A5049874968- Congenital Heart Disease Studies
- Lung Cancer Diagnosis and Treatment
- Congenital Diaphragmatic Hernia Studies
- COVID-19 diagnosis using AI
- Ultrasound in Clinical Applications
- Neonatal Respiratory Health Research
- Pulmonary Hypertension Research and Treatments
- Machine Learning in Healthcare
- Bone fractures and treatments
- Coronary Artery Anomalies
- Vascular anomalies and interventions
- Cardiac Imaging and Diagnostics
- Hip disorders and treatments
- Restraint-Related Deaths
- Neuroblastoma Research and Treatments
- Appendicitis Diagnosis and Management
- IL-33, ST2, and ILC Pathways
- Eosinophilic Disorders and Syndromes
- Pleural and Pulmonary Diseases
- Mitochondrial Function and Pathology
- Pediatric Urology and Nephrology Studies
- Bone health and osteoporosis research
- Infective Endocarditis Diagnosis and Management
- Airway Management and Intubation Techniques
- Myasthenia Gravis and Thymoma
University of Colorado Anschutz Medical Campus
2021-2025
University of Colorado Denver
2018-2023
Children's Hospital Colorado
2018-2023
University of Colorado System
2019
Children's Hospital of Philadelphia
2014-2016
Large, labeled datasets have driven deep learning methods to achieve expert-level performance on a variety of medical imaging tasks. We present CheXpert, large dataset that contains 224,316 chest radiographs 65,240 patients. design labeler automatically detect the presence 14 observations in radiology reports, capturing uncertainties inherent radiograph interpretation. investigate different approaches using uncertainty labels for training convolutional neural networks output probability...
Background Chest radiograph interpretation is critical for the detection of thoracic diseases, including tuberculosis and lung cancer, which affect millions people worldwide each year. This time-consuming task typically requires expert radiologists to read images, leading fatigue-based diagnostic error lack expertise in areas world where are not available. Recently, deep learning approaches have been able achieve expert-level performance medical image tasks, powered by large network...
Large, labeled datasets have driven deep learning methods to achieve expert-level performance on a variety of medical imaging tasks. We present CheXpert, large dataset that contains 224,316 chest radiographs 65,240 patients. design labeler automatically detect the presence 14 observations in radiology reports, capturing uncertainties inherent radiograph interpretation. investigate different approaches using uncertainty labels for training convolutional neural networks output probability...
Abstract Background Mediastinal masses in children may present with compression of the great vessels and airway. An interdisciplinary plan for rapid diagnosis, acute management, treatment prevents devastating outcomes optimizes care. Emergency pretreatment steroids or radiation is more likely to be administered when care variable, which delay complicate diagnosis treatment. Strategies standardize expedite improve patient safety long‐term outcomes. Aims The aim this quality improvement...
Background: Positron emission tomography (PET) scans are used in disease diagnosis and evaluation for pediatric oncology patients. Brown adipose tissue (BAT) 18 F-fluorodeoxyglucose-PET uptake is reported 35% to 47% of Several risk factors may be associated with BAT uptake. Objective: The aim was determine the incidence patients using a consensus-based system novel grading scale. Methods: A total 285 PET 154 were retrospectively reviewed presence from September 2015 through December 2016....