基于深度学习的人工智能模型在乳腺结节分类中的应用价值

IF 1.8 4区 医学 Q3 MEDICINE, GENERAL & INTERNAL
British journal of hospital medicine Pub Date : 2025-06-25 Epub Date: 2025-06-15 DOI:10.12968/hmed.2025.0078
Shaogang Zhi, Xiaoxia Cai, Wei Zhou, Peipei Qian
{"title":"基于深度学习的人工智能模型在乳腺结节分类中的应用价值","authors":"Shaogang Zhi, Xiaoxia Cai, Wei Zhou, Peipei Qian","doi":"10.12968/hmed.2025.0078","DOIUrl":null,"url":null,"abstract":"<p><p><b>Aims/Background</b> Breast nodules are highly prevalent among women, and ultrasound is a widely used screening tool. However, single ultrasound examinations often result in high false-positive rates, leading to unnecessary biopsies. Artificial intelligence (AI) has demonstrated the potential to improve diagnostic accuracy, reducing misdiagnosis and minimising inter-observer variability. This study developed a deep learning-based AI model to evaluate its clinical utility in assisting sonographers with the Breast Imaging Reporting and Data System (BI-RADS) classification of breast nodules. <b>Methods</b> A retrospective analysis was conducted on 558 patients with breast nodules classified as BI-RADS categories 3 to 5, confirmed through pathological examination at The People's Hospital of Pingyang County between December 2019 and December 2023. The image dataset was divided into a training set, validation set, and test set, and a convolutional neural network (CNN) was used to construct a deep learning-based AI model. Patients underwent ultrasound examination and AI-assisted diagnosis. The receiver operating characteristic (ROC) curve was used to analyse the performance of the AI model, physician adjudication results, and the diagnostic efficacy of physicians before and after AI model assistance. Cohen's weighted Kappa coefficient was used to assess the consistency of BI-RADS classification among five ultrasound physicians before and after AI model assistance. Additionally, statistical analyses were performed to evaluate changes in BI-RADS classification results before and after AI model assistance for each physician. <b>Results</b> According to pathological examination, 765 of the 1026 breast nodules were benign, while 261 were malignant. The sensitivity, specificity, and accuracy of routine ultrasonography in diagnosing benign and malignant nodules were 80.85%, 91.59%, and 88.31%, respectively. In comparison, the AI system achieved a sensitivity of 89.36%, specificity of 92.52%, and accuracy of 91.56%. Furthermore, AI model assistance significantly improved the consistency of physicians' BI-RADS classification (<i>p</i> < 0.001). <b>Conclusion</b> A deep learning-based AI model constructed using ultrasound images can enhance the differentiation between benign and malignant breast nodules and improve classification accuracy, thereby reducing the incidence of missed and misdiagnoses.</p>","PeriodicalId":9256,"journal":{"name":"British journal of hospital medicine","volume":"86 6","pages":"1-19"},"PeriodicalIF":1.8000,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Application Value of Deep Learning-Based AI Model in the Classification of Breast Nodules.\",\"authors\":\"Shaogang Zhi, Xiaoxia Cai, Wei Zhou, Peipei Qian\",\"doi\":\"10.12968/hmed.2025.0078\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p><b>Aims/Background</b> Breast nodules are highly prevalent among women, and ultrasound is a widely used screening tool. However, single ultrasound examinations often result in high false-positive rates, leading to unnecessary biopsies. Artificial intelligence (AI) has demonstrated the potential to improve diagnostic accuracy, reducing misdiagnosis and minimising inter-observer variability. This study developed a deep learning-based AI model to evaluate its clinical utility in assisting sonographers with the Breast Imaging Reporting and Data System (BI-RADS) classification of breast nodules. <b>Methods</b> A retrospective analysis was conducted on 558 patients with breast nodules classified as BI-RADS categories 3 to 5, confirmed through pathological examination at The People's Hospital of Pingyang County between December 2019 and December 2023. The image dataset was divided into a training set, validation set, and test set, and a convolutional neural network (CNN) was used to construct a deep learning-based AI model. Patients underwent ultrasound examination and AI-assisted diagnosis. The receiver operating characteristic (ROC) curve was used to analyse the performance of the AI model, physician adjudication results, and the diagnostic efficacy of physicians before and after AI model assistance. Cohen's weighted Kappa coefficient was used to assess the consistency of BI-RADS classification among five ultrasound physicians before and after AI model assistance. Additionally, statistical analyses were performed to evaluate changes in BI-RADS classification results before and after AI model assistance for each physician. <b>Results</b> According to pathological examination, 765 of the 1026 breast nodules were benign, while 261 were malignant. The sensitivity, specificity, and accuracy of routine ultrasonography in diagnosing benign and malignant nodules were 80.85%, 91.59%, and 88.31%, respectively. In comparison, the AI system achieved a sensitivity of 89.36%, specificity of 92.52%, and accuracy of 91.56%. Furthermore, AI model assistance significantly improved the consistency of physicians' BI-RADS classification (<i>p</i> < 0.001). <b>Conclusion</b> A deep learning-based AI model constructed using ultrasound images can enhance the differentiation between benign and malignant breast nodules and improve classification accuracy, thereby reducing the incidence of missed and misdiagnoses.</p>\",\"PeriodicalId\":9256,\"journal\":{\"name\":\"British journal of hospital medicine\",\"volume\":\"86 6\",\"pages\":\"1-19\"},\"PeriodicalIF\":1.8000,\"publicationDate\":\"2025-06-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"British journal of hospital medicine\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.12968/hmed.2025.0078\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/6/15 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q3\",\"JCRName\":\"MEDICINE, GENERAL & INTERNAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"British journal of hospital medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.12968/hmed.2025.0078","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/6/15 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"MEDICINE, GENERAL & INTERNAL","Score":null,"Total":0}
引用次数: 0

摘要

目的/背景乳腺结节在女性中非常普遍,超声是一种广泛使用的筛查工具。然而,单一超声检查往往导致高假阳性率,导致不必要的活组织检查。人工智能(AI)已经证明了提高诊断准确性、减少误诊和最小化观察者之间差异的潜力。本研究开发了一种基于深度学习的人工智能模型,以评估其在协助超声医师使用乳腺成像报告和数据系统(BI-RADS)对乳腺结节进行分类方面的临床应用。方法回顾性分析2019年12月至2023年12月在平阳县人民医院经病理检查确诊的BI-RADS 3 ~ 5类乳腺结节患者558例。将图像数据集分为训练集、验证集和测试集,利用卷积神经网络(CNN)构建基于深度学习的AI模型。患者接受超声检查和人工智能辅助诊断。采用受试者工作特征(ROC)曲线分析人工智能模型的性能、医生裁决结果以及人工智能模型辅助前后医生的诊断效果。采用Cohen加权Kappa系数评估5位超声医师在AI模型辅助前后BI-RADS分类的一致性。此外,对每位医生在AI模型辅助前后BI-RADS分类结果的变化进行统计分析。结果1026例乳腺结节中,良性765例,恶性261例。常规超声诊断良、恶性结节的敏感性为80.85%,特异性为91.59%,准确性为88.31%。相比之下,人工智能系统的灵敏度为89.36%,特异性为92.52%,准确率为91.56%。此外,AI模型辅助显著提高了医生BI-RADS分类的一致性(p < 0.001)。结论基于超声图像构建的基于深度学习的人工智能模型可以增强乳腺结节良恶性的鉴别,提高分类准确率,从而降低漏诊和误诊的发生率。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Application Value of Deep Learning-Based AI Model in the Classification of Breast Nodules.

Aims/Background Breast nodules are highly prevalent among women, and ultrasound is a widely used screening tool. However, single ultrasound examinations often result in high false-positive rates, leading to unnecessary biopsies. Artificial intelligence (AI) has demonstrated the potential to improve diagnostic accuracy, reducing misdiagnosis and minimising inter-observer variability. This study developed a deep learning-based AI model to evaluate its clinical utility in assisting sonographers with the Breast Imaging Reporting and Data System (BI-RADS) classification of breast nodules. Methods A retrospective analysis was conducted on 558 patients with breast nodules classified as BI-RADS categories 3 to 5, confirmed through pathological examination at The People's Hospital of Pingyang County between December 2019 and December 2023. The image dataset was divided into a training set, validation set, and test set, and a convolutional neural network (CNN) was used to construct a deep learning-based AI model. Patients underwent ultrasound examination and AI-assisted diagnosis. The receiver operating characteristic (ROC) curve was used to analyse the performance of the AI model, physician adjudication results, and the diagnostic efficacy of physicians before and after AI model assistance. Cohen's weighted Kappa coefficient was used to assess the consistency of BI-RADS classification among five ultrasound physicians before and after AI model assistance. Additionally, statistical analyses were performed to evaluate changes in BI-RADS classification results before and after AI model assistance for each physician. Results According to pathological examination, 765 of the 1026 breast nodules were benign, while 261 were malignant. The sensitivity, specificity, and accuracy of routine ultrasonography in diagnosing benign and malignant nodules were 80.85%, 91.59%, and 88.31%, respectively. In comparison, the AI system achieved a sensitivity of 89.36%, specificity of 92.52%, and accuracy of 91.56%. Furthermore, AI model assistance significantly improved the consistency of physicians' BI-RADS classification (p < 0.001). Conclusion A deep learning-based AI model constructed using ultrasound images can enhance the differentiation between benign and malignant breast nodules and improve classification accuracy, thereby reducing the incidence of missed and misdiagnoses.

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
British journal of hospital medicine
British journal of hospital medicine 医学-医学:内科
CiteScore
1.50
自引率
0.00%
发文量
176
审稿时长
4-8 weeks
期刊介绍: British Journal of Hospital Medicine was established in 1966, and is still true to its origins: a monthly, peer-reviewed, multidisciplinary review journal for hospital doctors and doctors in training. The journal publishes an authoritative mix of clinical reviews, education and training updates, quality improvement projects and case reports, and book reviews from recognized leaders in the profession. The Core Training for Doctors section provides clinical information in an easily accessible format for doctors in training. British Journal of Hospital Medicine is an invaluable resource for hospital doctors at all stages of their career. The journal is indexed on Medline, CINAHL, the Sociedad Iberoamericana de Información Científica and Scopus.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信