9 May 2026 – 14 May 2026
· Cape Town, South Africa
461-02-001
ISMRM Abstract
Patient-tailored Protocol Prescription using Physics-informed Large Language Model Agents
Primary:
Acquisition & Reconstruction - AI methods
Secondary:
Analysis Methods - Software Tools
461-02-001 · AI To Make Protocols, Plan, QC, and Correct Motion
· Tuesday, 12 May, 9:15 AM–10:10 AM · Digital Posters Row B
Keywords:Large Language ModelsAI-assisted radiologyExam Personalization
Accepted
Anuj Sharma 1, William A Grissom1, Mark Griswold1,2
1Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, United States of America
2Department of Radiology, University Hospitals, Cleveland, United States of America
Presenting Author: Anuj Sharma
Synopsis
Motivation:
Goals:
Approach:
Results:
Preview figure
Full abstract & presentation
The full text, figures, and any recorded presentation for this abstract are not shown here. Log in if you are a member or registered attendee with access.
Full abstracts, figures, and presentations for 2026 ISMRM-ISMRT Annual Meeting and Exhibition are available to registered attendees. This content becomes freely available to the public on 13 May 2028.
To request or purchase access, contact the ISMRM Central Office at support@ismrm.org.
1. S Gyftopoulos, D Kim, E Aaltonen, LI Horwitz. Patient recall imaging in the ambulatory setting. American Journal of Roentgenology, 206(4):787–791, 2016. doi:10.2214/AJR.15.15268. [doi]
2. A Sharma, W A Grissom, M A Griswold. Designing MR exams using an autonomous multi-agent large language model system. In Proceedings Annual Meeting, ISMRM Hawaii, page 3376, 2025.
3. A E W Johnson, L Bulgarelli, L Shen et al. MIMIC-IV, a freely accessible electronic health record dataset. Sci Data 10(1), 2023. https://doi.org/10.1038/s41597-022-01899-x. [doi]
4. C Harrison. LangChain. Version 0.2.16. https://github.com/langchain-ai/langchain
5. X Hou, et al. Model context protocol (MCP): Landscape, security threats, and future research directions. arXiv preprint arXiv:2503.23278, 2025.