A5089587974- Radiomics and Machine Learning in Medical Imaging
- Radiation Dose and Imaging
- Advanced X-ray and CT Imaging
- COVID-19 diagnosis using AI
- Advanced Radiotherapy Techniques
- Radioactivity and Radon Measurements
- Glioma Diagnosis and Treatment
- Ultrasound in Clinical Applications
- Radiology practices and education
- MRI in cancer diagnosis
- Effects of Radiation Exposure
- Chemical Thermodynamics and Molecular Structure
- Thermal and Kinetic Analysis
- Radiation Therapy and Dosimetry
- Breast Lesions and Carcinomas
- Machine Learning in Materials Science
- Medical Imaging Techniques and Applications
- MicroRNA in disease regulation
- Breast Cancer Treatment Studies
- RNA Interference and Gene Delivery
- Electronic Health Records Systems
- COVID-19 and healthcare impacts
- Extracellular vesicles in disease
- Radiation Shielding Materials Analysis
- Graphite, nuclear technology, radiation studies
Kurdistan University of Medical Sciences
2024-2025
Tarbiat Modares University
2016-2024
This study evaluates the reproducibility of machine learning models that integrate radiomics and deep features (features extracted from a 3D autoencoder neural network) to classify various brain hemorrhages effectively. Using dataset 720 patients, we 215 (RFs) 15,680 (DFs) CT images. With rigorous screening based on Intraclass Correlation Coefficient thresholds (>0.75), identified 135 RFs 1054 DFs for analysis. Feature selection techniques such as Boruta, Recursive Elimination (RFE),...
Gliomas, the most common primary brain tumors, are classified into low-grade glioma (LGG) and high-grade (HGG) based on aggressiveness. Accurate preoperative differentiation is vital for effective treatment prognosis, but traditional methods like biopsy have limitations, such as sampling errors procedural risks. This study introduces a comprehensive model that combines radiomics features (RFs) deep (DFs) from magnetic resonance imaging (MRI) scans, integrating clinical factors with advanced...
We aimed to analyze the prognostic power of CT-based radiomics models using data 14,339 COVID-19 patients.
ABSTRACT This study evaluates the efficacy of four deep learning methods—YOLOv8, VGG16, ResNet101, and EfficientNet—for classifying mammography images into normal, benign, malignant categories using a large‐scale, multi‐institutional dataset. Each dataset was divided training testing groups with an 80%/20% split, ensuring that all examinations from same patient were consistently allocated to split. The set for class contained 10 220 images, benign 6086 normal 8526 images. For testing, had...
Abstract Purpose To derive and validate an effective radiomics-based model for differentiation of COVID-19 pneumonia from other lung diseases using a very large cohort patients. Methods We collected 19 private 5 public datasets, accumulating to 26,307 individual patient images (15,148 COVID-19; 9,657 with e.g. non-COVID-19 pneumonia, cancer, pulmonary embolism; 1502 normal cases). Images were automatically segmented validated deep learning (DL) the results carefully reviewed. first cropped...
Abstract To derive and validate an effective machine learning radiomics‐based model to differentiate COVID‐19 pneumonia from other lung diseases using a large multi‐centric dataset. In this retrospective study, we collected 19 private five public datasets of chest CT images, accumulating 26 307 images (15 148 COVID‐19; 9657 including non‐COVID‐19 pneumonia, cancer, pulmonary embolism; 1502 normal cases). We tested 96 learning‐based models by cross‐combining four feature selectors (FSs) eight...
Abstract Background Notwithstanding the encouraging results of previous studies reporting on efficiency deep learning (DL) in COVID‐19 prognostication, clinical adoption developed methodology still needs to be improved. To overcome this limitation, we set out predict prognosis a large multi‐institutional cohort patients with using DL‐based model. Purpose This study aimed evaluate performance privacy‐preserving federated (DPFL) predicting outcomes chest CT images. Methods After applying...
Abstract The main focus of the current study was to fabricate fibrous nanocomposite based on polyacrylonitrile (PAN) fibers containing Bi 2 O 3 NPs as X‐ray shielding material. were synthesized solid dispersion evaporation method and dispersed into PAN polymer solution with different weight concentrations. electrospinning technique used nanocomposite. morphology, surface functional group, wettability, elemental analysis, efficacy fabricated thoroughly evaluated. dimeter nanocomposites 10,...
Due to different treatment strategies, it is extremely important differentiate between glioblastoma multiforme (GBM) and brain metastases (MET). It often proves difficult distinguish GBM MET using MRI due their similar appearance on the imaging modalities. Surgical methods are still necessary for definitive diagnosis, despite importance of magnetic resonance in detecting, characterizing, monitoring tumors. We introduced an accurate, convenient, user-friendly method through routine sequence...
Abstract Aim: To evaluate the dosimetric parameters of level II lymph nodes in chest wall three-dimensional conformal radiotherapy (3D-CRT) and intensity-modulated (IMRT) mastectomy patients using dual-isocentric (DIT) mono-isocentric techniques (MIT). Materials methods: Computed tomography (CT) images 20 undergoing external were used as input data for abovementioned techniques. Selected calculated axillary I–III nodes, wall, heart lung. Paired t -test statistical analysis was comparing...
Purpose: The danger of radiation at low doses continues linearly, and without a threshold, investigations concluded that although the risk cancer from Computed Tomography (CT) scans is low, it not zero. This study aims to determine patient's dose estimate Lifetime Attributable Risk (LAR) incidence for single chest CT scan in children. Materials Methods: We divided 1,105 children into four age groups: 0 years, 5 10 15 years. Dosimetric data were plugged VirtualDoseCT software, organ effective...
Abstract Objective In this large multi-institutional study, we aimed to analyze the prognostic power of computed tomography (CT)-based radiomics models in COVID-19 patients. Methods CT images 14,339 patients with overall survival outcome were collected from 19 medical centers. Whole lung segmentations performed automatically using a previously validated deep learning-based model, and regions interest further evaluated modified by human observer. All resampled an isotropic voxel size,...
Introduction: Nowadays, we are witnessing an exponential use of interventional radiology techniques in different communities. After CT, the second factor increasing patients’ doses societies. Measuring patient from aforementioned methods has been recommended by many radiation protection professional organizations such as ICRP and IAEA. Our aim was to measure/calculate entrance skin also necessary parameters required estimate relevant effective for common diagnostic therapeutic...
Introduction: Medical uses of radiation have grown very rapidly over in the past two decades, medical represent largest source exposure to people, The most important methods diagnosis are useses diagnostic radiology exams. Although use these is beneficial for treatment patients, but ionizing produces ion pairs, radicals, primary, secondary, and tertiary chemical reactions body. main purposes this study were investigate patient dose common radiographic examinations Materials Methods: This...