Imaging consortium releases first-of-its-kind database to help fight lung disease
A new collaboration between academic, industry and patient groups has released a first-of-its-kind repository with high-resolution scans and clinical information for interstitial lung diseases.
The Open Source Imaging Consortium Data Repository currently houses nearly 1,500 anonymous CT scans with corresponding health data, the 501(c)(3) not-for-profit announced Tuesday. Lead by radiologists, pulmonologists and AI experts, the goal is to enable quick, open-source solutions to fight deadly respiratory diseases.
Advances in AI-driven medical image analysis have historically been held back by the need for large, diverse datasets. OSIC has some 5,000 additional scans in its quality control queue and plans to vet approximately 15,000 by the first quarter of 2022, the group noted.
“Being able to reliably predict how pulmonary fibrosis will progress in an individual patient would allow doctors to initiate appropriate treatment at the earliest opportunity and slow disease progression,” radiology project leader Simon Walsh, MD, of the Imperial College London’s National Heart and Lung Institute, said Sept. 7. “It remains one of the most urgent challenges for effective management for patients with fibrotic lung disease."
The new database is three years in the making and each scan has been vetted by two global GDPR/HIPPA privacy firms. OSIC is seeking additional scans from government agencies, advocacy groups and via direct patient outreach.
A long list of organizations and partners are supporting the endeavor, including Siemens Healthineers, the American Lung Association and the University of Vienna, among many others.
"The future of medical research depends heavily on our ability to collate significant amounts of data and make that data available for detailed and open scientific investigation,” computational science lead David Barber, PhD, with the University College London said. “It's a proud moment that OSIC is at the forefront of this movement.”
Matt joined Chicago’s TriMed team in 2018 covering all areas of health imaging after two years reporting on the hospital field. He holds a bachelor’s in English from UIC, and enjoys a good cup of coffee and an interesting documentary.