Could a repository of anonymized CT scans and clinical information provide critical clues about rare, unclassified lung diseases? Elizabeth Estes, executive director of Open Source Imaging Consortium, and Dr. Simon Walsh, consultant radiologist and NIHR clinician scientist, sure think so.

In this episode, Elizabeth and Dr. Walsh discuss the exciting role machine learning and algorithms may play on enhancing our disease knowledge—from diagnosis and prognosis to biomarker discovery and therapy response.

Companies across a range of industries are deploying image- and video-based artificial intelligence to improve and optimize key business processes and products. The OSIC Data Repository, supported by PwC and Microsoft, is building a platform to share anonymized imaging data to help with diagnosing the disease.

The Open Source Image Consortium (OSIC) is working to democratize medicine by giving OSIC clinicians and members everywhere the ability to access and benefit from the same technology and information as those affiliated with major research centers. “If we can figure out how to drive collaboration in healthcare, we will change the paradigm,” says Executive Director Elizabeth Estes. 

For decades, the healthcare industry has lacked a long list of elements necessary to understand the nature of hundreds of rare diseases — industry cohesiveness and data transparency chief amongst them. With the help of PwC and Microsoft, one pioneering group of minds may have finally found a key part of the solution: an open-source approach to medical research.

“We have a lot of smart, motivated, dedicated people together who want to see these patients have a different path. The technology is there for personalized medicine. The technology is there to make advances in rare disease,” says Elizabeth Estes, OSIC executive director.

A discussion with the Open Source Imaging Consortium, Microsoft and PwC: See how data and analytics, AI and cloud will reshape the future of healthcare.

A first-of-its-kind open source medical imaging and data repository platform is highlighting new possibilities to help improve the speed and accuracy of diagnosis and help patients, providers and researchers better manage the disease.

HOLLAND, Mich., Tuesday, September 7, 2021 – The Open Source Imaging Consortium (OSIC) today announced the launch of its global, data-rich repository of anonymized HRCT scans and clinical information regarding interstitial lung diseases (ILDs). This first-of-its-kind database is the world’s largest and most diverse, with a plethora of real world clinical and imaging data that is both multi-ethnic and multi-center. The OSIC Data Repository currently houses close to 1,500 anonymized and quality-controlled scans with accompanying data, and has an additional 5,000 in the quality control queue. It is on track to reach its goal of 15,000 anonymized scans, available to OSIC members, by first quarter 2022.​

HOLLAND, Mich., Tuesday, July 7, 2020 -- The Open Source Imaging Consortium (OSIC) announced today the launch of the $55,000 OSIC Pulmonary Fibrosis Progression, an AI-focused challenge to predict lung function decline in people living with pulmonary fibrosis. The competition is administered by Kaggle, the world’s largest data science community platform, and runs through October 6, 2020.

Global, Not-for-Profit, Collaborative Effort Focuses on Digital Imaging and Machine Learning to Enable Rapid Advances in the Fight against Idiopathic Pulmonary Fibrosis (IPF), Fibrosing ILDs, and Other Respiratory Diseases including Emphysematous Conditions ​

HOLLAND, Mich., Wednesday, May 22, 2019 — An international group of leading experts and advocates in the fight against idiopathic pulmonary fibrosis (IPF), fibrosing interstitial lung diseases (ILDs), and other respiratory diseases including emphysematous conditions announced today the formation of the Open Source Imaging Consortium (OSIC). This global, not-for-profit organization is a cooperative and open source effort between academia, industry and philanthropy to enable rapid advances in the detection and diagnosis of these conditions through digital imaging and machine learning.