EUVIMEDObjevte EUVIMED
Open access

Using a Large Language Model for Breast Imaging Reporting and Data System Classification and Malignancy Prediction to Enhance Breast Ultrasound Diagnosis: Retrospective Study

Su Miaojiao iD, Liang Xia iD, Zeng Xian Tao iD, Hong Zhi Liang iD, Cheng Sheng iD, Wu Songsong iD

JMIR Medical Informatics · 2025-06-11 · 13 · e70924-e70924

DOI: 10.2196/70924 ↗

At a glance

Journal article in JMIR Medical Informatics, published online on 2025-06-11. Written by Su Miaojiao and 5 co-authors. Institution: Department of Ultrasound, Fujian Provincial Hospital, Affiliated Hospital of Fuzhou University, 134 Dong Street, Gulou District, Fuzhou, 350500, Chin…. Major MEDLINE topics: Breast Neoplasms, Ultrasonography, Mammary. Cited 18 times so far (Crossref); 31 references. The full text is freely available in PubMed Central.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

Breast ultrasound is essential for evaluating breast nodules, with Breast Imaging Reporting and Data System (BI-RADS) providing standardized classification. However, interobserver variability among radiologists can affect diagnostic accuracy. Large language models (LLMs) like ChatGPT-4 have shown potential in medical imaging interpretation. This study explores its feasibility in improving BI-RADS classification consistency and malignancy prediction compared to radiologists.

Objective

This study aims to evaluate the feasibility of using LLMs, particularly ChatGPT-4, to assess the consistency and diagnostic accuracy of standardized breast ultrasound imaging reports, using pathology as the reference standard.

Methods

This retrospective study analyzed breast nodule ultrasound data from 671 female patients (mean 45.82, SD 9.20 years; range 26‐75 years) who underwent biopsy or surgical excision at our hospital between June 2019 and June 2024. ChatGPT-4 was used to interpret BI-RADS classifications and predict benign versus malignant nodules. The study compared the model’s performance to that of two senior radiologists (≥15 years of experience) and two junior radiologists (

Subjects

MeSH terms (MEDLINE)

Breast NeoplasmsUltrasonography, MammaryHumansRetrospective StudiesFemaleMiddle AgedAdultAgedSensitivity and SpecificityBreastLarge Language Models

Author keywords

BI-RADSBreast Imaging Reporting and Data SystemChatGPT-4breast ultrasoundimage-to-text–LLMlarge language models

Authors and institutions

  • Department of Ultrasound, Fujian Provincial Hospital, Affiliated Hospital of Fuzhou University, 134 Dong Street, Gulou District, Fuzhou, 350500, China, 86 15960191609.

ORCID profiles: Su Miaojiao, Liang Xia, Zeng Xian Tao, Hong Zhi Liang, Cheng Sheng, Wu Songsong

Cite

APA

Miaojiao, S., Xia, L., Xian Tao, Z., Zhi Liang, H., Sheng, C., & Songsong, W. (2025). Using a Large Language Model for Breast Imaging Reporting and Data System Classification and Malignancy Prediction to Enhance Breast Ultrasound Diagnosis: Retrospective Study. JMIR Medical Informatics, 13, e70924-e70924. https://doi.org/10.2196/70924

Vancouver

Miaojiao S, Xia L, Xian Tao Z, Zhi Liang H, Sheng C, Songsong W. Using a Large Language Model for Breast Imaging Reporting and Data System Classification and Malignancy Prediction to Enhance Breast Ultrasound Diagnosis: Retrospective Study. JMIR Medical Informatics. 2025;13:e70924-e70924. doi:10.2196/70924

BibTeX
@article{Miaojiao2025,
  author = {Miaojiao, Su and Xia, Liang and Xian Tao, Zeng and Zhi Liang, Hong and Sheng, Cheng and Songsong, Wu},
  title = {Using a Large Language Model for Breast Imaging Reporting and Data System Classification and Malignancy Prediction to Enhance Breast Ultrasound Diagnosis: Retrospective Study},
  journal = {JMIR Medical Informatics},
  year = {2025},
  volume = {13},
  pages = {e70924--e70924},
  doi = {10.2196/70924}
}
Start for free →