Evaluating text and visual diagnostic capabilities of large language models on questions related to the Breast Imaging Reporting and Data System Atlas 5 edition.

Journal: Diagnostic and interventional radiology (Ankara, Turkey)

Published Date: Sep 9, 2024

Abstract

PURPOSE: This study aimed to evaluate the performance of large language models (LLMs) and multimodal LLMs in interpreting the Breast Imaging Reporting and Data System (BI-RADS) categories and providing clinical management recommendations for breast radiology in text-based and visual questions.

Authors

Yasin Celal Güneş

Kırıkkale Yüksek İhtisas Hospital, Clinic of Radiology, Kırıkkale, Türkiye.
Turay Cesur

Mamak State Hospital, Clinic of Radiology, Ankara, Türkiye.
Eren Çamur

Ankara 29 Mayıs State Hospital, Clinic of Radiology, Ankara, Türkiye.
Leman Günbey Karabekmez

Ankara Yıldırım Beyazıt University Faculty of Medicine, Department of Radiology, Ankara, Türkiye.

Keywords

Breast Breast Neoplasms Cross-Sectional Studies Female Humans Language Large Language Models Radiology Information Systems Ultrasonography, Mammary

External Resources

View on PubMed Access via DOI PubMed (39248152)

Evaluating text and visual diagnostic capabilities of large language models on questions related to the Breast Imaging Reporting and Data System Atlas 5 edition.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals