Impact of artificial intelligence in breast cancer screening with mammography.

IF 2.9
Breast cancer (Tokyo, Japan) Pub Date : 2022-11-01 Epub Date: 2022-06-28 DOI:10.1007/s12282-022-01375-9
Lan-Anh Dang, Emmanuel Chazard, Edouard Poncelet, Teodora Serb, Aniela Rusu, Xavier Pauwels, Clémence Parsy, Thibault Poclet, Hugo Cauliez, Constance Engelaere, Guillaume Ramette, Charlotte Brienne, Sofiane Dujardin, Nicolas Laurent
{"title":"Impact of artificial intelligence in breast cancer screening with mammography.","authors":"Lan-Anh Dang,&nbsp;Emmanuel Chazard,&nbsp;Edouard Poncelet,&nbsp;Teodora Serb,&nbsp;Aniela Rusu,&nbsp;Xavier Pauwels,&nbsp;Clémence Parsy,&nbsp;Thibault Poclet,&nbsp;Hugo Cauliez,&nbsp;Constance Engelaere,&nbsp;Guillaume Ramette,&nbsp;Charlotte Brienne,&nbsp;Sofiane Dujardin,&nbsp;Nicolas Laurent","doi":"10.1007/s12282-022-01375-9","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>To demonstrate that radiologists, with the help of artificial intelligence (AI), are able to better classify screening mammograms into the correct breast imaging reporting and data system (BI-RADS) category, and as a secondary objective, to explore the impact of AI on cancer detection and mammogram interpretation time.</p><p><strong>Methods: </strong>A multi-reader, multi-case study with cross-over design, was performed, including 314 mammograms. Twelve radiologists interpreted the examinations in two sessions delayed by a 4 weeks wash-out period with and without AI support. For each breast of each mammogram, they had to mark the most suspicious lesion (if any) and assign it with a forced BI-RADS category and a level of suspicion or \"continuous BI-RADS 100\". Cohen's kappa correlation coefficient evaluating the inter-observer agreement for BI-RADS category per breast, and the area under the receiver operating characteristic curve (AUC), were used as metrics and analyzed.</p><p><strong>Results: </strong>On average, the quadratic kappa coefficient increased significantly when using AI for all readers [κ = 0.549, 95% CI (0.528-0.571) without AI and κ = 0.626, 95% CI (0.607-0.6455) with AI]. AUC was significantly improved when using AI (0.74 vs 0.77, p = 0.004). Reading time was not significantly affected for all readers (106 s without AI and vs 102 s with AI; p = 0.754).</p><p><strong>Conclusions: </strong>When using AI, radiologists were able to better assign mammograms with the correct BI-RADS category without slowing down the interpretation time.</p>","PeriodicalId":520574,"journal":{"name":"Breast cancer (Tokyo, Japan)","volume":" ","pages":"967-977"},"PeriodicalIF":2.9000,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9587927/pdf/","citationCount":"9","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Breast cancer (Tokyo, Japan)","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s12282-022-01375-9","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2022/6/28 0:00:00","PubModel":"Epub","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 9

Abstract

Objectives: To demonstrate that radiologists, with the help of artificial intelligence (AI), are able to better classify screening mammograms into the correct breast imaging reporting and data system (BI-RADS) category, and as a secondary objective, to explore the impact of AI on cancer detection and mammogram interpretation time.

Methods: A multi-reader, multi-case study with cross-over design, was performed, including 314 mammograms. Twelve radiologists interpreted the examinations in two sessions delayed by a 4 weeks wash-out period with and without AI support. For each breast of each mammogram, they had to mark the most suspicious lesion (if any) and assign it with a forced BI-RADS category and a level of suspicion or "continuous BI-RADS 100". Cohen's kappa correlation coefficient evaluating the inter-observer agreement for BI-RADS category per breast, and the area under the receiver operating characteristic curve (AUC), were used as metrics and analyzed.

Results: On average, the quadratic kappa coefficient increased significantly when using AI for all readers [κ = 0.549, 95% CI (0.528-0.571) without AI and κ = 0.626, 95% CI (0.607-0.6455) with AI]. AUC was significantly improved when using AI (0.74 vs 0.77, p = 0.004). Reading time was not significantly affected for all readers (106 s without AI and vs 102 s with AI; p = 0.754).

Conclusions: When using AI, radiologists were able to better assign mammograms with the correct BI-RADS category without slowing down the interpretation time.

Abstract Image

Abstract Image

Abstract Image

人工智能对乳腺x光筛查的影响。
目的:证明放射科医生在人工智能(AI)的帮助下,能够更好地将筛查乳房x光片分类到正确的乳房成像报告和数据系统(BI-RADS)类别中,并作为次要目标,探讨AI对癌症检测和乳房x光片解释时间的影响。方法:采用交叉设计的多读者、多病例研究,包括314张乳房x线照片。在有和没有人工智能支持的情况下,12名放射科医生在两次会议中解释了4周的洗脱期。对于每次乳房x光检查的每个乳房,他们必须标记最可疑的病变(如果有的话),并将其分配给强制BI-RADS类别和可疑水平或“连续BI-RADS 100”。以评估每个乳房BI-RADS类别的观察者间一致性的Cohen's kappa相关系数和受试者工作特征曲线下的面积(AUC)作为指标并进行分析。结果:平均而言,使用人工智能时,所有读者的二次卡帕系数显著增加[未使用人工智能时κ = 0.549, 95% CI(0.528-0.571),使用人工智能时κ = 0.626, 95% CI(0.607-0.6455)]。人工智能显著改善了AUC (0.74 vs 0.77, p = 0.004)。所有读者的阅读时间都没有明显的影响(没有人工智能的106秒和有人工智能的102秒;p = 0.754)。结论:当使用人工智能时,放射科医生能够更好地分配具有正确BI-RADS类别的乳房x线照片,而不会减慢解释时间。
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
自引率
0.00%
发文量
0
×
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