A5058945277- Acute Ischemic Stroke Management
- Cerebrovascular and Carotid Artery Diseases
- Biomedical Text Mining and Ontologies
- Radiomics and Machine Learning in Medical Imaging
- Radiology practices and education
- Brain Tumor Detection and Classification
- AI in cancer detection
- Advanced X-ray and CT Imaging
- Medical Image Segmentation Techniques
- Medical Imaging Techniques and Applications
- MRI in cancer diagnosis
- Radiation Dose and Imaging
- Advanced MRI Techniques and Applications
- Stroke Rehabilitation and Recovery
- Image Retrieval and Classification Techniques
- Electronic Health Records Systems
- Traumatic Brain Injury and Neurovascular Disturbances
- Topic Modeling
- Machine Learning in Healthcare
- Cardiovascular Health and Disease Prevention
- Semantic Web and Ontologies
- Advanced Neuroimaging Techniques and Applications
- Intracranial Aneurysms: Treatment and Complications
- Medical Imaging and Analysis
- Artificial Intelligence in Healthcare
Phoenix VA Health Care System
2021-2022
University of California, Los Angeles
2008-2019
Computational Diagnostics (United States)
2019
UCLA Health
2017
Photon Imaging (United States)
2016
VA Greater Los Angeles Healthcare System
2011-2015
Los Angeles Medical Center
1995-2014
Ronald Reagan UCLA Medical Center
2014
UCLA Medical Center
2001-2008
University at Buffalo, State University of New York
2007
We present a new method for automatic segmentation of heterogeneous image data that takes step toward bridging the gap between bottom-up affinity-based methods and top-down generative model based approaches. The main contribution paper is Bayesian formulation incorporating soft assignments into calculation affinities, which are conventionally free. integrate resulting model-aware affinities multilevel by weighted aggregation algorithm, apply technique to task detecting segmenting brain tumor...
Current clinical practice relies on history to determine the time since stroke (TSS) onset. Imaging-based determination of acute onset could provide critical information clinicians in deciding treatment options, such as thrombolysis. The patients with unknown or unwitnessed TSS are usually excluded from thrombolysis, even if their symptoms began within therapeutic window. In this paper, we demonstrate a machine learning approach for classification using routinely acquired imaging sequences....
ABSTRACT Background and Purpose . Elevation in pulsatility indices (PIs) as measured by transcranial Doppler (TCD) have been postulated to reflect downstream increased vascular resistance caused small‐vessel ischemic disease. Methods The authors retrospectively compared TCD PIs magnetic resonance imaging (MRI) manifestations of disease 55 consecutive patients who underwent studies brain MRI within 6 months each other during a 2‐year period. Results Correlations between middle cerebral artery...
Due to the increasingly data-intensive clinical environment, physicians now have unprecedented access detailed information from a multitude of sources. However, applying this guide medical decisions for specific patient case remains challenging. One issue is related presenting practitioner: displaying large (irrelevant) amount often leads overload. Next-generation interfaces electronic health record (EHR) should not only make data easily searchable and accessible, but also synthesize...
PURPOSE: To evaluate ultrasonography (US) and magnetic resonance (MR) angiography in the differentiation between occlusion near of internal carotid artery (ICA). MATERIALS AND METHODS: Consecutive patients with or ICA at catheter who underwent MR US were included. compared angiography, standard, for ability to help distinguish from occlusion. Noninvasive examinations evaluated classify occlusions as having severe focal stenosis distal luminal collapse versus diffuse nonfocal disease. The 95%...
With the increased routine use of advanced imaging in clinical diagnosis and treatment, it has become imperative to provide patients with a means view understand their studies. We illustrate feasibility patient portal that automatically structures integrates radiology reports corresponding studies according several information orientations tailored for layperson.The is composed an image processing module creation timeline illustrates progression disease, natural language extract salient...
Abstract Background and Purpose Treatment of acute ischemic stroke is heavily contingent upon time, as there a strong relationship between time clock tissue progression. Work has established imaging biomarker assessments surrogates for since (TSS), namely, by comparing signal mismatch diffusion‐weighted (DWI) fluid‐attenuated inversion recovery (FLAIR) imaging. Our goal was to develop an automatic technique determining TSS from that does not require subspecialist radiology expertise. Methods...
Perfusion magnetic resonance (MR) images are often used in the assessment of acute ischemic stroke to distinguish between salvageable tissue and infarcted core. Deconvolution methods such as singular value decomposition have been approximate model-based perfusion parameters from these images. However, studies shown that existing deconvolution algorithms can introduce distortions may negatively influence utility parameter maps. There is limited previous work on utilizing machine learning...
The objective of this study was to report the sonographic abnormalities in a group patients with angiographically proven innominate artery stenosis and occlusion.A review all cerebrovascular sonograms at our institutions undertaken identify complete or partial flow reversal right vertebral midsystolic deceleration any one three major segments carotid system (common, internal, external artery). distribution appearance these evaluated, presence absence tardus-parvus waveforms noted segment...
The development of comprehensive picture archive and communication systems (PACS) has mainly been limited to proprietary developments by vendors, though a number freely available software projects have addressed specific image management tasks. openSourcePACS project aims provide an open source, common foundation upon which not only can basic PACS be readily implemented, but also support the evolution new functionality through novel imaging applications services. consists four main modules:...
Gadolinium diethylenetriamine pentaacetic acid (Gd-DTPA) is a contrast agent commonly used for enhancing MRI. In this paper, the authors report on 2 cases of postoperative inadvertent administration Gd-DTPA directly into ventriculostomy tubing side port that was mistaken intravenous tubing. Both demonstrated low signal MRI throughout ventricular system and dependent portions subarachnoid spaces, which originally believed to be CSF with areas T1 shortening in nondependent misinterpreted as...