A5073945430- Radiomics and Machine Learning in Medical Imaging
- Glioma Diagnosis and Treatment
- Advanced MRI Techniques and Applications
- Advanced Neuroimaging Techniques and Applications
- MRI in cancer diagnosis
- Advanced NMR Techniques and Applications
- Functional Brain Connectivity Studies
- Epilepsy research and treatment
- Acne and Rosacea Treatments and Effects
- Medical Imaging Techniques and Applications
- Cancer-related cognitive impairment studies
- Electron Spin Resonance Studies
- Brain Metastases and Treatment
- Artificial Intelligence in Healthcare and Education
- Machine Learning in Healthcare
- Neurobiology of Language and Bilingualism
- melanin and skin pigmentation
- Bone Tissue Engineering Materials
- MicroRNA in disease regulation
- Protein Structure and Dynamics
- Cardiac Imaging and Diagnostics
- Enzyme Structure and Function
- Hepatocellular Carcinoma Treatment and Prognosis
- Redox biology and oxidative stress
- Thyroid and Parathyroid Surgery
Tehran University of Medical Sciences
2024
University of California, San Diego
2017-2023
University of California, San Francisco
2014-2020
San Diego State University
2019-2020
Boston University
2020
Medical University of South Carolina
2020
Epilepsy Foundation
2019
Wake Forest University
2016-2018
United States Nuclear Regulatory Commission
2018
Oxford University Press (United Kingdom)
2018
Purpose To examine the effects of subconcussive impacts resulting from a single season youth (age range, 8–13 years) football on changes in specific white matter (WM) tracts as detected with diffusion-tensor imaging absence clinically diagnosed concussions. Materials and Methods Head impact data were recorded by using Impact Telemetry system quantified combined-probability risk-weighted cumulative exposure (RWECP). Twenty-five male participants evaluated for seasonal fractional anisotropy...
To assess feasibility of training a convolutional neural network (CNN) to automate liver segmentation across different imaging modalities and techniques used in clinical practice apply this enable automation biometry.We trained 2D U-Net CNN for two stages using 330 abdominal MRI CT exams acquired at our institution. First, we the with non-contrast multi-echo spoiled-gradient-echo (SGPR)images 300 provide multiple signal-weightings. Then, transfer learning generalize additional images from 30...
Background Cardiac MRI is limited by long acquisition times, yet faster of smaller-matrix images reduces spatial detail. Deep learning (DL) might enable both and higher detail via super-resolution. Purpose To explore the feasibility using DL to enhance from small-matrix acquisitions evaluate its performance against that conventional image upscaling methods. Materials Methods Short-axis cine cardiac examinations performed between January 2012 December 2018 at one institution were...
To identify distinct cognitive phenotypes in temporal lobe epilepsy (TLE) and evaluate patterns of white matter (WM) network alterations associated with each phenotype.
Abstract New magnetic resonance (MR) molecular imaging techniques offer the potential for noninvasive, simultaneous quantification of metabolic and perfusion parameters in tumors. This study applied a three-dimensional dynamic dual-agent hyperpolarized 13C spectroscopic approach with 13C-pyruvate 13C-urea to investigate differences metabolism between low- high-grade tumors transgenic adenocarcinoma mouse prostate (TRAMP) model cancer. Dynamic MR data were corrected T1 relaxation RF...
Purpose To develop and evaluate a system to prescribe imaging planes for cardiac MRI based on deep learning (DL)−based localization of key anatomic landmarks. Materials Methods Annotated landmarks 892 long-axis (LAX) 493 short-axis (SAX) cine steady-state free precession series from MR images were retrospectively collected between February 2012 June 2017. U-Net−based heatmap regression was used landmarks, which compute planes. Performance evaluated by comparing distances plane angle...
The distributed white matter network underlying language leads to difficulties in extracting clinically meaningful summaries of neural alterations leading impairment. Here we determine the predictive ability structural connectome (SC), compared with global measures tract microstructure and clinical data, discriminate impaired patients temporal lobe epilepsy (TLE) from TLE without T1- diffusion-MRI, variables (CVs), neuropsychological naming verbal fluency were available for 82 patients....
The accurate detection and characterization of cancerous tissue is still a major problem for the clinical management individual cancer patients monitoring their response to therapy. MRI with hyperpolarized agents promising technique because it can non-invasively provide local assessment metabolic profile. In this work, we measured kinetics [1-(13)C] pyruvate (13)C-urea in prostate liver tumor models using compressed sensing dynamic MRSI method. A kinetic model fitting method was developed...
Radiation therapy (RT) is a critical treatment modality for patients with brain tumors, although it can cause adverse effects. Recent data suggest that RT associated dose-dependent cortical atrophy, which could disrupt neocortical networks. This study examines whether affects structural network properties in tumor patients. We applied graph theory to MRI-derived thickness estimates of 54 before and after RT. Cortical surfaces were parcellated into 68 regions correlation matrices created pre-...
Abstract Objectives Temporal lobe epilepsy ( TLE ) is known to affect large‐scale gray and white matter networks, these network changes likely contribute the verbal memory impairments observed in many patients. In this study, we investigate multimodal imaging patterns of brain alterations evaluate sensitivity different measures impairment. Methods Diffusion tensor DTI ), volumetric magnetic resonance vMRI resting‐state functional MRI (rs‐ fMRI were evaluated 46 patients with 33 healthy...
Purpose Delayed enhancement imaging is an essential component of cardiac MRI, which used widely for the evaluation myocardial scar and viability. The selection optimal inversion time (TI) or null point (TI NP ) to suppress background signal required. purpose this study was assess feasibility automated TI using a convolutional neural network (CNN). We hypothesized that CNN may use spatial temporal characteristics from inversion‐recovery scout select , without aid human observer. Methods...
<h3>BACKGROUND AND PURPOSE:</h3> Treatment with bevacizumab is standard of care for recurrent high-grade gliomas; however, monitoring response to treatment following remains a challenge. The purpose this study was determine whether quantifying the sharpness fluid-attenuated inversion recovery hyperintense border using measure derived from texture analysis—edge contrast—improves evaluation in patients gliomas. <h3>MATERIALS METHODS:</h3> MRIs were evaluated 33 gliomas before and after...
We assessed the effect of purmorphamine along with collagen/hydroxyapatite scaffold in inducing osteogenesis human endometrial stem cells (hEnSCs). The adhesion, viability, proliferation, and differentiation on were assayed SEM, MTT, real time-PCR, ALP assay, respectively. results shown good integration scaffold. Also, qRT-PCR differentiated shows that osteoblast cell markers are expressed after 21d 2D groups while group expression these higher than group. Based our findings, PMA has...
Summary Objective Bilingual healthy adults have been shown to exhibit an advantage in executive functioning ( EF ) that is associated with microstructural changes white matter WM networks. Patients temporal lobe epilepsy TLE often show deficits are compromise. In this study, we investigate whether bilingualism can increase cognitive reserve and/or brain bilingual patients , mitigating impairment and Methods Diffusion tensor imaging was obtained 19 26 monolingual 12 controls HC ), 21 ....
<h3>Objective</h3> To determine the predictive power of white matter neuronal networks (i.e., structural connectomes [SCs]) in discriminating memory-impaired patients with temporal lobe epilepsy (TLE) from those normal memory. <h3>Methods</h3> T1- and diffusion MRI (dMRI), clinical variables, neuropsychological measures verbal memory were available for 81 TLE. Prediction impairment was performed a tree-based classifier (XGBoost) 4 models: (1) model including demographic features, (2)...
Immunotherapy is increasingly used in the treatment of glioblastoma (GBM), with immune checkpoint therapy gaining popularity given favorable outcomes achieved for other tumors. However, immune-mediated (IM)-pseudoprogression common, remains poorly characterized, and renders conventional imaging little utility when evaluating response. We present case a 64-year-old man GBM who developed pathologically proven IM-pseudoprogression after initiation inhibitor, subsequently true tumor progression...
Bevacizumab-related imaging abnormality (BRIA), appearing as areas of restricted diffusion on magnetic resonance (MRI) and representing atypical coagulative necrosis pathologically, has been observed in patients with brain tumors receiving radiotherapy bevacizumab. We investigated the role cumulative radiation dose BRIA development a voxel-wise analysis.Patients (n = 18) were identified. All had high-grade gliomas or metastases treated Areas segmented semi-automatically diffusion-weighted...