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, 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","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.