Keywords: Language Models, AI/ML Software, Workflow, Assistant
Motivation: Operating MRI scanners is complex, and technicians frequently encounter technical issues that disrupt the workflow. Existing keyword-based support tools often fail to provide adequate assistance.
Goal(s): Develop an advanced troubleshoot companion (TSC) leveraging large language models (LLMs) to provide faster, context-aware solutions for MRI technicians.
Approach: We implemented a retrieval-augmented generation (RAG) system, combining GPT-4 with a curated knowledge base, and evaluated it against existing tools in a user study.
Results: The RAG-based TSC was rated more effective and time-efficient, demonstrating potential as a superior support tool for MRI troubleshooting.
Impact: This work enhances MRI troubleshooting by introducing a context-aware support tool based on LLMs, improving problem-solving efficiency for technicians. It highlights the potential of RAG systems in healthcare to replace traditional keyword-based search methods with more intelligent solutions.
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