Integrating artificial intelligence with the radiology reporting workflows (RIS and PACS)
Date: 2021
Date of next review: 2025
This guidance sets out the standards that a department should meet when integrating AI into already established systems, producing a safe seamless system with the patients at the centre. Users should be made aware by vendors of the limitations of the system with clear declarations to serve this purpose.
Recommendations of the guidance
- Artificial intelligence must be integrated in reporting (radiology information system [RIS] and picture archiving and communication system [PACS]) workflows seamlessly and in a way that does not add extra burden to radiologists.
- The accuracy of the AI algorithms must be clearly declared for radiologists and others making decisions on patient management.
- AI findings must be communicated to the RIS via existing, widely used global technical standards (HL7).
- AI findings must be communicated to the PACS using existing, widely used global technical standards (DICOM).
- The workflow must be robust enough to ensure AI analysis is complete and available on PACS before a human reporter starts image interpretation.
The four main technologies that will be expected to work co-operatively for a radiology department are:
- Scanners/modalities
- RIS
- PACS
- AI platforms (containing one or more AI algorithm).
They must support interoperability standards like DICOM and HL7 communications as explained in Appendix 1 of this guidance.
![](/media/vjjphbri/rcr-publications_integrating-artificial-intelligence-with-the-radiology-reporting-workflows-ris-and-pacs-_march-2021.png?rxy=0.462406015037594,0.3331915496951652&v=1da0272d5cf9790?center=0%2C0&height=905.0862676056338&width=717)