A5058304766- EEG and Brain-Computer Interfaces
- Functional Brain Connectivity Studies
- ECG Monitoring and Analysis
- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- COVID-19 diagnosis using AI
- Cardiac Imaging and Diagnostics
- Cardiovascular Function and Risk Factors
- Liver Disease Diagnosis and Treatment
- Transcranial Magnetic Stimulation Studies
- Emotion and Mood Recognition
- Neural dynamics and brain function
- Medical Image Segmentation Techniques
- Cardiac Valve Diseases and Treatments
- Advanced MRI Techniques and Applications
- Neuroscience and Neural Engineering
- Advanced X-ray and CT Imaging
- Cardiovascular Health and Disease Prevention
- Non-Invasive Vital Sign Monitoring
- Anesthesia and Sedative Agents
- Image and Signal Denoising Methods
- Artificial Intelligence in Healthcare
- Medical Imaging Techniques and Applications
- Brain Tumor Detection and Classification
- Optical Imaging and Spectroscopy Techniques
Shahid Beheshti University of Medical Sciences
2019-2024
Tehran University of Medical Sciences
2023
Baqiyatallah University of Medical Sciences
2023
Macquarie University
2023
Shahid Beheshti University
2016-2021
Islamic Azad University, Science and Research Branch
2014-2020
Islamic Azad University, Tehran
2015-2017
Iran University of Science and Technology
2010-2014
COVID-19 has infected millions of people worldwide. One the most important hurdles in controlling spread this disease is inefficiency and lack medical tests. Computed tomography (CT) scans are promising providing accurate fast detection COVID-19. However, determining requires highly trained radiologists suffers from inter-observer variability. To remedy these limitations, paper introduces an automatic methodology based on ensemble deep transfer learning for
The objective of this paper is to develop a novel emotion recognition system from electroencephalogram (EEG) signals using effective connectivity and deep learning methods. Emotion an important task for various applications such as human-computer interaction and, mental health diagnosis. aims improve the accuracy robustness by combining different (EC) methods pre-trained convolutional neural networks (CNNs), well long short-term memory (LSTM). EC measure information flow in brain during...
Accurate and noninvasive monitoring of the depth anesthesia (DoA) is highly desirable. Since anesthetic drugs act mainly on central nervous system, analysis brain activity using electroencephalogram (EEG) very useful. This paper proposes a novel automated method for assessing DoA EEG. First, 11 features including spectral, fractal, entropy are extracted from EEG signal then, by applying an algorithm according to exhaustive search all subsets features, combination best (Beta-index, sample...
Abstract Mental workload refers to the cognitive effort required perform tasks, and it is an important factor in various fields, including system design, clinical medicine, industrial applications. In this paper, we propose innovative methods assess mental from EEG data that use effective brain connectivity for purpose of extracting features, a hierarchical feature selection algorithm select most significant finally machine learning models. We have used Simultaneous Task Workload (STEW)...
Abstract This study aims to develop a machine learning approach leveraging clinical data and blood parameters predict non-alcoholic steatohepatitis (NASH) based on the NAFLD Activity Score (NAS). Using dataset of 181 patients, we performed preprocessing including normalization categorical encoding. To identify predictive features, applied sequential forward selection (SFS), chi-square, analysis variance (ANOVA), mutual information (MI). The selected features were used train classifiers SVM,...
Abstract This study aimed to investigate the diagnostic performance of machine learning-based radiomics analysis diagnose coronary artery disease status and risk from rest/stress Myocardial Perfusion Imaging (MPI) single-photon emission computed tomography (SPECT). A total 395 patients suspicious who underwent 2-day stress-rest protocol MPI SPECT were enrolled in this study. The left ventricle myocardium, excluding cardiac cavity, was manually delineated on rest stress images define a volume...
The automatic detection of end-diastole and end-systole frames echocardiography images is the first step for calculation ejection fraction, stroke volume some other features related to heart motion abnormalities. In this paper, manifold learning algorithm applied on 2D find out relationship between one cycle motion. By approach nonlinear embedded information in sequential represented a two-dimensional by LLE each image depicted point reconstructed manifold. There are three dense regions...
Abstract Severity assessment of the novel Coronavirus (COVID‐19) using chest computed tomography (CT) scan is crucial for effective administration right therapeutic drugs and also monitoring progression disease. However, determining severity COVID‐19 needs a highly expert radiologist by visual assessment, which time‐consuming, boring, subjective. This article introduces an advanced machine learning tool to determine mild, moderate, severe from lung CT images. We have used set quantitative...
Prediction of response to Repetitive Transcranial Magnetic Stimulation (rTMS) can build a very effective treatment platform that helps Major Depressive Disorder (MDD) patients receive timely treatment. We proposed deep learning model powered up by state-of-the-art methods classify responders (R) and non-responders (NR) rTMS Pre-treatment Electro-Encephalogram (EEG) signal public TDBRAIN dataset 46 proprietary MDD subjects were utilized create time-frequency representations using Continuous...