A5070723046- Radiomics and Machine Learning in Medical Imaging
- Advanced X-ray and CT Imaging
- Medical Imaging Techniques and Applications
- AI in cancer detection
- Advanced Radiotherapy Techniques
- Radiation Dose and Imaging
- COVID-19 diagnosis using AI
- Lung Cancer Diagnosis and Treatment
- Digital Radiography and Breast Imaging
- Radiation Therapy and Dosimetry
- Oral health in cancer treatment
- Head and Neck Cancer Studies
- X-ray Spectroscopy and Fluorescence Analysis
- Endometrial and Cervical Cancer Treatments
- Brain Tumor Detection and Classification
- Gastric Cancer Management and Outcomes
- Mobile Health and mHealth Applications
- Radioactivity and Radon Measurements
- Physical Activity and Health
- MRI in cancer diagnosis
- Plasma Applications and Diagnostics
- Thyroid Cancer Diagnosis and Treatment
- Artificial Intelligence in Healthcare and Education
- Nuclear physics research studies
- Nuclear Physics and Applications
The University of Texas MD Anderson Cancer Center
2021-2025
Iran University of Medical Sciences
2017-2024
Princess Margaret Cancer Centre
2020-2023
University Health Network
2020-2023
University of Toronto
2020-2021
Isfahan University of Medical Sciences
2015
Iran Meteorological Organization
2015
University of Isfahan
2015
Coronavirus disease 2019 (Covid-19) is highly contagious with limited treatment options. Early and accurate diagnosis of Covid-19 crucial in reducing the spread its accompanied mortality. Currently, detection by reverse transcriptase-polymerase chain reaction (RT-PCR) gold standard outpatient inpatient Covid-19. RT-PCR a rapid method; however, accuracy only ~70-75%. Another approved strategy computed tomography (CT) imaging. CT imaging has much higher sensitivity ~80-98%, but similar 70%. To...
To train a convolutional neural network (CNN) model from scratch to automatically detect tuberculosis (TB) chest X-ray (CXR) images and compare its performance with transfer learning based technique of different pre-trained CNNs.We used two publicly available datasets postero-anterior radiographs, which are Montgomery County, Maryland, Shenzhen, China. A CNN (ConvNet) was trained TB on radiographs. Also, CNN-based approach using five models, including Inception_v3, Xception, ResNet50, VGG19,...
PurposeTo establish the early prediction models of radiation-induced oral mucositis (RIOM) based on baseline CT-based radiomic features (RFs), dosimetric data, and clinical by machine learning for head neck cancer (HNC) patients.MethodsIn this single-center prospective study, 49 HNCs treated with curative intensity modulated radiotherapy (IMRT) were enrolled. Baseline CT images (i.e., simulation), dosimetric, collected. RIOM was assessed using CTCAE v.5.0. RFs extracted from...
Pneumonia is a lung infection and causes the inflammation of small air sacs (Alveoli) in one or both lungs. Proper faster diagnosis pneumonia at an early stage imperative for optimal patient care. Currently, chest X-ray considered as best imaging modality diagnosing pneumonia. However, interpretation images challenging. To this end, we aimed to use automated convolutional neural network-based transfer-learning approach detect paediatric radiographs.Herein, using four different pre-trained...
Coronavirus disease 2019 (Covid-19) is highly contagious with limited treatment options. Early and accurate diagnosis of Covid-19 crucial in reducing the spread its accompanied mortality. Currently, detection by reverse transcriptase polymerase chain reaction (RT-PCR) gold standard outpatient inpatient Covid-19. RT-PCR a rapid method, however, accuracy only ~70-75%. Another approved strategy computed tomography (CT) imaging. CT imaging has much higher sensitivity ~80-98%, but similar 70%. To...
Background: Generalizability and domain dependency are critical challenges in developing predictive models for healthcare, particularly medical diagnostics radiation oncology. Predictive designed to assess tumor recurrence rely on comprehensive high-quality datasets, encompassing treatment planning parameters, imaging protocols, patient-specific data. However, dependency, arising from variations dose calculation algorithms, computed tomography (CT) density conversion curves, modalities,...
Artificial intelligence in automatic classification of invasive ductal carcinoma breast cancer digital pathology images
Abstract In this study, an inter-fraction organ deformation simulation framework for the locally advanced cervical cancer (LACC), which considers anatomical flexibility, rigidity, and motion within image deformation, was proposed. Data included 57 CT scans (7202 2D slices) of patients with LACC randomly divided into train ( n = 42) test 15) datasets. addition to images corresponding RT structure (bladder, cervix, rectum), bone segmented, coaches were eliminated. The correlated stochastic...
Purpose Evaluation of the organ dose in pediatric patients up to 15 years old and Estimation lifetime attributable risk (LAR) cancer incidence computed tomography procedures.Materials methods Data from 532 below was collected they were categorized into four age groups <1, 1–5, 5–10, 10–15 old. NCICT software used calculate dose, LAR has been estimated according BEIR VII report.Results The highest median all related eye lens (head scan), thyroid (chest colon (abdomen-pelvic scan). average...
Objectives This study investigated the potential of a clinical decision support approach for classification metastatic and tumor‐free cervical lymph nodes (LNs) in papillary thyroid carcinoma on basis radiologic textural analysis through ultrasound (US) imaging. Methods In this research, 170 LNs were examined by proposed method. To discover difference between groups, US imaging was used extraction features. The features B‐mode scans included echogenicity, margin, shape, presence...
This study was designed to assess the dose accumulation (DA) of bladder and rectum between brachytherapy fractions using hybrid-based deformable image registration (DIR) compare it with simple summation (SS) approach GEC-ESTRO in cervical cancer patients.Patients (n = 137) treated 3D conformal radiotherapy three high-dose-rate were selected. CT images acquired delineate organs at risk targets according recommendations. In order determine DA for rectum, DIR done different results compared...
Studies have shown that radiomic features are sensitive to the variability of imaging parameters (e.g., scanner models), and one major challenges in these studies lies improving robustness quantitative against variations datasets from multi-center studies. Here, we assess impact choice on computed tomography (CT)-derived predict association oropharyngeal squamous cell carcinoma with human papillomavirus (HPV). This experiment was performed CT image acquired two different manufacturers. We...
Metal artifacts are one of the major issues encountered in computed tomography (CT) images since they may make distinguishing healthy and tumor organs computing dose distribution through radiotherapy very difficult. Accordingly, designing generative adversarial neural networks (GANs) will help reduce metal artifacts. Training validating with without were simulated MATLAB. Then, these used as input data for GAN, while CT 30 patients head neck cancer testing GAN. Finally, quality metrics...
Background and purposeComputed tomography (CT) is one of the most common medical imaging modalities in radiation oncology radiomics research, computational voxel-level analysis images. Radiomics vulnerable to effects dental artifacts (DA) caused by metal implants or fillings can hamper future reproducibility on new datasets. In this study we seek better understand robustness quantitative radiomic features DAs. Furthermore, propose a novel method detecting DAs order safeguard studies improve...
Recently availability of large scale mammography databases enable researchers to evaluates advanced tumor detections applying deep convolution networks (DCN) images which is one the common used imaging modalities for early breast cancer. With recent advance learning, performance detection has been developed by agreat extent, especially using R-CNNs or Region neural networks.This study a simple faster R-CNN detector lesion MIAS databases.
Abstract The main purpose of this pilot study was to assess the regional diagnostic reference level (RDRL) computed tomography (CT) examinations optimise medical exposure in five pediatric imaging centers Tehran, Iran where most frequent CT were investigated. For each patient, volume dose indexes (CTDIvol) and length product (DLP) group recorded their third quartile calculated set as RDRL. Pediatrics divided into four age groups (&lt;1; 1–5; 5–10 10–15 years). Then, values for head,...
Background: Breast cancer is one of the most causes death in women. Early diagnosis and detection Invasive Ductal Carcinoma (IDC) an important key for treatment IDC. Computer-aided approaches have great potential to improve accuracy. In this paper, we proposed a deep learning-based method automatic classification IDC whole slide images (WSI) breast cancer. Furthermore, different types neural networks training such as from scratch transfer learning classify were evaluated. Methods: total,...
Early detection and monitoring of kidney function during the post-transplantation period is one most important issues for improving accuracy an initial diagnosis. The aim this study was to evaluate texture analysis (TA) in scintigraphic imaging detect changes status after transplantation.Scintigraphic images were used TA from a total 94 allografts (39 rejected 55 non-rejected). Images corresponding frames at 2nd, 5th, 20th minute determine optimum time point differences features between...
Background: Use of hair samples to analyze the trace element concentrations is one interesting fields among many researchers. X-ray fluorescence (XRF) considered as most common methods in studying concentration elements tissues and also crystalline materials, using low energy X-ray. In present study, we aimed evaluate scalp sample through XRF spectroscopy signal processing techniques a screening tool for prostate cancer. Methods: Hair 22 men (including 11 healthy patients) were analyzed. All...