The added value of including thyroid nodule features into large language models for automatic ACR TI-RADS classification based on ultrasound reports.

Journal: Japanese journal of radiology

PMID: 39585560

Abstract

OBJECTIVE: The ACR Thyroid Imaging, Reporting, and Data System (TI-RADS) uses a score based on ultrasound (US) imaging to stratify the risk of nodule malignancy and recommend appropriate follow-up. This study aims to analyze US reports and explore how Natural Language Processing (NLP) leveraging Transformers models can classify ACR TI-RADS from text reports using the description of thyroid nodule features.

Authors

Pilar López-Úbeda

Universidad de Jaén, Jaén, Andalucía, Spain.
Teodoro Martín-Noguerol

MRI Unit, Radiology Department, HT médica Carmelo Torres 2, Jaén 23007, Spain. Electronic address: t.martin.f@htime.org.
Alba Ruiz-Vinuesa

Escuela de Ingeniería de Fuenlabrada, Universidad Rey Juan Carlos, Cam. del Molino, 5, 28942, Fuenlabrada, Madrid, Spain.
Antonio Luna

MRI Unit, Radiology Department, Health Time, Jaén, Spain. Electronic address: aluna70@htime.org.

Keywords

Female Humans Large Language Models Male Natural Language Processing Radiology Information Systems Retrospective Studies Thyroid Gland Thyroid Neoplasms Thyroid Nodule Ultrasonography

External Resources

View on PubMed Access via DOI PubMed (39585560)

The added value of including thyroid nodule features into large language models for automatic ACR TI-RADS classification based on ultrasound reports.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals