A large language model (LLM) significantly outperforms RadLex in expanding terms for radiology report language standardization.
Key Details
- 1Study published in American Journal of Roentgenology compared LLM to RadLex for term expansion in radiology reports.
- 2LLM (Gemini 2.0 Flash Thinking) generated 208,465 additional variants and 69,918 synonyms beyond RadLex's expansion.
- 3LLM expansion improved lexical coverage rate to 81.9% vs. RadLex's 67.5%.
- 4Semantic recall improved to 81.6% (LLM) versus 64% (RadLex), with slightly lower precision (94.8% vs 100%).
- 5F1 score was higher for LLM expansion (0.91) compared to RadLex (0.86).
- 6Study used chest CT reports from five international datasets.
Why It Matters
Automating terminology expansion with LLMs can enhance the accuracy and scalability of natural language processing in radiology, aiding standardized reporting, AI model development, and multi-center research.
Source
AuntMinnie
Related News
•Cardiovascular Business
FDA Clears AI Platform for Comprehensive Cardiac Risk Assessment on CT
HeartLung Corporation's AI-CVD receives FDA clearance for opportunistic multi-condition screening on routine chest CT scans.
•Radiology Business
Google Releases MedGemma 1.5 and MedASR AI Models for Medical Imaging
Google has launched MedGemma 1.5 and MedASR, two new open-access AI models tailored for healthcare and medical imaging use cases.
•Radiology Business
Patients Favor AI in Imaging Diagnostics, Hesitate on Triage Use
Survey finds most patients support AI in diagnostic imaging but are reluctant about its use in triage decisions.