A5007055141- Radiomics and Machine Learning in Medical Imaging
- Advanced X-ray and CT Imaging
- COVID-19 diagnosis using AI
- Venous Thromboembolism Diagnosis and Management
- Cardiac tumors and thrombi
- Congenital Heart Disease Studies
- Cardiac Imaging and Diagnostics
- Pulmonary Hypertension Research and Treatments
- Cardiac Structural Anomalies and Repair
- AI in cancer detection
- Atrial Fibrillation Management and Outcomes
- Vascular anomalies and interventions
- Pericarditis and Cardiac Tamponade
- Acute Ischemic Stroke Management
- Coronary Artery Anomalies
- Medical Imaging Techniques and Applications
- Radiation Dose and Imaging
- Breast Lesions and Carcinomas
- Lung Cancer Diagnosis and Treatment
- Central Venous Catheters and Hemodialysis
- Diagnosis and Treatment of Venous Diseases
- Ultrasound in Clinical Applications
- Breast Cancer Treatment Studies
- Eosinophilic Disorders and Syndromes
- Cardiovascular Effects of Exercise
Shaheed Rajaei Cardiovascular Medical and Research Center
2017-2025
Iran University of Medical Sciences
2017-2024
Motamed Cancer Institute
2024
Academic Center for Education, Culture and Research
2024
Tehran University of Medical Sciences
2007-2012
Rasool Akram Hospital
2012
Firoozgar General Hospital
2011
Children's Medical Center
2007
Abstract Objectives The current study aimed to design an ultra-low-dose CT examination protocol using a deep learning approach suitable for clinical diagnosis of COVID-19 patients. Methods In this study, 800, 170, and 171 pairs full-dose images were used as input/output training, test, external validation set, respectively, implement the prediction technique. A residual convolutional neural network was applied generate from images. quality predicted assessed root mean square error (RMSE),...
Robust differentiation between infarcted and normal tissue is important for clinical diagnosis precision medicine. The aim of this work to investigate the radiomic features develop a machine learning algorithm myocardial infarction (MI) viable tissues/normal cases in left ventricular myocardium on non-contrast Cine Cardiac Magnetic Resonance (Cine-CMR) images.Seventy-two patients (52 with MI 20 healthy control patients) were enrolled study. MR imaging was performed 1.5 T MRI using following...
We aimed to analyze the prognostic power of CT-based radiomics models using data 14,339 COVID-19 patients.
We present a deep learning (DL)-based automated whole lung and COVID-19 pneumonia infectious lesions (COLI-Net) detection segmentation from chest computed tomography (CT) images. This multicenter/multiscanner study involved 2368 (347'259 2D slices) 190 (17 341 volumetric CT exams along with their corresponding manual of lungs lesions, respectively. All images were cropped, resized, the intensity values clipped normalized. A residual network non-square Dice loss function built upon TensorFlow...
The main aim of the present study was to predict myocardial function improvement in cardiac MR (LGE-CMR) images patients after coronary artery bypass grafting (CABG) using radiomics and machine learning algorithms. Altogether, 43 who had visible scars on short-axis LGE-CMR were candidates for CABG surgery selected enrolled this study. imaging performed preoperatively a 1.5-T MRI scanner. All segmented by two expert radiologists (in consensus). Prior extraction features, all resampled an...
Mohsen Maadani, Soudabeh Shafiee Ardestani, Farnaz Rafiee, Kiara Rezaei-Kalantari, Parham Rabiee, Yasmin Mohtasham Kia, Ali Zahedmehr, Bahram Mohebbi, Armin Elahifar, Ehsan Khalilipur, Ata Firouzi, and Sadeghipour. Vasc Specialist Int 2025;41:. https://doi.org/10.5758/vsi.240103
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 Background We present a deep learning (DL)-based automated whole lung and COVID-19 pneumonia infectious lesions (COLI-Net) detection segmentation from chest CT images. Methods prepared 2358 (347’259, 2D slices) 180 (17341, volumetric images along with their corresponding manual of lungs lesions, respectively, in the framework multi-center/multi-scanner study. All were cropped, resized intensity values clipped normalized. A residual network (ResNet) non-square Dice loss function...
The percentage of shunt fraction significantly impacts the management patients with congenital shunts, influencing strategic choices such as surgical or interventional procedures. This study compared estimated (the ratio pulmonary-to-systemic flow, Qp/Qs) for quantifying left-to-right in children ventricular septal defect (VSD) using heart catheterization, four-dimensional (4D) and two-dimensional (2D) flow magnetic resonance imaging (MRI). goal was to establish a non-invasive reliable...
Common variable immunodeficiency (CVID) is a heterogeneous group of disorders, characterized by decreased serum immunoglobulin levels, and increased susceptibility to recurrent bacterial infections, malignancies, autoimmune disorders. In this report, 2 siblings with CVID who developed Hodgkin lymphoma are presented: 16-year-old girl at stage IIB her 12-year-old brother IIIB lymphoma. Their father 1 uncle were also affected the same cancer no state. The presence should be considered in...
Primary non-Hodgkin's lymphoma of the cranial vault is extremely rare. This case report presents a 42-year-old man with painless subcutaneous scalp mass which extended intracranially associated recent mild headache. Initial computed tomography and magnetic resonance imaging revealed two lesions emanating from skull. Biopsy diagnosis diffuse large B cell (DLBCL). A thorough work-up no other point involvement. concerned about considering in differential calvarial both intra- extra extensions...
Background Little evidence is available on post-pulmonary embolism impairment (PPEI), a recently defined complication of pulmonary (PE) encompassing dysfunctional clinical and imaging parameters. In the present study, we sought to evaluate its frequency with focus main components. Methods this prospective registry, included patients confirmed diagnosis acute PE focused those initial right ventricular (RV) dysfunction. Their baseline, pre-discharge, 6 month follow-up characteristics were...
Several complications have been reported with inguinal hernias. Although hematuria and flank pain, either as the presentation or a complication of hernia, are infrequent, this condition may lead to development obstructive uropathy, which can diverse manifestations.A 71-year-old Iranian man Persian ethnicity presented new onset episodes gross left-sided pain. A physical examination revealed large non-tender hernia on his left side. An initial workup included an abdominal ultrasound,...
Abstract To reduce inferior vena cava filter (IVCF) related complications, retrieval is recommended whenever possible. Nevertheless, IVCF rates remain lower than expected, likely due to insufficient follow-up after placement. We evaluated the value of a structured program designed follow patients by interventional radiology team up 5 months prospectively enrolled 366 consecutive (mean age 64 ± 17 years; 201 men and 165 women) who benefited from between March 2015 February 2020. The consisted...
Abstract Left ventricular (LV) intra‐myocardial dissection or dissecting hematoma is a rare complication of myocardial infarction that could occur in the acute phase, during remodeling process and even after coronary revascularization. LV has high mortality, best management strategy remains controversial. Here, we present case left ventricle late anterior diagnosed by multimodality imaging.
Abstract Background May–Thurner anomaly is characterized as external venous compression by the arterial framework against hard bony structures. This chronic anatomical lesion infrequently leads to deep vein thrombosis in lower extremity, and it may lead leg swelling a long-term post-thrombotic complication. Left iliac not be uncommon was previously thought, typically occurs women more than men. Congenital anomalies of tree are rare; they exist 8.7% general population. Case-presentation We...
Although one of the most important differential diagnoses cardiac masses in cancer patients is metastasis from underlying tumor, it may also be caused by benign etiologies. In this article, we describe calcified amorphous which causes masses, a patient with colon cancer.
Hemangioma is the most common benign lesion of liver. It mostly asymptomatic and may be found incidentally during cross-sectional liver or abdominal imaging. This study aimed to investigate prevalence clinical characteristics hepatic hemangioma in an Iranian population.This retrospective was conducted between July November 2017 Firoozgar Hospital affiliated Iran University Medical Sciences, Tehran, Iran. The population consisted adult patients (>18 years) referred for transabdominal...
Background: To evaluate ultrasound (US) characteristics and BI-RADS (Breast imaging-reporting data system) of malignant breast masses in women <40 years to compare with older patients. Methods: In a retrospective, descriptive-analytical study, we assessed the US images category 78 final pathology invasive ductal carcinoma (IDC, NOS type). Results: Overall, most frequent descriptors IDC were indistinct margin (45%), irregular shaped (63.5%), posterior shadowing (38.8%), heterogeneous internal...