At SIIM 2026, LLMs demonstrated high accuracy on radiology-based numerical tasks, particularly in extraction and judgment tests.
Key Details
- 1LLMs evaluated included Llama 3.1 8B, DeepSeek R1-distilled Llama 8B, OpenAI o1-mini, and OpenAI GPT 5-mini.
- 2Tasks tested involved extraction and judgment from DEXA, ultrasound, CT, and PET radiology reports.
- 3Most models, except Llama, achieved over 95% accuracy on extraction tasks; Llama ranged from 86% to 98.7%.
- 4GPT 5-mini achieved highest minimum accuracy (judgment tasks: 91.7%) among tested models.
- 5o1-mini and GPT 5-mini reached perfect accuracy in detecting osteoporosis and made no mathematical errors.
- 6Answer-only output formats reduced accuracy for Llama and DeepSeek, but not OpenAI models.
Why It Matters
Reliable numerical extraction and judgment by LLMs could streamline radiology workflows, increasing efficiency for repetitive data extraction. However, caution remains due to ongoing risks of non-mathematical and medical knowledge-based errors.
Source
AuntMinnie
Related News
•Radiology Business
AI-Powered Tool Streamlines CT Scan Prioritization in Emergency Departments
An AI-based CT queue system significantly reduces wait times for ED patients by prioritizing scans likely to reveal critical findings.
•Radiology Business
AI Workflow Enables General Radiologists to Match Breast Specialists in Screening
AI-powered workflow helps generalist radiologists detect breast cancer at rates comparable to specialists.
•Radiology Business
LLMs Automate Radiology Report Quality Control, Study Finds
LLM-based systems can rapidly automate radiology report quality control, saving significant manual review time.