We are expanding across the U.S. to ensure maximum diversity in our medical image datasets. Academic Partners include academic medical centers with research labs and personnel that have an interest in multi-institutional AI research.
The primary investigator of the AI MINER study is Andrew Smith MD PhD, Chair of Radiology at St. Jude Children's Research Hospital. St. Jude is the coordinating center and supports the aiCore software, secure data transfer, and secure storage of data.
A site investigator at your center submits the AI MINER protocol to the IRB, which is a minimal risk multi-institutional research study that will likely be classified as exempt or expedited.
The site investigator signs a research agreement with St. Jude to share data with other Academic Partners.
Your information technology (IT) team reviews the aiCore sofware, installation plans, and manual. St. Jude personnel will answer all security questions.
As an Academic Partner, you can propose or participate in multi-institutional AI research projects.
Investigators will utilize existing software to search radiology reports and the EMR for cohorts.
Academic Partners will have free access aiCore, custom software compiled as a MacOS application for wide accessibility and straightforward installation.aiCore operates on standard iMac systems, offering a cost-effective and simplified solution. Minimal setup is required to establish connections with radiology PACS for bulk image retrieval. Once the images are retrieved on the local iMac, aiCore performs bulk image de-identification. Image de-identification builds off of the Clinical Trial Processor from the RSNA. Text de-identification is also included and builds off the National Library of Medicine scrubber and utilizes a large language model for additional de-identification. Patient names, medical record numbers, and the names of academic medical centers are replaced with coded identifiers, and all dates in images and text are shifted. The investigator can easily quality control the images using Horos, a free medical image viewer.
Image will be securely transferred and stored on a cloud-based system (e.g.Microsoft Azure).
In the United States, each medical center owns the images, reports, and multimodal data. It is legal and ethical to share these under an IRB-approved research study. The Artificial Intelligence Multi-Institutional Network for Ethical Research (AI MINER) is an IRB approved research study. This study has minimal risk, qualifies for a HIPAA waiver and waiver of consent, and the images, reports, and multimodal data will be de-identified with a coded identifier applied. Click here to learn more about patient privacy and security.
We don’t sell or place a value on patient images, reports, or multimodal data. Funding from industry and grants covers research and service expenses only, including personnel effort and data curation, de-identification, storage and transfer. Academic Partners that contribute data will earn credits to gain access to data in the repository.
The following PHI will remain with the Academic Partners and will not be entered into the
AI MINER data repository:
No. The name of each AMC is removed from the images, reports, and multimodal data as part of the de-identified process. Our de-identification software (aiCore) labels each site with a coded identifier that cannot be linked back to the specific AMCs by outside entities.