Keywords: Language Models, Language Models
Motivation: Selecting MRI scan protocols is a manual task for technicians, requiring extensive scanner-specific training. Current support methods lack precision and adaptability to scan requirements.
Goal(s): Develop a tool using a RAG approach, leveraging a language model to suggest optimal protocols and strategies based on site-specific protocol layouts and requested procedures.
Approach: Our method incorporates the local protocol tree and RIS layout to streamline protocol selection. A feasibility study, using simulated scan requests and a vendor's protocol tree, assesses its effectiveness.
Results: Our RAG-based tool reliably aids protocol selection with up to 97.8% success rate without additional language model training.
Impact: This work streamlines MRI scan protocol selection using a context-aware, RAG-based pipeline. By minimizing manual input and training needs, it demonstrates potential for enhancing workflow efficiency and patient-adapted imaging based on available patient information.
How to access this content:
For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.
After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.
After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.
Keywords