December 5, 2025

The NIH Common Fund Bridge2AI Program’s Salutogenesis Grand Challenge has released the 3rd edition of the Flagship Dataset of Type 2 Diabetes from the AI-READI Project. The Salutogenesis team’s Artificial Intelligence Ready and Exploratory Atlas for Diabetes Insights (AI-READI) project seeks to create a flagship ethically-sourced dataset to enable future generations of artificial intelligence/machine learning (AI/ML) research to provide critical insights into type 2 diabetes mellitus (T2DM), including salutogenic pathways to return to health. 

This release includes:

• 358,999 files of data from 2,280 participants
• Heidelberg Spectralis OCTA data on all participants
• Segmentation of B-scans on Topcon Maestro2, Topcon Triton, Zeiss Cirrus, and Heidelberg Spectralis (under OCTA)
•  New scalable dissemination method using Azure storage containers for improved data delivery and access
• Whole genome sequencing, proteomics, metabolomics, and EHR extraction are underway

The Salutogenesis team has enabled researchers to interact with their data on a smaller scale, launching a highly requested 179.68 GB “Mini Version” of the dataset designed to help with creating pipelines and prototyping code before accessing the full 3.82 TB. This joins their growing suite of interactive resources for data exploration, such as the Metadata Interaction tool designed to filter key metadata from the dataset by clinical measures, imaging types, sites, and more.

Learn more: Explore the dataset on the AI-READI site or visit the Bridge2AI datasets page.