Case studies
SIFT Dataset from Stanford University Hospital
BIDMC/Harvard University (MIMIC-CXR dataset)
MIMIC-CXR, a large dataset of 227,835 & imaging studies for 65,379 patients
MIDRC Annotated COVID-19 Radiographs
Medical Imaging and Data Resource Center (MIDRC), funded by the National Institute of Biomedical Imaging and Bioengineering (NIBIB) of NIH and hosted at the University of Chicago, is co-led by the American College of Radiology® (ACR®), the Radiological Society of North America (RSNA), and the American Association of Physicists in Medicine (AAPM). For the past several years, Caddie has collaborated with MIDRC to develop, evaluate, and annotate 175,481 COVID-19 DR images, including the identification of COVID lesions, comorbidities, and detailed boundaries available in MIDRC to foster machine learning innovation through data sharing for rapid and flexible collection, analysis, and dissemination of imaging and associated clinical data by providing researchers with unparalleled resources. Caddie will continue to collaborate with MIDRC to offer annotation services, tools, and data.
TB Portals Annotated TB CXR Images
For the past several years, Caddie has collaborated with the TB Portals Program of the National Institute of Allergy and Infectious Diseases (NIAID) to develop, evaluate, and apply SIFT (Smart Imagery Framing and Truthing) to annotate over 10,000 TB radiographs successfully. The goal of this initiative is to generate a large amount of high-quality data, which is now available in the TB Portals for researchers worldwide. This data is important to the training of AI models aimed at improving TB screening and other clinical practices, aligning with the National Institutes of Health’s (NIH) mission to “enhance health, lengthen life, and reduce illness and disability.” As detailed in a forthcoming paper to be published in the 2025 SPIE Medical Imaging Proceeding, “High efficiency of SIFT predictions makes it attractive for tuberculosis diagnostics and monitoring. Multi-domain, patient-centric databases from NIAID TB Portals could be used to align SIFT predictions with retrospective data on treatment history, drug sensitivity, history of relapses, influence of comorbidities and treatment outcomes.” Caddie will continue to collaborate with MIDRC to offer annotation services, tools, and data.
Get in touch
Accelerate your research and enhance diagnostic accuracy with Caddie's solutions.
Connect with us
ADDRESS:
Ste 300 #1238
Gaithersburg, MD 20879