about hero


We’re working with a variety of stakeholders — including the developer community — to inform development of clinically relevant AI that will benefit radiology and improve health care.


Explore freely available use cases focusing on critical content for algorithm development, including the value proposition, common data elements, and output parameters including radiologist decision support tools. Our use cases help radiologists and allied professionals by ensuring that AI tools provide needed information, can be efficiently implemented into daily workflow, and have the potential to improve patient care.


Streamline the process for independently evaluating an algorithm’s performance ahead of the FDA pre-market review process by using our sequestered, multi-institution, well-qualified datasets. Services can be used individually or bundled together to determine if an algorithm performs well across imaging devices, clinical facilities and demographic populations.


Capture real-world data during clinical use in a clinical data registry. Our service reports longitudinal algorithm performance data for use with algorithm improvement and meeting FDA post-market surveillance requirements. Performance reports are available for both developers and clinical sites.

ACR Assist

Modernize your reporting and unlock the value of your data with guidance for optimal radiologist interpretation of clinical scenarios, encoded into machine-readable modules. Each ACR Assistant includes information on required inputs of each clinical guidance scenario, as well as the logic to guide radiologists’ reports and recommendations.

AI Central

Explore AI Central, the most complete and up to date online, searchable directory of FDA-cleared imaging AI products in the United States. AI Central allows users to streamline their review of the imaging AI marketplace with the option to sort by specific anatomical areas, subspecialties, or modalities through its interactive, graphical database search interface. 

ACR Common

Simplify making one-to-one comparisons with this common language used across all ACR products and services. ACR Common  is beneficial for organizations because it is based on a collection of common radiology terms and semantic structures, and organized around fundamental and derived axes such as scenario, procedure and finding.

Dataset Directory

Our list of datasets connects machine learning practitioners with accessible and meaningful datasets for their projects. The list includes organizations to contact about their datasets and organizations with datasets ready to be pulled directly from their websites.

Image Anonymization and Data Labeling

Protecting personal health information and preparing data appropriately for training and testing an algorithm can be difficult and time-consuming, but it is an area in which the ACR has developed significant experience through its clinical trials networks. We offer image anonymization and annotation tools and services to developers so they in turn can work with radiologists in a wide array of clinical settings to prepare images for use in AI development.


The RadElement.org site offers a catalog of radiology common data elements (CDEs), indexed by title and controlled terms such as SNOMED CT, LOINC, and RadLex. CDEs can be grouped into "sets" that list the CDEs used in particular applications. CDEs define the attributes and allowable values of a unit of information, so that information can be collected and stored uniformly across institutions and studies. CDEs can be reused, and hence may belong to more than one set.