RAPID: Deep Learning Models for Early Screening of COVID-19 using CT Images
- Funded by National Science Foundation (NSF)
- Total publications:0 publications
Grant number: unknown
Grant search
Key facts
Disease
COVID-19Start & end year
20202021Known Financial Commitments (USD)
$149,995Funder
National Science Foundation (NSF)Principal Investigator
Aryya GangopadhyayResearch Location
United States of AmericaLead Research Institution
University of Maryland Baltimore CountyResearch Priority Alignment
N/A
Research Category
Pathogen: natural history, transmission and diagnostics
Research Subcategory
Diagnostics
Special Interest Tags
N/A
Study Type
Non-Clinical
Clinical Trial Details
N/A
Broad Policy Alignment
Pending
Age Group
Not Applicable
Vulnerable Population
Not applicable
Occupations of Interest
Not applicable
Abstract
The rapid spread of COVID-19 has severely impacted the lives of billions of people across the world. Healthcare systems are strained both in terms of dealing with the large number of cases but also the risk of infection imposed on healthcare workers. This project develops low-cost, effective, and minimal contact early screening tools for detection, treatment, and prevention of the spread of the disease. In order to respond to infectious diseases such as COVID-19 and prevent future, this project proactively builds resources to help the medical community be better prepared in early stages of diseases with pandemic potential.
This project develops an understanding of SARS-CoV-2 through an early screening tool to distinguish the recent coronavirus (COVID-19) infections from other respiratory illnesses such as Influenza-A and viral or bacterial pneumonia as well as from patients who have no pulmonary disease. There are two major contributions of the project: (1) generate high quality Convolutional Neural Networks (CNNs) with 2D and 3D kernels for early detection of COVID-19 infection, and (2) synthesize realistic Computed Tomography (CT) images using Generative Adversarial Networks (GANs) that will be publicly available for research and practice.
The project has significant broader impacts in the United States and across the globe. The pre-trained models are useful as early screening tools by medical practitioners. The pre-trained models can also be useful in studying other widespread diseases and pandemics in the future. The synthetic data generated in this project allows researchers to develop newer models for early screening of COVID-19. This project will be part of the necessary preparation that the United States and other nations across the world could put in place to minimize the impact of future disasters caused by pandemic diseases such as COVID-19. This project is being performed within the auspices of the Center for Accelerated Real Time Analytics (CARTA), an Industry University Cooperative Research Center at UMBC funded by NSF. The project repository will be maintained at https://carta.umbc.edu/ for 5 years. The repository consists of the following resources: (1) High-quality pre-trained models for early detection of COVID-19 detection and (2) realistic CT images with both 2D axial slices and 3D volumes that can be used to train other models. The codes, models, synthetic data, and results generated in this project are being widely disseminated through the project website and Github repository.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
This project develops an understanding of SARS-CoV-2 through an early screening tool to distinguish the recent coronavirus (COVID-19) infections from other respiratory illnesses such as Influenza-A and viral or bacterial pneumonia as well as from patients who have no pulmonary disease. There are two major contributions of the project: (1) generate high quality Convolutional Neural Networks (CNNs) with 2D and 3D kernels for early detection of COVID-19 infection, and (2) synthesize realistic Computed Tomography (CT) images using Generative Adversarial Networks (GANs) that will be publicly available for research and practice.
The project has significant broader impacts in the United States and across the globe. The pre-trained models are useful as early screening tools by medical practitioners. The pre-trained models can also be useful in studying other widespread diseases and pandemics in the future. The synthetic data generated in this project allows researchers to develop newer models for early screening of COVID-19. This project will be part of the necessary preparation that the United States and other nations across the world could put in place to minimize the impact of future disasters caused by pandemic diseases such as COVID-19. This project is being performed within the auspices of the Center for Accelerated Real Time Analytics (CARTA), an Industry University Cooperative Research Center at UMBC funded by NSF. The project repository will be maintained at https://carta.umbc.edu/ for 5 years. The repository consists of the following resources: (1) High-quality pre-trained models for early detection of COVID-19 detection and (2) realistic CT images with both 2D axial slices and 3D volumes that can be used to train other models. The codes, models, synthetic data, and results generated in this project are being widely disseminated through the project website and Github repository.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.