Predicting Very Early-Stage Breast Cancer in BI-RADS 3 Lesions of Large Population with Deep Learning.

IF 2.7 Q3 IMAGING SCIENCE & PHOTOGRAPHIC TECHNOLOGY
Congyu Wang, Changzhen Li, Gengxiao Lin
{"title":"Predicting Very Early-Stage Breast Cancer in BI-RADS 3 Lesions of Large Population with Deep Learning.","authors":"Congyu Wang, Changzhen Li, Gengxiao Lin","doi":"10.3390/jimaging11070240","DOIUrl":null,"url":null,"abstract":"<p><p>Breast cancer accounts for one in four new malignant tumors in women, and misdiagnosis can lead to severe consequences, including delayed treatment. Among patients classified with a BI-RADS 3 rating, the risk of very early-stage malignancy remains over 2%. However, due to the benign imaging characteristics of these lesions, radiologists often recommend follow-up rather than immediate biopsy, potentially missing critical early interventions. This study aims to develop a deep learning (DL) model to accurately identify very early-stage malignancies in BI-RADS 3 lesions using ultrasound (US) images, thereby improving diagnostic precision and clinical decision-making. A total of 852 lesions (256 malignant and 596 benign) from 685 patients who underwent biopsies or 3-year follow-up were collected by Southwest Hospital (SW) and Tangshan People's Hospital (TS) to develop and validate a deep learning model based on a novel transfer learning method. To further evaluate the performance of the model, six radiologists independently reviewed the external testing set on a web-based rating platform. The proposed model achieved an area under the receiver operating characteristic curve (AUC), sensitivity, and specificity of 0.880, 0.786, and 0.833 in predicting BI-RADS 3 malignant lesions in the internal testing set. The proposed transfer learning method improves the clinical AUC of predicting BI-RADS 3 malignancy from 0.721 to 0.880. In the external testing set, the model achieved AUC, sensitivity, and specificity of 0.910, 0.875, and 0.786 and outperformed the radiologists with an average AUC of 0.653 (<i>p</i> = 0.021). The DL model could detect very early-stage malignancy of BI-RADS 3 lesions in US images and had higher diagnostic capability compared with experienced radiologists.</p>","PeriodicalId":37035,"journal":{"name":"Journal of Imaging","volume":"11 7","pages":""},"PeriodicalIF":2.7000,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12296032/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Imaging","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/jimaging11070240","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"IMAGING SCIENCE & PHOTOGRAPHIC TECHNOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Breast cancer accounts for one in four new malignant tumors in women, and misdiagnosis can lead to severe consequences, including delayed treatment. Among patients classified with a BI-RADS 3 rating, the risk of very early-stage malignancy remains over 2%. However, due to the benign imaging characteristics of these lesions, radiologists often recommend follow-up rather than immediate biopsy, potentially missing critical early interventions. This study aims to develop a deep learning (DL) model to accurately identify very early-stage malignancies in BI-RADS 3 lesions using ultrasound (US) images, thereby improving diagnostic precision and clinical decision-making. A total of 852 lesions (256 malignant and 596 benign) from 685 patients who underwent biopsies or 3-year follow-up were collected by Southwest Hospital (SW) and Tangshan People's Hospital (TS) to develop and validate a deep learning model based on a novel transfer learning method. To further evaluate the performance of the model, six radiologists independently reviewed the external testing set on a web-based rating platform. The proposed model achieved an area under the receiver operating characteristic curve (AUC), sensitivity, and specificity of 0.880, 0.786, and 0.833 in predicting BI-RADS 3 malignant lesions in the internal testing set. The proposed transfer learning method improves the clinical AUC of predicting BI-RADS 3 malignancy from 0.721 to 0.880. In the external testing set, the model achieved AUC, sensitivity, and specificity of 0.910, 0.875, and 0.786 and outperformed the radiologists with an average AUC of 0.653 (p = 0.021). The DL model could detect very early-stage malignancy of BI-RADS 3 lesions in US images and had higher diagnostic capability compared with experienced radiologists.

深度学习预测大人群BI-RADS 3病变的极早期乳腺癌。
乳腺癌占女性新发恶性肿瘤的四分之一,误诊可能导致严重后果,包括延误治疗。在BI-RADS评分为3级的患者中,极早期恶性肿瘤的风险仍超过2%。然而,由于这些病变的良性影像学特征,放射科医生通常建议随访而不是立即活检,这可能会错过关键的早期干预措施。本研究旨在开发一种深度学习(DL)模型,利用超声(US)图像准确识别BI-RADS 3病变的极早期恶性肿瘤,从而提高诊断精度和临床决策。西南医院(SW)和唐山市人民医院(TS)收集了685例活检或3年随访的患者的852个病变(恶性256个,良性596个),开发并验证了基于新型迁移学习方法的深度学习模型。为了进一步评估模型的性能,六位放射科医生在一个基于网络的评分平台上独立审查了外部测试集。该模型在预测BI-RADS 3恶性病变的内测集中,受试者工作特征曲线下面积(AUC)、灵敏度和特异性分别为0.880、0.786和0.833。提出的迁移学习方法将BI-RADS 3恶性肿瘤的临床AUC从0.721提高到0.880。在外部测试集中,该模型的AUC、灵敏度和特异性分别为0.910、0.875和0.786,优于放射科医师的平均AUC为0.653 (p = 0.021)。与经验丰富的放射科医师相比,DL模型可以在超声图像中检测出BI-RADS 3病变的早期恶性肿瘤,具有更高的诊断能力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Journal of Imaging
Journal of Imaging Medicine-Radiology, Nuclear Medicine and Imaging
CiteScore
5.90
自引率
6.20%
发文量
303
审稿时长
7 weeks
×
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