人工智能在外科超声诊断细胞学不确定甲状腺结节中的作用

IF 2.7 3区医学 Q1 SURGERY

American journal of surgery Pub Date : 2025-09-02 DOI:10.1016/j.amjsurg.2025.116599

Man Him Matrix Fung , Wai In Ng , Henry Ethan Lee , Tin Ho Chan , Steven Tsz King Leung , Yan Luk , Brian Hung Hin Lang

{"title":"人工智能在外科超声诊断细胞学不确定甲状腺结节中的作用","authors":"Man Him Matrix Fung , Wai In Ng , Henry Ethan Lee , Tin Ho Chan , Steven Tsz King Leung , Yan Luk , Brian Hung Hin Lang","doi":"10.1016/j.amjsurg.2025.116599","DOIUrl":null,"url":null,"abstract":"<div><h3>Introduction</h3><div>Evaluating indeterminate thyroid nodules(ITN) is challenging, especially without molecular tests. This study examines whether artificial intelligence (AI) assistance can improve ITN diagnostic accuracy and bridge expertise gaps in surgeon-performed ultrasound.</div></div><div><h3>Methods</h3><div>134 ultrasound clips from 67 patients with ITN were reviewed by doctors of four levels: endocrine-surgery specialist, senior residents, junior residents, and medical student. After a 2-week wash-out, they re-evaluated the clips using AI-SONIC, an AI platform analyzing ultrasound real-time to predict cancer risk. Performance was validated against final histopathology.</div></div><div><h3>Results</h3><div>Without AI, medical students, junior residents and senior residents performed significantly worse than specialists(AUROC 0.530–0.560 vs 0.771, p < 0.05). AI-SONIC improved residents' and medical students' diagnostic accuracy to levels comparable with specialists(AUROC 0.733–0.751 vs 0.771). The specialists’ performance remained unchanged with AI assistance.</div></div><div><h3>Conclusion</h3><div>AI enhances ultrasound evaluation of ITN by junior surgeons and medical students, elevating their accuracy to expert levels, supporting clinical assessment and medical education.</div></div>","PeriodicalId":7771,"journal":{"name":"American journal of surgery","volume":"249 ","pages":"Article 116599"},"PeriodicalIF":2.7000,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"The role of artificial intelligence in surgeon-performed ultrasonographic evaluation of cytologically indeterminate thyroid nodules\",\"authors\":\"Man Him Matrix Fung , Wai In Ng , Henry Ethan Lee , Tin Ho Chan , Steven Tsz King Leung , Yan Luk , Brian Hung Hin Lang\",\"doi\":\"10.1016/j.amjsurg.2025.116599\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Introduction</h3><div>Evaluating indeterminate thyroid nodules(ITN) is challenging, especially without molecular tests. This study examines whether artificial intelligence (AI) assistance can improve ITN diagnostic accuracy and bridge expertise gaps in surgeon-performed ultrasound.</div></div><div><h3>Methods</h3><div>134 ultrasound clips from 67 patients with ITN were reviewed by doctors of four levels: endocrine-surgery specialist, senior residents, junior residents, and medical student. After a 2-week wash-out, they re-evaluated the clips using AI-SONIC, an AI platform analyzing ultrasound real-time to predict cancer risk. Performance was validated against final histopathology.</div></div><div><h3>Results</h3><div>Without AI, medical students, junior residents and senior residents performed significantly worse than specialists(AUROC 0.530–0.560 vs 0.771, p < 0.05). AI-SONIC improved residents' and medical students' diagnostic accuracy to levels comparable with specialists(AUROC 0.733–0.751 vs 0.771). The specialists’ performance remained unchanged with AI assistance.</div></div><div><h3>Conclusion</h3><div>AI enhances ultrasound evaluation of ITN by junior surgeons and medical students, elevating their accuracy to expert levels, supporting clinical assessment and medical education.</div></div>\",\"PeriodicalId\":7771,\"journal\":{\"name\":\"American journal of surgery\",\"volume\":\"249 \",\"pages\":\"Article 116599\"},\"PeriodicalIF\":2.7000,\"publicationDate\":\"2025-09-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"American journal of surgery\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0002961025004222\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"SURGERY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"American journal of surgery","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0002961025004222","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"SURGERY","Score":null,"Total":0}

引用次数: 0

摘要

评估不确定甲状腺结节（ITN）具有挑战性，特别是在没有分子检测的情况下。本研究探讨人工智能（AI）辅助是否可以提高ITN诊断的准确性，并弥合外科超声的专业知识差距。方法对67例ITN患者的134张超声片进行分析，由内分泌外科专科医生、老年住院医师、初级住院医师和医学生四个级别的医生进行分析。在两周的冲洗后，他们使用AI- sonic（一种实时分析超声以预测癌症风险的人工智能平台）重新评估这些剪辑。根据最终的组织病理学结果验证了性能。结果在不使用人工智能的情况下，医学生、初级住院医师和老年住院医师的表现明显差于专科医师（AUROC: 0.530-0.560 vs 0.771, p < 0.05）。AI-SONIC将住院医生和医学生的诊断准确性提高到与专家相当的水平（AUROC 0.733-0.751 vs 0.771）。在人工智能的帮助下，专家们的表现保持不变。结论人工智能增强了初级外科医生和医学生对ITN的超声评估，将其准确性提高到专家水平，支持临床评估和医学教育。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

The role of artificial intelligence in surgeon-performed ultrasonographic evaluation of cytologically indeterminate thyroid nodules

Introduction

Evaluating indeterminate thyroid nodules(ITN) is challenging, especially without molecular tests. This study examines whether artificial intelligence (AI) assistance can improve ITN diagnostic accuracy and bridge expertise gaps in surgeon-performed ultrasound.

Methods

134 ultrasound clips from 67 patients with ITN were reviewed by doctors of four levels: endocrine-surgery specialist, senior residents, junior residents, and medical student. After a 2-week wash-out, they re-evaluated the clips using AI-SONIC, an AI platform analyzing ultrasound real-time to predict cancer risk. Performance was validated against final histopathology.

Results

Without AI, medical students, junior residents and senior residents performed significantly worse than specialists(AUROC 0.530–0.560 vs 0.771, p < 0.05). AI-SONIC improved residents' and medical students' diagnostic accuracy to levels comparable with specialists(AUROC 0.733–0.751 vs 0.771). The specialists’ performance remained unchanged with AI assistance.

Conclusion

AI enhances ultrasound evaluation of ITN by junior surgeons and medical students, elevating their accuracy to expert levels, supporting clinical assessment and medical education.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

American journal of surgery 医学-外科

CiteScore

5.00

自引率

6.70%

发文量

570

审稿时长

56 days

期刊介绍： The American Journal of Surgery® is a peer-reviewed journal designed for the general surgeon who performs abdominal, cancer, vascular, head and neck, breast, colorectal, and other forms of surgery. AJS is the official journal of 7 major surgical societies* and publishes their official papers as well as independently submitted clinical studies, editorials, reviews, brief reports, correspondence and book reviews.