Developers and Industry

We’re working with all AI stakeholders to inform development of clinically relevant AI algorithms that will benefit radiology and improve health care.

Providing expert guidance

DSI operations are led by senior scientists, data science subspecialty panel members, and the ACR AI Advisory Group, and include radiology professionals with clinical and data science expertise, as well other statistical and data science experts. The Data Science Subspecialty Panels evaluate use cases, prioritizing those that can yield the greatest clinical and operational value while considering which problems are most amenable to AI solutions.

Defining problems amenable to AI solutions

Our TOUCH-AI use cases include a narrative overview, flowcharts and the technical specifications relevant to the clinical problem. They assist developers by detailing critical content pertinent to algorithm development, such as the value proposition, common data elements to inform annotation specifications for training and testing, and output parameters, including radiologist decision support tools.

Training, testing and initial validation

Certify-AI offers developers a method to statistically validate algorithms and gather performance data ahead of the FDA pre-market review process, using a novel dataset that goes far beyond the scope of the original training and testing datasets.

Validating performance

Assess-AI provides developers with longitudinal algorithm performance data. This data can be used for algorithm improvement and meeting any FDA post-market surveillance requirements.

See the complete directory of freely available use cases