Article

Automated ACR TI-RADS Classification of Thyroid Nodules from Narrative Ultrasound Reports Using a Fine-Tuned Open-Source Language Model: A Reproducible and Low-Resource Framework

2025-11-04

Abstract excerpt

<title>Abstract</title> <p>Background: Manual ACR TI-RADS classification from narrative ultrasound reports is a key component of thyroid nodule risk stratification but is laborious and subject to inter-observer variability. While Large Language Models (LLMs) offer potential solutions, existing approaches often rely on proprietary models or require extensive computational resources, limiting widespread adoption. T...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 12ca2a63-24a3-56b5-a392-cf11e2e70aad
DOI: 10.21203/rs.3.rs-7864505/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Automated ACR TI-RADS Classification of Thyroid Nodules from Narrative Ultrasound Reports Using a Fine-Tuned Open-Source Language Model: A Reproducible and Low-Resource FrameworkDOI 10.21203/rs.3.rs-7864505/v1Read

Auditable agentic AI for evidence-grounded thyroid ultrasound diagnosis and reportingSemantic proximity Read

Implementing a Resource-Light and Low-Code Large Language Model System for Information Extraction from Mammography Reports: A Case StudySemantic proximity Read

DB-ATRG: The Density and BI-RADS–Aware Triage and Automatic Report Generation System for MammographySemantic proximity Read

Generalizable and Automated Classification of TNM Stage from Pathology Reports with External ValidationSemantic proximity Read

Transfer learning with BERT and ClinicalBERT models for multiclass classification of radiology imaging reportsSemantic proximity Read

Comparative Evaluation the Knowledge of Large Language Models about Response Evaluation Criteria in Solid Tumors?Semantic proximity Read

An Open-source Fine-tuned Large Language Model for Radiological Impression Generation: A Multi-reader Performance StudySemantic proximity Read

Empowering Radiologists with ChatGPT-4o: Comparative Evaluation of Large Language Models and Radiologists in Cardiac CasesSemantic proximity Read

ToKSA - Tokenized Key Sentence Annotation - a Novel Method for Rapid Approximation of Ground Truth for Natural Language ProcessingSemantic proximity Read

An Agentic, No Code Artificial Intelligence Workflow for Developing and Externally Validating a Thyroid Nodule Ultrasound Malignancy ClassifierSemantic proximity Read

Data Extraction from Oncology Imaging Reports by Large Language Models: A Comparative Accuracy StudySemantic proximity Read

An Empirical Evaluation of Low-Rank Adapted Vision–Language Models for Radiology Medical Image CaptioningSemantic proximity Read