Large language models can match radiologists in selecting MRI protocols, potentially improving workflow efficiency.
Key Details
- 1Researchers evaluated four open-weight LLMs on 1,200 MRI referral forms for protocol selection.
- 2Models received actual referral texts and chose institutional protocols and sequences from set lists.
- 3A consensus from two board-certified radiologists served as the standard of reference.
- 4Manual protocol selection is time-consuming and subject to variability, impacting quality and efficiency.
Why It Matters
This study demonstrates that LLMs can reliably automate a complex radiology workflow, offering potential to standardize and accelerate MRI protocoling. Adoption of such AI tools could free radiologists for higher-level tasks and improve departmental consistency and efficiency.
Source
Radiology Business
Related News
•Radiology Business
Weill Cornell Investigates Unauthorized Use of Radiology Data in AI Research
Weill Cornell Medicine reported improper use of patient information in radiology AI research, violating privacy protocols.
•AuntMinnie
Open-Source AI Platform Powers Pediatric Bone and Fetal MRI Pipelines
Open-source AI platform successfully integrated and sustained two pediatric imaging pipelines for bone length and fetal MRI at a children's hospital.
•Radiology Business
Meta Funds Ohio State’s Radiology AI Innovation Projects
Meta will fund Ohio State researchers to explore AI-driven advancements in radiology, including chest X-ray reporting and disease prediction.