We are expanding across the U.S. to ensure maximum diversity in our medical image datasets. Our partners include academic medical centers with research labs and personnel that have an interest in multi-institutional AI research. Academic partners gain access to bulk image retrieval and de-identification software and obtain access to existing multi-institutional de-identified pediatric and adult datasets for use in academic research.
Our miners meet with your research team to work through all questions and concerns. A sub-investigator from your academic medical center submits the multi-institutional IRB. Your radiology information technology (IT) team will review our technology and installation plans. We answer all security questions, demonstrate how our software removes all PHI, and demonstrate how nothing leaves your center without review by your research team. Your research lab will enter into a data transfer research agreement. Once the agreement is signed and active, we help install the bulk image retrieval and de-identification tools. We make sure it is easy for your lab to use and manage. Then you are a full academic partner and can begin mining and access data from other mines as a part of the AI MINER consortium.
AI Miner provides technology that allows your lab to bulk de-identify text reports (e.g. radiology reports and EMR notes and reports), and to bulk retrieve and de-identify images from your PACS. You will use these tools to participate in AI MINER but can also use them for your own research. We also provide a simple solution to securely transfer the de-identified data to the AI MINER repository. The technology helps to make these complex tasks seem easy.
In the United States, each medical center owns the images, reports, and metadata. It is legal and ethical to share these under an IRB-approved research study. The Artificial Intelligence Multi-institutional Imaging aNd Exploratory Research (AI MINER) constortium 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 metadata 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 data. Our fair pricing covers research and service expenses only, including personnel effort and data curation, de-identification, storage and transfer. The costs of our services depend upon the volume of images needed and overall complexity of the research, including the need for patient outcomes data. 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 metadata as part of the de-identified process. Our de-identification software labels each site with a coded identifier that cannot be linked back to the specific AMCs by outside entities.