The repository will serve as an open-source, central location for worldwide imaging and clinical data. The goal is to advance digital imaging biomarkers for accurate imaging-based diagnosis, prognosis, and prediction of response to therapy in patients with ILDs according to the consortium.
The repository was built with images and clinical data from various sources; nearly 1,500 anonymized and quality-controlled studies with accompanying data have been stored so far in the repository, with an additional 5,000 exams in the quality-control queue, OSIC said. Every scan has been anonymized with a personal and automated quality control check, according to the nonprofit industry and academic collaborative.
The goal is to have 15,000 anonymized scans available to OSIC members by the first quarter of 2022. The consortium is also seeking additional scans for the repository from governmental agencies, patient advocacy groups, and through direct patient outreach.
Any artificial intelligence algorithms created using OSIC data will be made available as open-source.
Copyright © 2021 AuntMinnie.com