The Most Diverse Global Repository for ILA/ILD Research: AI-Ready, Curated, and Powered by OSIC
ATS Innovation Hub |
From Incidental ILAs to Early ILD Detection: Leveraging OSIC’s Global Database |
Date |
Monday, May 19, 2025 |
Time |
1:15 PM–1:35 PM (Pacific time, US) |
Location |
Moscone Center • 747 Howard Street, San Francisco, CA 94103 Innovation Hub 7 (Booth #1165) |
Explore how AI-driven tools and lung cancer screening scans are transforming early detection and risk prediction in ILD.
Speakers
ELIZABETH
ESTES OSIC Executive Director |
PROF. MARTINA
KOZIAR VAŠÁKOVÁ Thomayer Hospital Faculty |
SANDRA
STAPLETON Vida Chief Operating Officer |
ATS Innovation Hub |
From Incidental ILAs to Early ILD Detection: Finding Hidden Clues within OSIC’s Global Database |
Date |
Tuesday, May 20, 2025 |
Time |
1:15 PM–1:35 PM (Pacific time, US) |
Location |
Moscone Center • 747 Howard Street, San Francisco, CA 94103 Innovation Hub 7 (Booth #1165) |
Discover powerful imaging advancements like tMPR and sub-pleural views, and how lung cancer screening data is uncovering previously hidden lung changes.
Why This Matters
Lung cancer screening is becoming a global standard, but imagine harnessing these routine scans to detect fibrosing lung disease before symptoms arise and before clinical suspicion. At OSIC, we leverage the world’s largest curated ILD database alongside advanced and generative AI techniques to help uncover early signs of ILAs in lung cancer screenings.
What is OSIC?
The Open Source Imaging Consortium (OSIC) is a worldwide, non-profit 501(c)(3) organization that brings together data scientists, clinicians, and industry professionals to drive significant advancements in interstitial lung diseases (ILDs) using AI and real-world data. These contributors were instrumental in developing the OSIC Cloud Data Repository (OSIC Cloud), powered by Vida.
We maintain the world's largest curated, AI-ready dataset for interstitial lung diseases (ILDs), housed in the OSIC Cloud Data Repository (OSIC Cloud). This comprehensive resource combines high-resolution CT scans, clinical data, and longitudinal follow-ups, designed to foster collaborative innovation. Built with the expertise of radiologists, pulmonologists, machine learners, and imaging experts worldwide, The OSIC Cloud offers a rich collection of anonymized HRCT scans and clinical information. Its diverse and representative sample of anonymized patient cases includes global data from multiple centers and ethnicities, providing a more complete and realistic picture of ILDs than individual studies or datasets.
It is our belief that this database could be the start of finding digital imaging biomarkers that could potentially speed up diagnosis, and aid in better understanding of individual prognosis and response to therapy.
We maintain the world's largest curated, AI-ready dataset for interstitial lung diseases (ILDs), housed in the OSIC Cloud Data Repository (OSIC Cloud). This comprehensive resource combines high-resolution CT scans, clinical data, and longitudinal follow-ups, designed to foster collaborative innovation. Built with the expertise of radiologists, pulmonologists, machine learners, and imaging experts worldwide, The OSIC Cloud offers a rich collection of anonymized HRCT scans and clinical information. Its diverse and representative sample of anonymized patient cases includes global data from multiple centers and ethnicities, providing a more complete and realistic picture of ILDs than individual studies or datasets.
It is our belief that this database could be the start of finding digital imaging biomarkers that could potentially speed up diagnosis, and aid in better understanding of individual prognosis and response to therapy.
How OSIC Accelerates Innovation
|
By uniting global expertise with highly curated, Al-ready data, OSIC is revolutionizing ILD and ILA research. Their comprehensive, meticulously organized dataset empowers researchers worldwide to unlock new insights and accelerate breakthroughs, paving the way for the future of lung health.
|
|
AI + Real-World Data
The OSIC Advantage
Transformational Potential
Enables Innovation In …
10.5K+ HRCT Scans (De-identified)
ILA/ILD Identification & Risk Prediction
200K+ Clinical Data Points (Demographics, PFTs, etc.)
Biomarker Discovery
Longitudinal Follow-Up Data
Trial Simulation & Endpoint Refinement
Global Cohort (US, EU, Asia, LatAm)
Generalizable Model Validation
During this collaborative forum, attendees:
- Listened to, learned from, and asked questions of OSIC members who presented their quantifiable AI advances and emerging innovations using the OSIC data.
- Learned about benefits of the new OSIC Cloud Data Repository, powered by VIDA, including easier contribution of data, robust new filters for cohort selection, collaboration tools to support data sharing.
- Discussed the robust clinical data curation, global normalization, and advanced data power to drive radical progress in drug development for fibrosing lung diseases.
- Had a dialog about the inclusion of new cohorts, including lung cancer screening scans to look for ILAs and ILDs, sarcoidosis, alpha-1.
- Learned about Project OPUS, a new, real-time observational study that applies AI and machine learning technology to the spirometry, environmental and imaging data.
- Participated in a dynamic discussion led by panelists, who shared valuable insights on OSIC’s progress and future direction, early ILD detection, and the impact of clinical data on improving predictions.
Explore what was presented and discussed during the OSIC AI/Biomarker Innovation Showcase:
Case Study
Training AI to Detect ILA
Can we predict which ILAs will progress to ILD?
OSIC is enabling researchers to train deep learning models to do just that.
OSIC is enabling researchers to train deep learning models to do just that.
- Early ILA detection using LDCT and HDCT
- Stratification of “at-risk” populations
- Potential for earlier treatment and better outcomes
AI + OSIC = New frontiers in preventive pulmonology
Can AI learn a risk score?*
* OSIC asked contextflow and Brainomix to analyze limited data from the OSIC Cloud lung cancer screening/ILA cohort to identify a proof of concept. These preliminary findings are not conclusive and are for exploratory purposes only.
Unlocking Early Detection with AI ILA Risk Scoring
Enabling precision-driven, personalized management; minimizing missed and delayed diagnoses; enhancing outcomes through timely intervention.
New Cohort
Lung Cancer Screening
The presence of ILA on a lung cancer screening is a significant finding that can increase the risk of developing ILD and may be associated with a higher risk of mortality. Early detection and appropriate management of ILA may be crucial in preventing the progression to ILD and improving long-term outcomes.
|
In a recent study of 1,384 individuals who received a lung cancer screening via CT scan, researchers identified “4% ILA in a lung cancer screening cohort; 37% had radiologic progression of ILA at 1 year and 40% were diagnosed with ILD within 5 years. Fibrotic ILA, defined by the presence of traction bronchiectasis, was a strong predictor of mortality, reduced progression-free survival, and diagnosis of ILD.”
The lung cancer cohort in our database will allow for future research to help identify biomarkers that can predict ILA/ILD disease progression. |
Goal of
5,000
screens in 2025
|
About the OSIC Dataset
|
IMAGING MODALITIES
Standardized DICOM formats: HRCT, LDCT, X-ray, and Photon Counting CT (PCCT) CLINICAL DATA Curated and normalized from global contributors |
PATIENT DIVERSITY
Ethics-cleared, internationally diverse population ILD TYPES INCLUDED IPF, Sarcoidosis, RA‑ILD, Lung Cancer Screens, and more |
AI COLLABORATION
Led by Prof. David Barber, OSIC’s ML lead and Director, UCL Centre for Artificial Intelligence |
About The OSIC Cloud Platform
The OSIC Cloud, powered by vida, is a secure platform for managing de-identified, curated, real-world and clinical trial data — designed to fuel collaborative lung disease research.
THE OSIC CLOUD FEATURES
|
|
NEW
ADVANCED IMAGING TOOLS
The OSIC Cloud Data Overview
Discover Innovative Research Utilizing the Global AI-Ready OSIC Datase
|
Explore the innovative studies conducted using the OSIC dataset, the world's largest AI-ready resource for interstitial lung diseases (ILDs). Researchers from around the globe are harnessing this invaluable data to make significant strides in understanding and treating ILDs. To delve deeper into the impactful research published to date.
|
Released Open-Source
CenTime
Event-conditional modeling of censoring in survival analysis
OSIC provided a grant to University College London (UCL) to create algorithms to help advance digital imaging biomarkers for accurate imaging-based diagnosis, prognosis and prediction of response to therapy. Through this initiative, the UCL team created “CenTime: Event-conditional modeling of censoring in survival analysis.” This work aims to address key limitations in current survival analysis methods.
The algorithm has been trained and evaluated using the combination of real-world, high-resolution lung CT scans (HRCT), associated clinical data, and mortality labels from the OSIC Data Repository. CenTime has shown promising results in more accurately predicting survival probabilities. This has the potential to advance digital imaging biomarkers, not only for lung disease but for other diseases by addressing key limitations in current survival analysis methods and allowing for more accurate and reliable models.
The algorithm has been trained and evaluated using the combination of real-world, high-resolution lung CT scans (HRCT), associated clinical data, and mortality labels from the OSIC Data Repository. CenTime has shown promising results in more accurately predicting survival probabilities. This has the potential to advance digital imaging biomarkers, not only for lung disease but for other diseases by addressing key limitations in current survival analysis methods and allowing for more accurate and reliable models.
|
Current Limitations
Vertical Divider
|
CenTime
|
UCL compared CenTime with standard methods like the Cox proportional-hazard model and DeepHit. Results have indicated that CenTime offers state-of-the-art performance in predicting time-to-death while maintaining comparable ranking performance.
Institutional Partners
These organizations have made multi-year commitments of funding and/or pledged to contribute with imaging and clinical data or with other means to OSIC to ensure that it is positioned for success.
Learn more about OSIC
|
We encourage you to contact us to discuss our mission, the OSIC Cloud Data Repository, and how you can help make a difference in the fight against IPF and ILDs. Additional partners, collaborators and contributors are welcome and encouraged.
|
|
