Open database will assist with disease detection and differentiation.
In answer to a global call from the healthcare community and in an effort to expand the body of knowledge around the COVID-19 pandemic, the Radiological Society of North America (RSNA) is launching the COVID-19 Imaging Data Repository.
The open database will collect COVID-19 images and data from institutions, practices, and professional societies worldwide, building a comprehensive source for research and education efforts pertaining to the virus. All images and data will collected securely and in a way that maintains privacy and ethical principles.
“RSNA is committed to accelerating collaborative research and education on the uses of medical imaging to address diagnosis and imaging-based treatment of COVID-19,” said Curtis P. Langlotz, M.D., Ph.D., RSNA Board Liaison for Information Technology and Annual Meeting, in an announcement. “Because RSNA is a leader in connecting radiologists around the world, we have received a wave of requests from organizations interested in sharing imaging data, as well as from individuals and organizations seeking access to such data for research and education.”
Providers, practices, and organizations interested in submitting COVID-19 images and related information to the repository can respond to an RSNA survey. Expression of interest and responses are requested by April 15, 2020.
Similar to RSNA’s other data-sharing efforts with images, research, and technologic innovation, this repository will be grounded in collaboration with other imaging organizations, particularly the European Imaging COVID-19 AI Initiative that is supported by the European Society of Medical Imaging Informatics.
MRI-Based AI Radiomics Model Offers 'Robust' Prediction of Perineural Invasion in Prostate Cancer
July 26th 2024A model that combines MRI-based deep learning radiomics and clinical factors demonstrated an 84.8 percent ROC AUC and a 92.6 percent precision-recall AUC for predicting perineural invasion in prostate cancer cases.
Breast MRI Study Examines Common Factors with False Negatives and False Positives
July 24th 2024The absence of ipsilateral breast hypervascularity is three times more likely to be associated with false-negative findings on breast MRI and non-mass enhancement lesions have a 4.5-fold likelihood of being linked to false-positive results, according to new research.
Can Polyenergetic Reconstruction Help Resolve Streak Artifacts in Photon Counting CT?
July 22nd 2024New research looking at photon-counting computed tomography (PCCT) demonstrated significantly reduced variation and tracheal air density attenuation with polyenergetic reconstruction in contrast to monoenergetic reconstruction on chest CT.