Transforming adnexal mass assessment: how large language model improve ovarian-adnexal reporting and data system interpretation and sonographer performance
Abdominal Radiology · 2026
DOI: 10.1007/s00261-026-05498-x ↗Kurz gefasst
Fachartikel in der Zeitschrift Abdominal Radiology, 2026. Verfasst von Yueting Sun und 8 weiteren Autor:innen. Beteiligte Einrichtung: First Affiliated Hospital of Sun Yat-sen University, Guangzhou, China. Hauptthemen laut MEDLINE: Large Language Models, Adnexal Diseases, Ovarian Neoplasms, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 34 Literaturangaben. Gefördert von: National Nature Science Foundation of China.
Abstract (Originalsprache)
OBJECTIVES: To assess the accuracy of large language models (LLMs) in Ovarian-Adnexal Reporting and Data System (O-RADS) categorization based on free-text ultrasound reports and to explore their potential to support radiologists with varying levels of experience. MATERIALS AND METHODS: This retrospective study included patients with suspected adnexal masses from October 2022 to May 2024. A reference standard for O-RADS categorization was established by consensus of three senior radiologists. Surgical pathology served as the gold standard for determining benign versus malignant nature. Three LLMs (ChatGPT-4o, ChatGPT-5, Gemini 2.5 Pro) were prompted with O-RADS rules using few-shot learning. Intra-LLM agreement and accuracy against the reference standard were evaluated, along with structured error analysis for systematic misclassification patterns. In a crossover design, a subset of 150 lesions was interpreted independently by two junior and two senior readers with and without LLM assistance. Diagnostic performance (area under the receiver operating characteristic curve [AUC]), inter-reader agreement, and agreement with the reference standard were compared between assisted and unassisted readings. RESULTS: A total of 302 patients with 324 lesions were analyzed. All three LLMs demonstrated substantial intra-LLM agreement (κ = 0.65-0.77) and high categorization accuracy against the reference standard, with no significant differences among models (p = 0.70). Error analysis revealed that misclassifications were concentrated in lesions with borderline morphologic features. With LLM assistance, junior radiologists showed higher inter-reader agreement and agreement with the reference standard (weighted κ ≥ 0.85), along with a non-significant trend toward better diagnostic performance (mean ΔAUC = 0.10; p = 0.06). In contrast, senior readers showed stable performance (mean ΔAUC = 0.01; p = 0.22). In discordant cases, junior readers accepted LLM suggestions in 60.78%-72.34% of instances, compared with only 2.04%-2.33% among seniors. CONCLUSION: LLMs demonstrated high accuracy and reliability in O-RADS ultrasound categorization based on free-text reports. Their assistance was associated with increased O-RADS categorization performance and a non-significant trend toward better diagnostic performance among junior readers, suggesting their potential as an adjunct tool for less experienced radiologists, however, these observed effects predominantly reflect substantial reliance on LLM suggestions rather than independent skill improvement.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- First Affiliated Hospital of Sun Yat-sen University, Guangzhou, China.
- First Affiliated Hospital of Sun Yat-sen University, Guangzhou, China. xiehn@mail.sysu.edu.cn.
Förderung
- National Nature Science Foundation of China
Zitieren
APA
Sun, Y., Shen, H., Zhang, L., Jiang, Y., Zheng, Q., Du, L., He, M., Wu, L., & Xie, H. (2026). Transforming adnexal mass assessment: how large language model improve ovarian-adnexal reporting and data system interpretation and sonographer performance. Abdominal Radiology. https://doi.org/10.1007/s00261-026-05498-x
Vancouver
Sun Y, Shen H, Zhang L, Jiang Y, Zheng Q, Du L, et al. Transforming adnexal mass assessment: how large language model improve ovarian-adnexal reporting and data system interpretation and sonographer performance. Abdominal Radiology. 2026. doi:10.1007/s00261-026-05498-x
BibTeX
@article{Sun2026,
author = {Sun, Yueting and Shen, Hui and Zhang, Lihe and Jiang, Yuting and Zheng, Qiao and Du, Liu and He, Miao and Wu, Lihong and Xie, Hongning},
title = {Transforming adnexal mass assessment: how large language model improve ovarian-adnexal reporting and data system interpretation and sonographer performance},
journal = {Abdominal Radiology},
year = {2026},
doi = {10.1007/s00261-026-05498-x}
}
EUVIMED