Background: Detecting brain tumors in their early stages is crucial. Brain tumors are classified by biopsy, which can only be performed through definitive brain surgery. Computational intelligence-oriented techniques can help physicians identify and classify brain tumors. Herein, we proposed two deep learning methods and several machine learning approaches for diagnosing three types of tumor, i.e., glioma, meningioma, and pituitary gland tumors, as well as healthy brains without tumors, using magnetic resonance brain images to enable physicians to detect with high accuracy tumors in early stages.Materials and Methods: A dataset containing 3264 Magnetic Resonance Imaging (MRI) brain images comprising images of glioma, meningioma, pituitary gland tumors, and healthy brains were used in this study. First, preprocessing and augmentation algorithms were applied to MRI brain images. Next, we developed a new 2D Convolutional Neural Network (CNN) and a convolutional auto-encoder network, both of which were already trained by our assigned hyperparameters. Then 2D CNN includes several convolution layers; all layers in this hierarchical network have a 2*2 kernel function. This network consists of eight convolutional and four pooling layers, and after all convolution layers, batch-normalization layers were applied. The modified auto-encoder network includes a convolutional auto-encoder network and a convolutional network for classification that uses the last output encoder layer of the first part. Furthermore, six machine-learning techniques that were applied to classify brain tumors were also compared in this study.Results: The training accuracy of the proposed 2D CNN and that of the proposed auto-encoder network were found to be 96.47% and 95.63%, respectively. The average recall values for the 2D CNN and auto-encoder networks were 95% and 94%, respectively. The areas under the ROC curve for both networks were 0.99 or 1. Among applied machine learning methods, Multilayer Perceptron (MLP) (28%) and K-Nearest Neighbors (KNN) (86%) achieved the lowest and highest accuracy rates, respectively. Statistical tests showed a significant difference between the means of the two methods developed in this study and several machine learning methods (p-value < 0.05).Conclusion: The present study shows that the proposed 2D CNN has optimal accuracy in classifying brain tumors. Comparing the performance of various CNNs and machine learning methods in diagnosing three types of brain tumors revealed that the 2D CNN achieved exemplary performance and optimal execution time without latency. This proposed network is less complex than the auto-encoder network and can be employed by radiologists and physicians in clinical systems for brain tumor detection.

Purpose. Artificial intelligence (AI) techniques are used in precision medicine to explore novel genotypes and phenotypes data. The main aims of precision medicine include early diagnosis, screening, and personalized treatment regime for a patient based on genetic‐oriented features and characteristics. The main objective of this study was to review AI techniques and their effectiveness in neoplasm precision medicine. Materials and Methods. A comprehensive search was performed in Medline (through PubMed), Scopus, ISI Web of Science, IEEE Xplore, Embase, and Cochrane databases from inception to December 29, 2021, in order to identify the studies that used AI methods for cancer precision medicine and evaluate outcomes of the models. Results. Sixty‐three studies were included in this systematic review. The main AI approaches in 17 papers (26.9%) were linear and nonlinear categories (random forest or decision trees), and in 21 citations, rule‐based systems and deep learning models were used. Notably, 62% of the articles were done in the United States and China. R package was the most frequent software, and breast and lung cancer were the most selected neoplasms in the papers. Out of 63 papers, in 34 articles, genomic data like gene expression, somatic mutation data, phenotype data, and proteomics with drug‐response which is functional data was used as input in AI methods; in 16 papers’ (25.3%) drug response, functional data was utilized in personalization of treatment. The maximum values of the assessment indicators such as accuracy, sensitivity, specificity, precision, recall, and area under the curve (AUC) in included studies were 0.99, 1.00, 0.96, 0.98, 0.99, and 0.9929, respectively. Conclusion. The findings showed that in many cases, the use of artificial intelligence methods had effective application in personalized medicine.

Background. Leukemia is fatal cancer in both children and adults and is divided into acute and chronic. Acute lymphoblastic leukemia (ALL) is a subtype of this cancer. Early diagnosis of this disease can have a significant impact on the treatment of this disease. Computational intelligence‐oriented techniques can be used to help physicians identify and classify ALL rapidly. Materials and Method. In this study, the utilized dataset was collected from a CodaLab competition to classify leukemic cells from normal cells in microscopic images. Two famous deep learning networks, including residual neural network (ResNet‐50) and VGG‐16 were employed. These two networks are already trained by our assigned parameters, meaning we did not use the stored weights; we adjusted the weights and learning parameters too. Also, a convolutional network with ten convolutional layers and 2∗2 max‐pooling layers—with strides 2—was proposed, and six common machine learning techniques were developed to classify acute lymphoblastic leukemia into two classes. Results. The validation accuracies (the mean accuracy of training and test networks for 100 training cycles) of the ResNet‐50, VGG‐16, and the proposed convolutional network were found to be 81.63%, 84.62%, and 82.10%, respectively. Among applied machine learning methods, the lowest obtained accuracy was related to multilayer perceptron (27.33%) and highest for random forest (81.72%). Conclusion. This study showed that the proposed convolutional neural network has optimal accuracy in the diagnosis of ALL. By comparing various convolutional neural networks and machine learning methods in diagnosing this disease, the convolutional neural network achieved good performance and optimal execution time without latency. This proposed network is less complex than the two pretrained networks and can be employed by pathologists and physicians in clinical systems for leukemia diagnosis.

Introduction: Emerging virtual technologies and cognitive rehabilitation methods are two new treatment approaches that can be used to strengthen cognitive functions in Autism Spectrum Disorder (ASD). The main aim of this study was to examine the effect of using virtual reality-based approaches on cognitive disorders of children and adults with ASD.Methods: This systematic review was conducted on scientific papers to determine the effects of virtual reality-based technologies on the cognitive functions of children and adults with ASD. We identified 688 studies related to this topic and filtered them down to 17 articles, and then extracted the effects of interventions on cognitive outcomes.Results: A total of 17 studies met the inclusion criteria, in which 226 persons with ASD had taken place. The sample size in the selected studies ranged from 1 to 56 participants (Median: 8, Q1: 3.5, Q3: 15.5). Four of the studies were case–control studies, ten were pre-test/post-test studies, and three were Randomized Control Trials (RCTs). Results of 16 studies showed significant progress in various cognitive indexes, such as task learning, attention, executive functioning, and daily skills in people with ASD. In most studies, virtual technologies had beneficial effects on reducing cognitive problems, but existing limitations could reduce their effectiveness. These limitations included the cost of virtual reality devices, inappropriate size of software, the weight of devices, potential addiction, intolerance of wearing glasses or headsets by people with autism (especially in children), and the possibility of eye injury.Conclusion: Applying appropriate virtual-based approaches could improve cognitive indexes in people with ASD. However, further studies are needed to investigate the real effects of these technologies in the long run.

Objective. A large number of patients need critical physical rehabilitation after the stroke. This study aimed to review and report the result of published studies, in which newly emerged games were employed for physical rehabilitating in poststroke patients. Materials and Methods. This systematic review study was performed based on the PRISMA method. A comprehensive search of PubMed, Scopus, IEEE Xplore Digital Library, and ISI Web of Science was conducted from January 1, 2014, to November 9, 2020, to identify related articles. Studies have been entered in this review based on inclusion and exclusion criteria, in which new games have been used for physical rehabilitation. Results. Of the 1326 retrieved studies, 60 of them met our inclusion criteria. Virtual reality-oriented games were the most popular type of physical rehabilitation approach for poststroke patients. The Nintendo Wii Fit game was used more than other games. The reviewed games were mostly operated to balance training and limb mobilization. Based on the evaluation results of the utilized games, only in three studies, applied games were not effective. In other studies, games had effective outcomes for target body members. Conclusions. The results indicate that modern games are efficient in poststroke patients physical rehabilitation and can be used alongside conventional methods.