonstrated that the proposed methods “HMI + GEPSVM” and “HMI + TSVM” achieved classification accuracy of 98.89%, higher than eight state-of-the-art methods: “DWT + PCA + BP-NN”, “DWT + PCA + RBF-NN”, “DWT + PCA + PSO-KSVM”, “WE + BP-NN”, “WE + KSVM”, “DWT + PCA + GA-KSVM”, “WE + PSO-KSVM” and “WE + BBO-KSVM”. Conclusion: The proposed methods are superior to other methods on pat...

To detect multiple sclerosis (MS) diseases early, we proposed a novel method on the hardware of magnetic resonance imaging, and on the software of three successful methods: biorthogonal wavelet transform, kernel principal component analysis, and logistic regression. The materials were 676 MR slices containing plaques from 38 MS patients, and 880 MR slices from 34 healthy controls. The statistical analysis showed our method achieved a sensitivity of 97.12±.14%, a specificity of 98.25±0.16%, and an accuracy of 97.76±0.10%. Our method is superior to five state-of-the-art approaches in MS detection.

Emotion recognition represents the position and motion of facial muscles. It contributes significantly in many fields. Current approaches have not obtained good results. This paper aimed to propose a new emotion recognition system based on facial expression images. We enrolled 20 subjects and let each subject pose seven different emotions: happy, sadness, surprise, anger, disgust, fear, and neutral. Afterward, we employed biorthogonal wavelet entropy to extract multiscale features, and used fuzzy multiclass support vector machine to be the classifier. The stratified cross validation was employed as a strict validation model. The statistical analysis showed our method achieved an overall accuracy of 96.77±0.10%. Besides, our method is superior to three state-of-the-art methods. In all, this proposed method is efficient.

The original version of this article unfortunately contained a mistake. The reference #27 in the reference list is incorrect in that the individual chapter should be cited instead of the whole book.

Cerebral microbleeds (CMBs) are the small foci of chronic blood products. CMBs are closely related to many diseases such as dementia, siderosis, ageing, etc. A data balance method is used for their identification, since CMB voxels in collected brain images are usually about 2000 times less common than non-CMB voxels.