Design and Stability Analysis of an Adaptive Neuro-Fuzzy Inference System (ANFIS)-Based Pacemaker Controller in MATLAB Simulink.

We present the design and stability analysis of an adaptive neuro-fuzzy inference system (ANFIS)-based controller of a pacemaker in MATLAB Simulink. ANFIS uses learning and speed properties of fuzzy and neural networks. Based on body states and preprogrammed situations of patients (age and sex, etc.), heart rate and amplitude of pacing pulse are changed. Output signal that is fed backed from heart is compared to the reference fuzzy bases ANFIS signals. After designing ANFIS based controller, the stability of the proposed system has been tested in both the time (step response) and trequency (Bode diagram and Nichols chart) domains. In our previous study, the step response analyzed and compared with other works. For frequency domain, all the possible frequency analysis methods have been tested but because of nonlinear properties of ANFIS, after linearization, just the Bode diagram achieved good results. The step response results in time domain is compared with previous work's results including optimum heart pulse rate for each particular patient. In the frequency domain, the Bode diagram stability analysis showed gain and phase margin as follows: GM (dB) = 42.1 and PM (deg) = 100.

Controlling pathological activity of Parkinson basal ganglia based on excitation and inhibition optogenetic models and monophasic and biphasic electrical stimulations.

We examined electrical and optogenetic stimulations to explore their benefits and the effective range of their network effects. The error index (EI) and beta-activity of a network were considered by us as appropriate phenomena to compare stimulations. The basal ganglia (BG) network model considers areas of the brain affected by Parkinson's disease (PD). It consists of the thalamus (TH), subthalamic nucleus (STN), globus pallidus interna (GPi,), and globus pallidus externa (GPe). To control the BG in PD, we stimulated the STN, GPe, and GPi with deep brain stimulation (DBS) and optogenetic stimulation, and to examine TH performance, we used the sensorimotor cortex (SMC). BG network performance was evaluated by measuring how TH responded to SMC input, and how STN, GPe, and Gpi were affected by DBS and optogenetic stimulation as evaluated using EI and beta-activity. By comparing the firing rates obtained from four applied stimulations at optimal conditions of the model, the effect of each stimulation was studied. The results indicated that applying monophasic DBS causes STN, GPi, and GPe cells to fire regularly, and biphasic DBS leads to increased oscillations between firings of STN cells; three-state optogenetic inhibition using halorhodopsin (NpHR) synchronizes the firing of GPe and GPi, and suppresses the neural activity of STN; and four-state optogenetic excitation using channelrhodopsin-2 (ChR2) incites the STN to excite and depolarize neural activity. All these events avoided pathological activation of PD and returned the performance to that of the healthy state. Finally, to evaluate our suggested method, we measured the beta-activity of monophasic and biphasic DBS and optogenetic inhibition and excitation by varying the electrical stimulation intensity (Aelec) and optical stimulation intensity (Alight) and obtained optimal values for each state. According to our results, increasing Aelec does not cause immediate decrease of beta-activity in monophasic and biphasic DBS. Increasing Alight causes immediate decrease of beta-activity in NpHR, which then remains constant. In ChR2 there is no significant relation between beta-activity and Alight.

Ocular condition prognosis in Keratoconus patients after corneal ring implantation using artificial neural networks.

The common disorder, Keratoconus (KC), is distinguished by cumulative corneal slimming and steepening. The corneal ring implantation has become a successful surgical procedure to correct the KC patient's vision. The determination of suitable patients for the surgery alternative is among the paramount concerns of ophthalmologists. To reduce the burden on them and enhance the treatment, this research aims to previse the ocular condition of KC patients after the corneal ring implantation. It focuses on predicting post-surgical corneal topographic indices and visual characteristics. This study applied an efficacious artificial neural network approach to foretell the aforementioned ocular features of KC subjects 6 and 12 months after implanting KeraRing and MyoRing based on the accumulated data. The datasets are composed of sufficient numbers of corneal topographic maps and visual characteristics recorded from KC patients before and after implanting the rings. The visual characteristics under study are uncorrected visual acuity (UCVA), sphere (SPH), astigmatism (Ast), astigmatism orientation (Axe), and best corrected visual acuity (BCVA). In addition, the statistical data of multiple KC subjects were registered, including three effective indices of corneal topography (i.e., Ast, K-reading, and pachymetry) pre- and post-ring embedding. The outcomes represent the contribution of practical training of the introduced models to the estimation of ocular features of KC subjects following the implantation. The corneal topographic indices and visual characteristics were estimated with mean errors of 7.29% and 8.60%, respectively. Further, the errors of 6.82% and 7.65% were respectively realized for the visual characteristics and corneal topographic indices while assessing the predictions by the leave-one-out cross-validation (LOOCV) procedure. The results confirm the great potential of neural networks to guide ophthalmologists in choosing appropriate surgical candidates and their specific intracorneal rings by predicting post-implantation ocular features.

A Hybrid EEG-based Emotion Recognition Approach Using Wavelet Convolutional Neural Networks and Support Vector Machine.

Introduction: Nowadays, deep learning and convolutional neural networks (CNNs) have become widespread tools in many biomedical engineering studies. CNN is an end-to-end tool, which makes the processing procedure integrated, but in some situations, this processing tool requires to be fused with machine learning methods to be more accurate. Methods: In this paper, a hybrid approach based on deep features extracted from wavelet CNNs (WCNNs) weighted layers and multiclass support vector machine (MSVM) was proposed to improve the recognition of emotional states from electroencephalogram (EEG) signals. First, EEG signals were preprocessed and converted to Time-Frequency (T-F) color representation or scalogram using the continuous wavelet transform (CWT) method. Then, scalograms were fed into four popular pre-trained CNNs, AlexNet, ResNet-18, VGG-19, and Inception-v3 to fine-tune them. Then, the best feature layer from each one was used as input to the MSVM method to classify four quarters of the valence-arousal model. Finally, the subject-independent leave-one-subject-out criterion was used to evaluate the proposed method on DEAP and MAHNOB-HCI databases. Results: Results showed that extracting deep features from the earlier convolutional layer of ResNet-18 (Res2a) and classifying using the MSVM increased the average accuracy, precision, and recall by about 20% and 12% for MAHNOB-HCI and DEAP databases, respectively. Also, combining scalograms from four regions of pre-frontal, frontal, parietal, and parietal-occipital and two regions of frontal and parietal achieved the higher average accuracy of 77.47% and 87.45% for MAHNOB-HCI and DEAP databases, respectively. Conclusion: Combining CNN and MSVM increased the recognition of emotion from EEG signals and the results were comparable to state-of-the art studies.

A New Nonlinear Autoregressive Exogenous (NARX)-based Intra-spinal Stimulation Approach to Decode Brain Electrical Activity for Restoration of Leg Movement in Spinally-injured Rabbits.

Introduction: This study aimed at investigating the stimulation by intra-spinal signals decoded from electrocorticography (ECoG) assessments to restore the movements of the leg in an animal model of spinal cord injury (SCI). Methods: The present work is comprised of three steps. First, ECoG signals and the associated leg joint changes (hip, knee, and ankle) in sedated healthy rabbits were recorded in different trials. Second, an appropriate set of intra-spinal electric stimuli was discovered to restore natural leg movements, using the three leg joint movements under a fuzzy-controlled strategy in spinally-injured rabbits under anesthesia. Third, a nonlinear autoregressive exogenous (NARX) neural network model was developed to produce appropriate intra-spinal stimulation developed from decoded ECoG information. The model was able to correlate the ECoG signal data to the intra-spinal stimulation data and finally, induced desired leg movements. In this study, leg movements were also developed from offline ECoG signals (deciphered from rabbits that were not injured) as well as online ECoG data (extracted from the same rabbit after SCI induction). Results: Based on our data, the correlation coefficient was 0.74±0.15 and the normalized root means square error of the brain-spine interface was 0.22±0.10. Conclusion: Overall, we found that using NARX, appropriate information from ECoG recordings can be extracted and used for the generation of proper intra-spinal electric stimulations for restoration of natural leg movements lost due to SCI.

Effects of COVID-19-related psychological distress and anxiety on quality of sleep and life in healthcare workers in Iran and three European countries.

Introduction: The COVID-19 pandemic has considerably affected human beings most of whom are healthcare workers (HCWs) combating the disease in the front line. Methods: This cross-sectional study aims to explore the effects of stress and anxiety caused by COVID-19 on the quality of sleep and life in HCWs, including physicians, nurses, and other healthcare staff. In this global study, we asked 1,210 HCWs (620 and 590 volunteers from Iran and European countries, including Germany, the Netherlands, and Italy, respectively), who age 21-70, to participate in the test. Several measures of COVID-related stress, anxiety, sleep, and life quality, including the 12-item General Health Questionnaire (GHQ-12), Fear of COVID-19 scale (FCV-19S), Beck Anxiety Inventory (BAI), the Pittsburgh Sleep Quality Index (PSQI), and World Health Organization Quality of Life-BREF (WHOQOL-BREF) are recorded. Results: Volunteers reported high rates of stress and anxiety and poor sleep quality as well as lower quality of life. The correlation analysis between the measures is reported. According to the results, regardless of the location, HCWs, predominantly female nurses, developed anxiety and stress symptoms which consequently resulted in lower sleep and life quality. Both for Iranian and the European HCWs, significant differences existed between nurses and the other two groups, with the p-values equal to 0.0357 and 0.0429 for GHQ-12, 0.0368, and 0.714 for BAI measure. Even though nurses reported the most stress, anxiety, fear of COVID-19, lower quality of life and sleep in both countries, and also an increase in other measures as well, there existed no statistically significant difference in FCV-19S, PSQI, and WHOQOL-BREF. Discussion: This study helps to expand our knowledge the effects of pandemics on HCWs and also for healthcare management to predict HCW's mental health conditions in similar situations.

Emotion recognition using effective connectivity and pre-trained convolutional neural networks in EEG signals.

Convolutional Neural Networks (CNN) have recently made considerable advances in the field of biomedical signal processing. These methodologies can assist in emotion recognition for affective brain computer interface. In this paper, a novel emotion recognition system based on the effective connectivity and the fine-tuned CNNs from multichannel Electroencephalogram (EEG) signal is presented. After preprocessing EEG signals, the relationships among 32 channels of EEG in the form of effective brain connectivity analysis which represents information flow between regions are computed by direct Directed Transfer Function (dDTF) method which yields a 32*32 image. Then, these constructed images from EEG signals for each subject were fed as input to four versions of pre-trained CNN models, AlexNet, ResNet-50, Inception-v3 and VGG-19 and the parameters of these models are fine-tuned, independently. The proposed deep learning architectures automatically learn patterns in the constructed image of the EEG signals in frequency bands. The efficiency of the proposed approach is evaluated on MAHNOB-HCI and DEAP databases. The experiments for classifying five emotional states show that the ResNet-50 applied on dDTF images in alpha band achieves best results due to specific architecture which captures the brain connectivity, efficiently. The accuracy and F1-score values for MAHNOB-HCI were obtained 99.41, 99.42 and for DEAP databases, 98.17, and 98.23. Newly proposed model is capable of effectively analyzing the brain function using information flow from multichannel EEG signals using effective connectivity measure of dDTF and ResNet-50.

EEG artifact removal using sub-space decomposition, nonlinear dynamics, stationary wavelet transform and machine learning algorithms.

Blind source separation (BSS) methods have received a great deal of attention in electroencephalogram (EEG) artifact elimination as they are routine and standard signal processing tools to remove artifacts and reserve desired neural information. On the other hand, a classifier should follow BSS methods to automatically identify artifactual sources and remove them in the following steps. In addition, removing all detected artifactual components leads to loss of information since some desired information related to neural activity leaks to these sources. So, an approach should be employed to detect and suppress the artifacts and reserve neural activity. This study introduces a novel method based on EEG and Poincare planes in the phase space to detect artifactual components estimated by second-order blind identification (SOBI). Artifacts are detected using a mixture of well-known conventional classifiers and were removed employing stationary wavelet transform (SWT) to reserve neural information. The proposed method is a combination of signal processing techniques and machine learning algorithms, including multi-layer perceptron (MLP), K-nearest neighbor (KNN), naïve Bayes, and support vector machine (SVM) which have significant results while applying our proposed method to different scenarios. Simulated, semi-simulated, and real EEG signals are employed to evaluate the proposed method, and several evaluation criteria are calculated. We achieved acceptable results, for example, 98% average accuracy and 97% average sensitivity in artifactual EEG component detection or about 2% as mean square error in EEG reconstruction after artifact removal. Results showed that the proposed method is effective and can be used in future studies as we have considered different real-world scenarios to evaluate it.

Synthetic OCT data in challenging conditions: three-dimensional OCT and presence of abnormalities.

Nowadays, retinal optical coherence tomography (OCT) plays an important role in ophthalmology and automatic analysis of the OCT is of real importance: image denoising facilitates a better diagnosis and image segmentation and classification are undeniably critical in treatment evaluation. Synthetic OCT was recently considered to provide a benchmark for quantitative comparison of automatic algorithms and to be utilized in the training stage of novel solutions based on deep learning. Due to complicated data structure in retinal OCTs, a limited number of delineated OCT datasets are already available in presence of abnormalities; furthermore, the intrinsic three-dimensional (3D) structure of OCT is ignored in many public 2D datasets. We propose a new synthetic method, applicable to 3D data and feasible in presence of abnormalities like diabetic macular edema (DME). In this method, a limited number of OCT data is used during the training step and the Active Shape Model is used to produce synthetic OCTs plus delineation of retinal boundaries and location of abnormalities. Statistical comparison of thickness maps showed that synthetic dataset can be used as a statistically acceptable representative of the original dataset (p > 0.05). Visual inspection of the synthesized vessels was also promising. Regarding the texture features of the synthesized datasets, Q-Q plots were used, and even in cases that the points have slightly digressed from the straight line, the p-values of the Kolmogorov-Smirnov test rejected the null hypothesis and showed the same distribution in texture features of the real and the synthetic data. The proposed algorithm provides a unique benchmark for comparison of OCT enhancement methods and a tailored augmentation method to overcome the limited number of OCTs in deep learning algorithms.

Prediction of obstructive sleep apnea using ensemble of recurrence plot convolutional neural networks (RPCNNs) from polysomnography signals.

Obstructive Sleep Apnea (OSA) is a common disorder characterized by periodic cessation of breathing during sleep. OSA affects daily life and poses a severe threat to human health. The standard clinical method for identifying and predicting OSA events is the use of Polysomnography signals. In this paper, a novel scheme based on an ensemble of recurrence plots (RPs) and pre-trained convolutional neural networks (RPCNNs) is proposed to improve the prediction rate of OSA. First, RPs were used to represent the dynamic behavior of single electroencephalogram (EEG) and electrocardiogram (ECG) signals for 60 s before and during OSA events. Then, using RPs, three prompt CNNs named ResNet-50 were fine-tuned, and their classification results were fused via the Majority Voting (MV) method to produce a final result concerning prediction. Next, the subject-independent Leave-One-Subject-Out Cross-Validation (LOSO-CV) and subject-dependent 10-fold Cross-Validation (10-fold CV) methods were used to validate the prediction rate from signals derived from the University College Dublin Sleep Apnea Database. Finally, the highest achieved average accuracy for the fusion level was 91.74% and 89.45% at the 10-fold CV and LOSO-CV. Additionally, our results outperformed state-of-the-art findings and could be recommended to predict and detect other biomedical signals. As a result, this predictive system can also be used to adjust the air pressure in sleep apnea patients' Automatic Positive Airway Pressure (APAP) devices.

Biomarker Discovery by Imperialist Competitive Algorithm in Mass Spectrometry Data for Ovarian Cancer Prediction.

BACKGROUND: Mass spectrometry is a method for identifying proteins and could be used for distinguishing between proteins in healthy and nonhealthy samples. This study was conducted using mass spectrometry data of ovarian cancer with high resolution. Usually, diagnostic and monitoring tests are done according to sensitivity and specificity rates; thus, the aim of this study is to compare mass spectrometry of healthy and cancerous samples in order to find a set of biomarkers or indicators with a reasonable sensitivity and specificity rates. METHODS: Therefore, combination methods were used for choosing the optimum feature set as t-test, entropy, Bhattacharya, and an imperialist competitive algorithm with K-nearest neighbors classifier. The resulting feature from each method was feed to the C5 decision tree with 10-fold cross-validation to classify data. RESULTS: The most important variables using this method were identified and a set of rules were extracted. Similar to most frequent features, repetitive patterns were not obtained; the generalized rule induction method was used to identify the repetitive patterns. CONCLUSION: Finally, the resulting features were introduced as biomarkers and compared with other studies. It was found that the resulting features were very similar to other studies. In the case of the classifier, higher sensitivity and specificity rates with a lower number of features were achieved when compared with other studies.

Intelligent Oscillometric System for Automatic Detection of Peripheral Arterial Disease.

Peripheral arterial disease (PAD) is a progressing arterial disorder that is associated with significant morbidity and mortality. The conventional PAD detection methods are invasive, cumbersome, or require expensive equipment and highly trained technicians. Here, we propose a new automated, noninvasive, and easy-to-use method for the detection of PAD based on characterizing the arterial system by applying an external varying pressure using a cuff. The superposition of the internal arterial pressure and the externally applied pressure were measured and mathematically modeled as a function of cuff pressure. A feature-based learning algorithm was then designed to identify PAD patterns by analyzing the parameters of the derived mathematical models. Genetic algorithm and principal component analysis were employed to select the best predictive features distinguishing PAD patterns from normal. A RUSBoost ensemble model using neural network as the base learner was designed to diagnose PAD from genetic algorithm selected features. The proposed method was validated on data collected from 14 PAD patients and 19 healthy individuals. It achieved a high accuracy, sensitivity, and specificity of 91.4%, 90.0%, and 92.1%, respectively, in detecting PAD. The effect of age, a confounding factor that may have impacted our analyzes, was not considered in this study. The proposed method shows promise toward noninvasive and accurate detection of PAD and can be integrated into routine oscillometric blood pressure measurements.

An innovative approach for determining the customized refractive index of ectatic corneas in cataractous patients.

The aim of this study is to determine the customized refractive index of ectatic corneas and also propose a method for determining the corneal and IOL power in these eyes. Seven eyes with moderate and severe corneal ectatic disorders, which had been under cataract surgery, were included. At least three months after cataract surgery, axial length, cornea, IOL thickness and the distance between IOL from cornea, and aberrometry were measured. All the measured points of the posterior and anterior parts of the cornea converted to points cloud and surface by using the MATLAB and Solidworks software. The implanted IOLs were designed by Zemax software. The ray tracing analysis was performed on the customized eye models, and the corneal refractive index was determined by minimizing the difference between the measured aberrations from the device and resulted aberrations from the simulation. Then, by the use of preoperative corneal images, corneal power was calculated by considering the anterior and posterior parts of the cornea and refractive index of 1.376 and the customized corneal refractive index in different regions and finally it was entered into the IOL power calculation formulas. The corneal power in the 4 mm region and the Barrett formula resulted the prediction error of six eyes within ± 1 diopter. It seems that using the total corneal power along with the Barrett formula can prevent postoperative hyperopic shift, especially in eyes with advanced ectatic disorders.

Estimation and evaluation of pseudo-CT images using linear regression models and texture feature extraction from MRI images in the brain region to design external radiotherapy planning.

AIM: The aim of this study is to construct and evaluate Pseudo-CT images (P-CTs) for electron density calculation to facilitate external radiotherapy treatment planning. BACKGROUND: Despite numerous benefits, computed tomography (CT) scan does not provide accurate information on soft tissue contrast, which often makes it difficult to precisely differentiate target tissues from the organs at risk and determine the tumor volume. Therefore, MRI imaging can reduce the variability of results when registering with a CT scan. MATERIALS AND METHODS: In this research, a fuzzy clustering algorithm was used to segment images into different tissues, also linear regression methods were used to design the regression model based on the feature extraction method and the brightness intensity values. The results of the proposed algorithm for dose-volume histogram (DVH), Isodose curves, and gamma analysis were investigated using the RayPlan treatment planning system, and VeriSoft software. Furthermore, various statistical indices such as Mean Absolute Error (MAE), Mean Error (ME), and Structural Similarity Index (SSIM) were calculated. RESULTS: The MAE of a range of 45-55 was found from the proposed methods. The relative difference error between the PTV region of the CT and the Pseudo-CT was 0.5, and the best gamma rate was 95.4% based on the polar coordinate feature and proposed polynomial regression model. CONCLUSION: The proposed method could support the generation of P-CT data for different parts of the brain region from a collection of MRI series with an acceptable average error rate by different evaluation criteria.

A decision support system for mammography reports interpretation.

PURPOSE: Mammography plays a key role in the diagnosis of breast cancer; however, decision-making based on mammography reports is still challenging. This paper aims to addresses the challenges regarding decision-making based on mammography reports and propose a Clinical Decision Support System (CDSS) using data mining methods to help clinicians to interpret mammography reports. METHODS: For this purpose, 2441 mammography reports were collected from Imam Khomeini Hospital from March 21, 2018, to March 20, 2019. In the first step, these mammography reports are analyzed and program code is developed to transform the reports into a dataset. Then, the weight of every feature of the dataset is calculated. Random Forest, Naïve Bayes, K-nearest neighbor (K-NN), Deep Learning classifiers are applied to the dataset to build a model capable of predicting the need for referral to biopsy. Afterward, the models are evaluated using cross-validation with measuring Area Under Curve (AUC), accuracy, sensitivity, specificity indices. RESULTS: The mammography type (diagnostic or screening), mass and calcification features mentioned in the reports are the most important features for decision-making. Results reveal that the K-NN model is the most accurate and specific classifier with the accuracy and specificity values of 84.06% and 84.72% respectively. The Random Forest classifier has the best sensitivity and AUC with the sensitivity and AUC values of 87.74% and 0.905 respectively. CONCLUSIONS: Accordingly, data mining approaches are proved to be a helpful tool to make the final decision as to whether patients should be referred to biopsy or not based on mammography reports. The developed CDSS may also be helpful especially for less experienced radiologists.

A study of factors related to patients' length of stay using data mining techniques in a general hospital in southern Iran.

PURPOSE: The length of stay (LOS) in hospitals is a widely used indicator for goals such as health care management, quality control, utilizing hospital services and resources, and determining the degree of efficiency. Various methods have been used to identify the factors influencing the LOS. This study adopts a comparative approach of data mining techniques for investigating effective factors and predict the length of stay in Shahid-Mohammadi Hospital, Bandar Abbas, Iran. METHODS: Using a dataset consists of 526 patient records of the Shahid-Mohammadi Hospital from March 2016 to March 2017, factors affecting the LOS were ranked using information gain and correlation indices. In addition, classification models for LOS prediction were created based on nine data mining classifiers applied with and without feature selection technique. Finally, the models were compared. RESULTS: The most important factors affecting LOS are the number of para-clinical services, counseling frequency, clinical ward, the specialty and the degree of the doctor, and the cause of hospitalization. In addition, regarding to the classifiers created based on the dataset, the best accuracy (83.91%) and sensitivity (80.36%) belongs to the Logistic Regression and Naïve Bayes respectively. In addition, the best AUC (0.896) belongs to the Random Forest and Generalized Linear classifiers. CONCLUSION: The results showed that most of the proposed models are suitable for classification of the length of stay, although the Logistic Regression might have a slightly better performance than others in term of accuracy, and this model can be used to determine the patients' Length of Stay. In general, continuous monitoring of the factors influencing each of the performance indicators based on proper and accurate models in hospitals is important for helping management decisions.

Application of a neural interface for restoration of leg movements: Intra-spinal stimulation using the brain electrical activity in spinally injured rabbits.

This study aimed to design a neural interface that extracts movement commands from the brain to generate appropriate intra-spinal stimulation to restore leg movement. This study comprised four steps: (1) Recording electrocorticographic (ECoG) signals and corresponding leg movements in different trials. (2) Partial laminectomy to induce spinal cord injury (SCI) and detect motor modules in the spinal cord. (3) Delivering appropriate intra-spinal stimulation to the motor modules for restoration of the movements to those documented before SCI. (4) Development of a neural interface created by sparse linear regression (SLiR) model to detect movement commands transmitted from the brain to the modules. Correlation coefficient (CC) and normalized root mean square (NRMS) error was calculated to evaluate the neural interface effectiveness. It was found that by stimulating detected spinal cord modules, joint angle evaluated before SCI was not significantly different from that of post-SCI (P > 0.05). Based on results of SLiR model, overall CC and NRMS values were 0.63 ± 0.14 and 0.34 ± 0.16 (mean ± SD), respectively. These results indicated that ECoG data contained information about intra-spinal stimulations and the developed neural interface could produce intra-spinal stimulation based on ECoG data, for restoration of leg movements after SCI.

A Comparison of the Efficiency of Using a Deep CNN Approach with Other Common Regression Methods for the Prediction of EGFR Expression in Glioblastoma Patients.

To estimate epithermal growth factor receptor (EGFR) expression level in glioblastoma (GBM) patients using radiogenomic analysis of magnetic resonance images (MRI). A comparative study using a deep convolutional neural network (CNN)-based regression, deep neural network, least absolute shrinkage and selection operator (LASSO) regression, elastic net regression, and linear regression with no regularization was carried out to estimate EGFR expression of 166 GBM patients. Except for the deep CNN case, overfitting was prevented by using feature selection, and loss values for each method were compared. The loss values in the training phase for deep CNN, deep neural network, Elastic net, LASSO, and the linear regression with no regularization were 2.90, 8.69, 7.13, 14.63, and 21.76, respectively, while in the test phase, the loss values were 5.94, 10.28, 13.61, 17.32, and 24.19 respectively. These results illustrate that the efficiency of the deep CNN approach is better than that of the other methods, including Lasso regression, which is a regression method known for its advantage in high-dimension cases. A comparison between deep CNN, deep neural network, and three other common regression methods was carried out, and the efficiency of the CNN deep learning approach, in comparison with other regression models, was demonstrated.

Fuzzy cognitive map based approach for determining the risk of ischemic stroke.

Stroke is the third major cause of mortality in the world. The diagnosis of stroke is a very complex issue considering controllable and uncontrollable factors. These factors include age, sex, blood pressure, diabetes, obesity, heart disease, smoking, and so on, having a considerable influence on the diagnosis of stroke. Hence, designing an intelligent system leading to immediate and effective treatment is essential. In this study, the soft computing method known as fuzzy cognitive mapping was proposed for diagnosis of the risk of ischemic stroke. Non-linear Hebbian learning method was used for fuzzy cognitive maps training. In the proposed method, the risk rate for each person was determined based on the opinions of the neurologists. The accuracy of the proposed model was tested using 10-fold cross-validation, for 110 real cases, and the results were compared with those of support vector machine and K-nearest neighbours. The proposed system showed a superior performance with a total accuracy of (93.6 ± 4.5)%. The data used in this study is available by emailing the first author for academic and non-commercial purposes.

Emotion recognition through EEG phase space dynamics and Dempster-Shafer theory.

Emotions play an important role in our life. Emotion recognition which is considered a subset of brain computer interface (BCI), has drawn a great deal of attention during recent years. Researchers from different fields have tried to classify emotions through physiological signals. Nonlinear analysis has been reported to be successful and effective in emotion classification due to the nonlinear and non-stationary behavior of biological signals. In this study, phase space reconstruction and Poincare planes are employed to describe the dynamics of electroencephalogram (EEG) in emotional states. EEG signals are taken from a reliable database and phase space is reconstructed. A new transformation is introduced in order to quantify the phase space. Dynamic characteristics of the new space are considered as features. Most significant features are selected and samples are classified into four groups including high arousal - high valence (HAHV), low arousal - high valence (LAHV), high arousal - low valence (HALV) and low arousal - low valence (LALV). Classification accuracy was about 90% on average. Results suggest that the proposed method is successful and classification performance is good in comparison with most studies in this field. Brain activity is also reported with respect to investigating brain function during emotion elicitation. We managed to introduce a new way to analyze EEG phase space. The proposed method is applied in a real world and challenging application (i.e. emotion classification). Not only does the proposed method describe EEG changes due to different emotional states but also it is able to represent new characteristics of complex systems. The suggested approach paves the way for researchers to analyze and understand more about chaotic signals and systems.