- Radiomics and Machine Learning in Medical Imaging
- Advanced MRI Techniques and Applications
- AI in cancer detection
- MRI in cancer diagnosis
- Medical Imaging Techniques and Applications
- Advanced Neuroimaging Techniques and Applications
- Radiation Dose and Imaging
- COVID-19 diagnosis using AI
- Lung Cancer Diagnosis and Treatment
- Cardiac Imaging and Diagnostics
- Advanced X-ray and CT Imaging
- Breast Cancer Treatment Studies
- Hip disorders and treatments
- Ultrasound and Hyperthermia Applications
- Advanced Neural Network Applications
- COVID-19 Clinical Research Studies
- Advanced Radiotherapy Techniques
- Osteoarthritis Treatment and Mechanisms
- Digital Radiography and Breast Imaging
- Cardiovascular Disease and Adiposity
- Chronic Obstructive Pulmonary Disease (COPD) Research
- Interstitial Lung Diseases and Idiopathic Pulmonary Fibrosis
- Lanthanide and Transition Metal Complexes
- Traumatic Brain Injury and Neurovascular Disturbances
- Long-Term Effects of COVID-19
Columbia University
2012-2025
Johns Hopkins University
2025
University of California, Los Angeles
2025
Resonance Research (United States)
2025
Wake Forest University
2025
University of Illinois Chicago
2025
Cornell University
2025
Columbia University Irving Medical Center
2015-2024
Texas Health Dallas
2018-2024
NewYork–Presbyterian Hospital
2017-2023
Many patients with SARS-CoV-2 infection develop neurological signs and symptoms; although, to date, little evidence exists that primary of the brain is a significant contributing factor. We present clinical, neuropathological molecular findings 41 consecutive infections who died underwent autopsy in our medical centre. The mean age was 74 years (38-97 years), 27 (66%) were male 34 (83%) Hispanic/Latinx ethnicity. Twenty-four (59%) admitted intensive care unit. Hospital-associated...
This study sought to determine updated conversion factors (k-factors) that would enable accurate estimation of radiation effective dose (ED) for coronary computed tomography angiography (CTA) and calcium scoring performed on 12 contemporary scanner models current clinical cardiac protocols compare these methods the standard chest k-factor 0.014 mSv·mGy−1cm−1. Accurate ED from CT scans is essential meaningfully benefits risks different imaging strategies optimize test protocol selection....
Purpose To organize a multi-institute knee MRI segmentation challenge for characterizing the semantic and clinical efficacy of automatic methods relevant monitoring osteoarthritis progression. Materials Methods A dataset partition consisting three-dimensional from 88 retrospective patients at two time points (baseline 1-year follow-up) with ground truth articular (femoral, tibial, patellar) cartilage meniscus segmentations was standardized. Challenge submissions majority-vote ensemble were...
Abstract Background Chest Computed tomography (CT) scans detect lung nodules and assess pulmonary fibrosis. While fibrosis indicates increased cancer risk, current clinical practice characterizes nodule risk of malignancy based on size smoking history; little consideration is given to the fibrotic microenvironment. Purpose To evaluate effect incorporating microenvironment into classifying in chest CT images using deep learning techniques. Materials methods We developed a visualizable 3D...
Preterm birth is a strong contributor to perinatal mortality, and preterm infants that survive are at risk for long-term morbidities. During most of pregnancy, appropriate mechanical function the cervix required maintain developing fetus in utero. Premature cervical softening subsequent shortening hypothesized cause birth. Presently, there lack understanding structural material factors influence during pregnancy. In this study we build finite element models pregnant uterus, cervix, fetal...
The purpose of our research is to evaluate the usefulness chest X-ray for triaging patients with suspected COVID-19 infection. IRB approval was obtained allow a retrospective review adult who presented Emergency Department complaint fever, cough, dyspnea or hypoxia and had between 12 March 2020 26 2020. initial graded on scale 0–3 grade 0 representing no alveolar opacities, 1: < 1/3 opacities lung, Grade 2: 2/3 lung 3: > lung. Past medical history diabetes hypertension, oxygen saturation,...
Background Oncotype Dx is a validated genetic analysis that provides recurrence score (RS) to quantitatively predict outcomes in patients who meet the criteria of estrogen receptor positive / human epidermal growth factor receptor‐2 negative (ER+/HER2–)/node invasive breast carcinoma. Although effective, test and expensive, which has motivated this investigation determine potential role radiomics. Hypothesis We hypothesized convolutional neural network (CNN) can be used RS using an MRI...
Deep learning with convolutional neural networks (CNNs) has experienced tremendous growth in multiple healthcare applications and been shown to have high accuracy semantic segmentation of medical (e.g., radiology pathology) images. However, a key barrier the required training CNNs is obtaining large-scale precisely annotated imaging data. We sought address lack data eye tracking technology. As proof principle, our hypothesis was that masks generated help (ET) would be very similar those...
Recent innovations in quantitative magnetic resonance imaging (MRI) measurement methods have led to improvements accuracy, repeatability, and acquisition speed, prompted renewed interest reevaluate the medical value of T 1 . The purpose this study was determine bias reproducibility measurements a variety MRI systems with an eye toward assessing feasibility applying diagnostic threshold across multiple clinical sites. We used International Society Magnetic Resonance Medicine/National...
Abstract Purpose Evaluate the behavior of lung nodules occurring in areas pulmonary fibrosis and compare them to non-fibrotic parenchyma. Methods This retrospective review chest CT scans electronic medical records received expedited IRB approval a waiver informed consent. 4500 consecutive patients with scan report containing word or specific type were identified using system M*Model Catalyst (Maplewood, Minnesota, U.S.). The largest nodule was measured longest dimension re-evaluated, same...
Metronome-paced tachypnea during real-time cine pulmonary MRI is a newly proposed technique to measure dynamic hyperinflation in chronic obstructive disease, which yielded reproducible results.
Functional scans in cardiovascular magnetic resonance (CMR) adopting bSSFP sequences suffer from dark band artifacts due to B0 inhomogeneity. The best remedy mitigate this issue is through cardiac shimming. development of an optimal shim strategy for the human heart hindered by a limited understanding conditions clinical diagnostic orientations CMR. Here, we present high-resolution distributions imaging planes, derived simulations utilizing computed tomography (CT) images 1008 subjects, and...