A5014601549- Radiology practices and education
- Radiomics and Machine Learning in Medical Imaging
- Artificial Intelligence in Healthcare and Education
- Biomedical Text Mining and Ontologies
- Topic Modeling
- Radiation Dose and Imaging
- AI in cancer detection
- Natural Language Processing Techniques
- Advanced X-ray and CT Imaging
- Medical Imaging Techniques and Applications
- Digital Radiography and Breast Imaging
- Pharmaceutical Quality and Counterfeiting
- Medical Imaging and Analysis
- Biomedical and Engineering Education
- Cardiac Imaging and Diagnostics
- Semantic Web and Ontologies
- Electronic Health Records Systems
- Lung Cancer Treatments and Mutations
- Lung Cancer Diagnosis and Treatment
- Social Media in Health Education
- Advances in Oncology and Radiotherapy
- Ultrasound in Clinical Applications
- Dental Radiography and Imaging
- COVID-19 diagnosis using AI
- Lymphoma Diagnosis and Treatment
MedStar Health
2018-2024
MedStar Georgetown University Hospital
2015-2023
Georgetown University
2014-2023
Shariati Hospital
2022
Emory University Hospital
2022
Tehran University of Medical Sciences
2022
The Research Council
2015
Georgetown University Medical Center
2014
United States Food and Drug Administration
2011-2014
Johns Hopkins Hospital
2007-2009
Traditional adverse event (AE) reporting systems have been slow in adapting to online AE from patients, relying instead on gatekeepers, such as clinicians and drug safety groups, verify each potential event. In the meantime, increasing numbers of patients turned social media share their experiences with drugs, medical devices, vaccines.The aim study was evaluate level concordance between Twitter posts mentioning AE-like reactions spontaneous reports received by a regulatory agency.We...
The development and implementation of quantitative imaging biomarkers has been hampered by the inconsistent often incorrect use terminology related to these markers. Sponsored Radiological Society North America, an interdisciplinary group radiologists, statisticians, physicists, other researchers worked develop a comprehensive serve as foundation for biomarker claims. Where possible, this working adapted existing definitions derived from national or international standards bodies rather than...
Coronary artery disease (CAD), the most common manifestation of cardiovascular disease, remains cause mortality in United States. Risk assessment is key for primary prevention coronary events and calcium (CAC) scoring using computed tomography (CT) one such non-invasive tool. Despite proven clinical value CAC, current practice implementation CAC has limitations as lack insurance coverage test, need capital-intensive CT machines, specialized imaging protocols, accredited 3D labs analysis...
Background Previous studies suggest that use of artificial intelligence (AI) algorithms as diagnostic aids may improve the quality skeletal age assessment, though these lack evidence from clinical practice. Purpose To compare accuracy and interpretation time assessment on hand radiograph examinations with without an AI algorithm a aid. Materials Methods In this prospective randomized controlled trial, was performed (n = 792) 739) For algorithm, radiologist shown part their routine work...
We retrospectively evaluated our single-center clinical experience with <sup>90</sup>Y-ibritumomab tiuxetan and <sup>131</sup>I-tositumomab for therapy of refractory non-Hodgkin9s lymphoma (NHL). the hypothesis that patient-specific dosing regimen used results in less bone marrow toxicity than does weight-based tiuxetan. <b>Methods:</b> Thirty-eight patients (25 male 13 female; median age, 64 y) received radioimmunotherapy NHL (20 tiuxetan; 18 <sup>131</sup>I-tositumomab). Patient disease...
Automatically generating accurate summaries from clinical reports could save a clinician's time, improve summary coverage, and reduce errors. We propose sequence-to-sequence abstractive summarization model augmented with domain-specific ontological information to enhance content selection generation. apply our method dataset of radiology show that it significantly outperforms the current state-of-the-art on this task in terms rouge scores. Extensive human evaluation conducted by radiologist...
Sequence-to-sequence (seq2seq) network is a well-established model for text summarization task. It can learn to produce readable content; however, it falls short in effectively identifying key regions of the source. In this paper, we approach content selection problem clinical abstractive by augmenting salient ontological terms into summarizer. Our experiments on two publicly available data sets (107,372 reports MIMIC-CXR, and 3,366 OpenI) show that our statistically significantly boosts...
We retrospectively evaluated <sup>18</sup>F-FDG PET/CT for monitoring the response of non-Hodgkin9s lymphoma to radioimmunotherapy. <b>Methods:</b> A total 33 clinical patients received <sup>131</sup>I-tositumomab (<i>n</i> = 23) or <sup>90</sup>Y-ibritumomab tiuxetan 10) and underwent scans before radioimmunotherapy at 12 wk after third scan was performed on 13 24 radioimmunotherapy, whom did not receive interval therapy. Tumor metabolic activity assessed visually quantitatively by lean...
Functional Joint Imaging Using 256-MDCT: Technical FeasibilityVivek Kalia1, Rick W. Obray1, Ross Filice1, Laura M. Fayad1, Kieran Murphy2 and John A. Carrino3Audio Available | Share
Objectives Response to the oncology drug gemcitabine may be variable in part due genetic differences enzymes and transporters responsible for its metabolism disposition. The aim of our in-silico study was identify gene variants significantly associated with response that help personalize treatment clinic. Methods We analyzed two independent data sets: (a) genotype from NCI-60 cell lines using Affymetrix DMET 1.0 platform combined cytotoxicity those lines, (b) genome-wide association studies...