超声与乳房x光影像融合的深度学习融合模型优化乳腺病变诊断与决策:一项双中心回顾性研究

IF 7.4 1区 医学 Q1 Medicine
Ziting Xu, Shengzhou Zhong, Yang Gao, Jiekun Huo, Weimin Xu, Weijun Huang, Xiaomei Huang, Chifa Zhang, Jianqiao Zhou, Qing Dan, Lian Li, Zhouyue Jiang, Ting Lang, Shuying Xu, Jiayin Lu, Ge Wen, Yu Zhang, Yingjia Li
{"title":"超声与乳房x光影像融合的深度学习融合模型优化乳腺病变诊断与决策:一项双中心回顾性研究","authors":"Ziting Xu, Shengzhou Zhong, Yang Gao, Jiekun Huo, Weimin Xu, Weijun Huang, Xiaomei Huang, Chifa Zhang, Jianqiao Zhou, Qing Dan, Lian Li, Zhouyue Jiang, Ting Lang, Shuying Xu, Jiayin Lu, Ge Wen, Yu Zhang, Yingjia Li","doi":"10.1186/s13058-025-02033-6","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>This study aimed to develop a BI-RADS network (DL-UM) via integrating ultrasound (US) and mammography (MG) images and explore its performance in improving breast lesion diagnosis and management when collaborating with radiologists, particularly in cases with discordant US and MG Breast Imaging Reporting and Data System (BI-RADS) classifications.</p><p><strong>Methods: </strong>We retrospectively collected image data from 1283 women with breast lesions who underwent both US and MG within one month at two medical centres and categorised them into concordant and discordant BI-RADS classification subgroups. We developed a DL-UM network via integrating US and MG images, and DL networks using US (DL-U) or MG (DL-M) alone, respectively. The performance of DL-UM network for breast lesion diagnosis was evaluated using ROC curves and compared to DL-U and DL-M networks in the external testing dataset. The diagnostic performance of radiologists with different levels of experience under the assistance of DL-UM network was also evaluated.</p><p><strong>Results: </strong>In the external testing dataset, DL-UM outperformed DL-M in sensitivity (0.962 vs. 0.833, P = 0.016) and DL-U in specificity (0.667 vs. 0.526, P = 0.030), respectively. In the discordant BI-RADS classification subgroup, DL-UM achieved an AUC of 0.910. The diagnostic performance of four radiologists improved when collaborating with the DL-UM network, with AUCs increased from 0.674-0.772 to 0.889-0.910, specificities from 52.1%-75.0 to 81.3-87.5% and reducing unnecessary biopsies by 16.1%-24.6%, particularly for junior radiologists. Meanwhile, DL-UM outputs and heatmaps enhanced radiologists' trust and improved interobserver agreement between US and MG, with weighted kappa increased from 0.048 to 0.713 (P < 0.05).</p><p><strong>Conclusions: </strong>The DL-UM network, integrating complementary US and MG features, assisted radiologists in improving breast lesion diagnosis and management, potentially reducing unnecessary biopsies.</p>","PeriodicalId":49227,"journal":{"name":"Breast Cancer Research","volume":"27 1","pages":"80"},"PeriodicalIF":7.4000,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12080162/pdf/","citationCount":"0","resultStr":"{\"title\":\"Optimizing breast lesions diagnosis and decision-making with a deep learning fusion model integrating ultrasound and mammography: a dual-center retrospective study.\",\"authors\":\"Ziting Xu, Shengzhou Zhong, Yang Gao, Jiekun Huo, Weimin Xu, Weijun Huang, Xiaomei Huang, Chifa Zhang, Jianqiao Zhou, Qing Dan, Lian Li, Zhouyue Jiang, Ting Lang, Shuying Xu, Jiayin Lu, Ge Wen, Yu Zhang, Yingjia Li\",\"doi\":\"10.1186/s13058-025-02033-6\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>This study aimed to develop a BI-RADS network (DL-UM) via integrating ultrasound (US) and mammography (MG) images and explore its performance in improving breast lesion diagnosis and management when collaborating with radiologists, particularly in cases with discordant US and MG Breast Imaging Reporting and Data System (BI-RADS) classifications.</p><p><strong>Methods: </strong>We retrospectively collected image data from 1283 women with breast lesions who underwent both US and MG within one month at two medical centres and categorised them into concordant and discordant BI-RADS classification subgroups. We developed a DL-UM network via integrating US and MG images, and DL networks using US (DL-U) or MG (DL-M) alone, respectively. The performance of DL-UM network for breast lesion diagnosis was evaluated using ROC curves and compared to DL-U and DL-M networks in the external testing dataset. The diagnostic performance of radiologists with different levels of experience under the assistance of DL-UM network was also evaluated.</p><p><strong>Results: </strong>In the external testing dataset, DL-UM outperformed DL-M in sensitivity (0.962 vs. 0.833, P = 0.016) and DL-U in specificity (0.667 vs. 0.526, P = 0.030), respectively. In the discordant BI-RADS classification subgroup, DL-UM achieved an AUC of 0.910. The diagnostic performance of four radiologists improved when collaborating with the DL-UM network, with AUCs increased from 0.674-0.772 to 0.889-0.910, specificities from 52.1%-75.0 to 81.3-87.5% and reducing unnecessary biopsies by 16.1%-24.6%, particularly for junior radiologists. Meanwhile, DL-UM outputs and heatmaps enhanced radiologists' trust and improved interobserver agreement between US and MG, with weighted kappa increased from 0.048 to 0.713 (P < 0.05).</p><p><strong>Conclusions: </strong>The DL-UM network, integrating complementary US and MG features, assisted radiologists in improving breast lesion diagnosis and management, potentially reducing unnecessary biopsies.</p>\",\"PeriodicalId\":49227,\"journal\":{\"name\":\"Breast Cancer Research\",\"volume\":\"27 1\",\"pages\":\"80\"},\"PeriodicalIF\":7.4000,\"publicationDate\":\"2025-05-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12080162/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Breast Cancer Research\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1186/s13058-025-02033-6\",\"RegionNum\":1,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"Medicine\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Breast Cancer Research","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s13058-025-02033-6","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"Medicine","Score":null,"Total":0}
引用次数: 0

摘要

背景:本研究旨在通过整合超声(US)和乳腺x线摄影(MG)图像来建立BI-RADS网络(DL-UM),并探讨其在与放射科医生合作时改善乳腺病变诊断和管理方面的作用,特别是在超声和MG乳腺成像报告和数据系统(BI-RADS)分类不一致的情况下。方法:我们回顾性收集了1283名在两个医疗中心一个月内接受过US和MG治疗的乳腺病变妇女的图像资料,并将其分为一致性和不一致性BI-RADS分类亚组。我们通过整合US和MG图像开发了DL- um网络,并分别单独使用US (DL- u)或MG (DL- m)开发了DL- um网络。使用ROC曲线评估DL-UM网络对乳腺病变诊断的性能,并与外部测试数据集中的DL-U和DL-M网络进行比较。在DL-UM网络的帮助下,不同经验水平的放射科医生的诊断表现也进行了评估。结果:在外部测试数据集中,DL-UM在灵敏度上优于DL-M(0.962比0.833,P = 0.016),在特异性上优于DL-U(0.667比0.526,P = 0.030)。在不一致的BI-RADS分类亚组中,DL-UM的AUC为0.910。与DL-UM网络合作后,四名放射科医生的诊断性能得到了提高,auc从0.674-0.772增加到0.889-0.910,特异性从52.1%- 75.0%增加到81.3-87.5%,减少了16.1%-24.6%的不必要的活检,特别是对于初级放射科医生。同时,DL-UM输出和热图增强了放射科医生的信任,并改善了美国和MG之间的观察者之间的一致性,加权kappa从0.048增加到0.713 (P)。结论:DL-UM网络整合了互补的美国和MG特征,帮助放射科医生改善乳房病变的诊断和管理,可能减少不必要的活检。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Optimizing breast lesions diagnosis and decision-making with a deep learning fusion model integrating ultrasound and mammography: a dual-center retrospective study.

Background: This study aimed to develop a BI-RADS network (DL-UM) via integrating ultrasound (US) and mammography (MG) images and explore its performance in improving breast lesion diagnosis and management when collaborating with radiologists, particularly in cases with discordant US and MG Breast Imaging Reporting and Data System (BI-RADS) classifications.

Methods: We retrospectively collected image data from 1283 women with breast lesions who underwent both US and MG within one month at two medical centres and categorised them into concordant and discordant BI-RADS classification subgroups. We developed a DL-UM network via integrating US and MG images, and DL networks using US (DL-U) or MG (DL-M) alone, respectively. The performance of DL-UM network for breast lesion diagnosis was evaluated using ROC curves and compared to DL-U and DL-M networks in the external testing dataset. The diagnostic performance of radiologists with different levels of experience under the assistance of DL-UM network was also evaluated.

Results: In the external testing dataset, DL-UM outperformed DL-M in sensitivity (0.962 vs. 0.833, P = 0.016) and DL-U in specificity (0.667 vs. 0.526, P = 0.030), respectively. In the discordant BI-RADS classification subgroup, DL-UM achieved an AUC of 0.910. The diagnostic performance of four radiologists improved when collaborating with the DL-UM network, with AUCs increased from 0.674-0.772 to 0.889-0.910, specificities from 52.1%-75.0 to 81.3-87.5% and reducing unnecessary biopsies by 16.1%-24.6%, particularly for junior radiologists. Meanwhile, DL-UM outputs and heatmaps enhanced radiologists' trust and improved interobserver agreement between US and MG, with weighted kappa increased from 0.048 to 0.713 (P < 0.05).

Conclusions: The DL-UM network, integrating complementary US and MG features, assisted radiologists in improving breast lesion diagnosis and management, potentially reducing unnecessary biopsies.

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
CiteScore
12.00
自引率
0.00%
发文量
76
审稿时长
12 weeks
期刊介绍: Breast Cancer Research, an international, peer-reviewed online journal, publishes original research, reviews, editorials, and reports. It features open-access research articles of exceptional interest across all areas of biology and medicine relevant to breast cancer. This includes normal mammary gland biology, with a special emphasis on the genetic, biochemical, and cellular basis of breast cancer. In addition to basic research, the journal covers preclinical, translational, and clinical studies with a biological basis, including Phase I and Phase II trials.
×
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:481959085
Book学术官方微信