hamid sharini

The use of artificial intelligence algorithms to help with accurate diagnosis in medical images is one of the most important applications of this technology in the field of medical imaging. In this research, the possibility of replacing simple chest radiography instead of CT scan using machine learning models to detect pneumothorax was investigated in cases where CT is usually requested.

This study is analytical and was conducted from November 2022 to May 2023 at Kermanshah University of Medical Sciences. The data used in this research was extracted from the files of 350 patients suspected of pneumothorax. The collected images were pre-processed in MATLAB software. Then, three machine learning algorithms, including Logistic elastic net regression (LENR), Logistic lasso regression (LLR) and Adaptive Boosting (AdaBoost) were used. To evaluate the performance of these models, the criteria of precision, accuracy, sensitivity, specificity, area under the receiver operating characteristic curve (AUC), F1 score, and misclassification were used.

In the AdaBoost model, the accuracy value in radiographic and CT images was calculated as 98.89% and 98.63%, respectively, and the precision value was calculated as 99.17% and 98.27%, respectively. In radiographic images, the AUC value for AdaBoost model was calculated as 100% and in CT scan images as 96.96%. The F1 score for the same model in radiographic was 99% and in CT images was 98.68%. The specificity value for the AdaBoost model was calculated as 99.45% in radiographic images and 94.67% in CT scan images. In the LLR model, the AUC value for radiographic and CT scan images was 99.87% and 99.02%, respectively.

According to the criteria evaluated in the present study, two LLR and AdaBoost models have similar performance in radiographic and CT images in terms of pneumothorax detection ability, so that this complication can also be diagnosed with high precision level using machine learning techniques on the radiographic images and thus receiving higher levels of radiation doses due to CT scan can be avoided in these patients.

Insomnia is a common sleep disorder with negative consequences such as decreased quality of life. In this study, the effect of sleep deprivation on memory in both young and older adults was investigated using functional magnetic resonance imaging (fMRI).

In this retrospective study, fMRI data of 40 healthy subjects (17 young and 23 older people) who had a one-month sleep deprivation period (during the experiment they woke up three hours earlier than usual) were obtained. Then, pre-processing was done to remove artifacts and noise. Finally, data processing was completed in order to extract the brain activity map focusing on brain areas related to memory.

Findings showed that the brain activity of most areas are reduced due to insomnia. In the young group, 17 functional connections were obtained at the beginning of the study which decreased to only one connection after the insomnia period. In older adults there were seven connections at the beginning of the study that decreased to four after the insomnia period (P< 0.05).

Brain map analysis, including connections and activity levels of memory-related areas, showed that sleep deprivation affects the brains of young and old people. Our findings can pave the way for future studies to understand the effect of insomnia on memory and brain.

fNIRS is a useful tool designed to record the changes in the density of blood’s oxygenated hemoglobin (oxyHb) and deoxygenated hemoglobin (deoxyHb) molecules during brain activity. This method has made it possible to evaluate the hemodynamic changes of the brain during neuronal activity in a completely non-aggressive manner. The present study has been designed to investigate and evaluate the brain cortex activities during imagining of the execution of wrist motor tasks by comparing fMRI and fNIRS imaging methods. This novel observational Optical Imaging study aims to investigate the brain motor cortex activity during imagining of the right wrist motor tasks in vertical and horizontal directions. To perform the study, ten healthy young right-handed volunteers were asked to think about right-hand movements in different directions according to the designed movement patterns. The required data were collected in two wavelengths, including 845 and 763 nanometers using a 48 channeled fNIRS machine. Analysis of the obtained data showed the brain activity patterns during imagining of the execution of a movement are formed in various points of the motor cortex in terms of location. Moreover, depending on the direction of the movement, activity plans have distinguishable patterns. The results showed contralateral M1 was mainly activated during imagining of the motor cortex (p <0.05). The results of our study showed that in brain imaging, it is possible to distinguish between patterns of activities during wrist motion in different directions using the recorded signals obtained through near-infrared Spectroscopy. The findings of this study can be useful in further studies related to movement control and BCI.

Functional Magnetic resonance imaging (fMRI) measures the small fluctuation of blood flow happening during task-fMRI in brain regions. This research investigated these active, imagery and passive movements in volunteers design to permit a comparison of their capabilities in activating the brain areas. In this applied research, the activity of the motor cortex during the right-wrist movement was evaluated in 10 normal volunteers under active, passive, and imagery conditions. T2* weighted, three-dimensional functional images were acquired using a BOLD sensitive gradient-echo EPI (echo planar imaging) sequence with echo time (TE) of 30 ms and repetition time (TR) of 2000 ms. The functional data, which included 248 volumes per subject and condition, were acquired using the blocked design paradigm. The images were analyzed by the SPM12 toolbox, MATLAB software. The findings determined a significant increase in signal intensity of the motor cortex while performing the test compared to the rest time (p < 0.05). It was also observed that the active areas in hand representation of the motor cortex are different in terms of locations and the number of voxels in different wrist directions. Moreover, the findings showed that the position of active centers in the brain is different in active, passive, and imagery conditions. Results confirm that primary motor cortex neurons play an essential role in the processing of complex information and are designed to control the direction of movement. It seems that the findings of this study can be applied for rehabilitation studies.

Alzheimer’s disease (AD) is the most common brain failure for which no cure has yetbeen found. The disease starts with a disturbance in the brain structure,then it manifests itselfclinically. Therefore,by timely,correct diagnosis of changes in the structure of the brain,theoccurrence of this disease or at least its progression can be prevented. Due to the fact that magneticresonance imaging (MRI) can be used to obtain very useful information from the brain,and alsobecause it is non-invasive,this method has been considered by researchers.Materials,

The data were obtained from an MRI database (MIRIAD) of 69 subjectsincluding 46 AD patients,23 healthy controls (HC). Individuals were categorized based on twocriteria including NINCDS-ADRAD,MMSE,as the gold standard. In this paper,we used thesupport vector machine (SVM),Bayesian SVM classifiers.

Using the SVM classifier with Gaussian radial basis function (RBF) kernel,we distinguishedAD,HC with an accuracy of 88.34%. The most important regions of interest (ROIs) in this studyincluded right para hippocampal gyrus,left para hippocampal gyrus,right hippocampus,and lefthippocampus.

This study showed that the SVM model with Gaussian RBF kernel can distinguish ADfrom HC with high accuracy. These studies are of great importance in medical science. Based onthe results of this study

Nowadays, the number of people diagnosed with movement disorders is increasing. Therefore, the evaluation of brain activity during motor task performance has attracted the attention of researchers in recent years. Functional Near-Infrared Spectroscopy (fNIRS) is a useful method that measures hemodynamic changes in the brain cortex based on optical principles. The purpose of this study was to evaluate the brain’s cortical activation in passive movement of the wrist. In current study, the activation of the brain's motor cortex during passive movement of the right wrist was investigated. To perform this study, ten healthy young right-handed volunteers were chosen. The required data were collected using a commercial 48-channel continuous wave fNIRS machine, using two different wavelengths of 765 and 855 nm at 10 Hz sampling rate. Analysis of collected data showed that the brain's motor cortex during passive motion was significantly activated (p≤0.05) compared to rest. Motor cortex activation patterns depending on passive movement direction were separated. In different directions of wrist movement, the maximum activation was recorded at the primary motor cortex (M1). The present study has investigated the ability of fNIRS to evaluate cortical activation during passive movement of the wrist. Analysis of recording signals showed that different directions of movement have specific activation patterns in the motor cortex.

Optical imaging has attracted the researcher’s attention in recent years as an uncompromising and efficient method to measure the changes in brain cortex activity. Functional Near-Infrared Spectroscopy (fNIRS) is a method that measures hemodynamic changes in the brain cerebral cortex based on optical principles.

The current study aimed to evaluate the activities of the brain cortex during wrist movement using fNIRS.

In this study, the activity of the brain motor cortex was investigated during right wrist movement in 10 young righthanded volunteers. Data were collected using a 48-channel fNIRS device with two wavelengths of 855 nm and 765 nm. For this experiment, 20 channels were used and the sampling frequency was set at 10 Hz.

Signal intensity in the motor cortex was significantly higher during movement than in the rest (P ≤ 0.05). The activation map of wrist movements was separated spatially in the motor cortex. The highest activity was recorded in the primary motor cortex (M1). There was a significant difference in the focus of the maximum activation of the brain between the four main directions.

It is possible to differentiate between different directions of movement using near-infrared signals. The presence of directional activation in the cerebral cortex helps confirm the notion that this part of the brain participates in the processing of complex information besides controlling the movement of different parts of the body.

Alzheimer's disease (AD) is the most common disorder of dementia, which has not been cured after its occurrence. AD progresses indiscernible, first destroy the structure of the brain and subsequently becomes clinically evident. Therefore, the timely and correct diagnosis of these structural changes in the brain is very important and it can prevent the disease or stop its progress. Nowadays, remark to this fact that magnetic resonance imaging (MRI) provides very useful and detailed information, and due to non-invasiveness, this method has been great interest to the researchers. The aim of this study was diagnosis of AD with MRI by support vector machine model (SVM).
This is an analytical and modeling research which done in School of Public Health, Kermanshah University of Medical Science, Iran, from February 2017 to November 2017. The data used in this study was a database named Miriad containing brain MRI of 69 individuals (46 Alzheimer's disease and 23 healthy subjects) that was collected at the central hospital in London. Individuals were categorized into two groups of healthy and Alzheimer's disease with two criteria: NINCDS-ADRAD and MMSE (as the golden standard). In this paper SVM model with three linear, binomial and Gaussian kernels was used to distinguish Alzheimer`s disease from healthy individuals.
Finally, SVM model with Gaussian kernel, separated AD and healthy subjects with 88.34% accuracy. The most important Areas for Alzheimer were three Area: Right para hippocampal gyrus, Left para hippocampal gyrus and Right hippocampus. The clinical result of this study is to identify the most important ROI for the diagnosis of Alzheimer's by a clinical specialist. Experts should focus on atrophy in the three Areas.
This study showed that the SVM model with Gaussian RBF kernel can separated AD from healthy subjects by high accuracy. Based on results of this study, can make a software to use in MRI centers for screening AD test by people over the age of 50 years