[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-406262-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-406262-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","differences-and-similarities-in-false-interpretations-by-ai-cad-and-radiologists-in-screening-mammography","Differences and similarities in false interpretations by AI CAD and radiologists in screening mammography","","Retrospective case–control evidence evaluates how false interpretations differ between artificial intelligence (AI) computer-aided detection and two radiologist readers in screening mammography. Using examinations from a 2008–2015 screening cohort, the study analyzes 714 women diagnosed with breast cancer and 8029 healthy controls, with control oversampling to match cancer proportions. False-positive and false-negative patterns are assessed in single- and double-reader simulations and related to age, breast density, tumor histology, and invasiveness.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/healthcare/","Healthcare",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/differences-and-similarities-in-false-interpretations-by-ai-cad-and-radiologists-in-screening-mammography/406262/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/differences-and-similarities-in-false-interpretations-by-ai-cad-and-radiologists-in-screening-mammography/406262.png","ImageObject",300,407,{"name":42,"@type":43},"Marglet","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-29","2026-09-28",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",10,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What was the main objective of the study?","Question",{"text":63,"@type":64},"To evaluate differences and similarities in false interpretations between AI CAD and radiologists in screening mammography and to understand how diagnostic mistake distributions may change when AI is integrated into screening.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How were false positives and false negatives analyzed?",{"text":68,"@type":64},"False-positive and false-negative assessments by AI, RAD 1, and RAD 2 were examined in both single-reader and double-reader simulation settings, with associations tested against age, density, tumor histology, and invasiveness.",{"name":70,"@type":61,"acceptedAnswer":71},"What did the study conclude about which groups benefited most from AI?",{"text":72,"@type":64},"The most pronounced decrease in false-negative assessments was observed for women over age 55 and for those with high breast density, suggesting a complementary AI role when combined with radiologists to improve sensitivity in these groups.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},406262,1790779373,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,110,115,120,123,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":108,"slug":109},7,40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":112,"show_sort_weight":113,"slug":114},8,"Research & Report",30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":55,"slug":125},"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":107,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":111,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":143,"read_time":118,"preview_page_count":4},2336477982702,"https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc","BJR [https://doi.org/10.1259/bjr.20230210](https://doi.org/10.1259/bjr.20230210)  \n\n| \u003Cbr>Received:\u003Cbr>28 February 2023\u003Cbr>Revised:\u003Cbr>10 July 2023\u003Cbr>Accepted:\u003Cbr>20 July 2023\u003Cbr>© 2023 The Authors. Published by the British Institute of Radiology under the terms of the Creative Commons Attribution-NonCommercial 4.0 Unported License [http://creativecommons.org/l](http://creativecommons.org/l)icenses/by-nc/4 .0/, which permits unrestricted non-commercial reuse, provided the original author and source are credited.\u003Cbr>Cite this article as:\u003Cbr>Salim M, Dembrower K, Eklund M, Smith K, Strand F. Differences and similarities in false interpretations by AI CAD and radiologists in screening mammography. Br J Radiol (2023) 10.1259/bjr.20230210. |  |\n| --- | --- |\n| FULL PAPER\u003Cbr>Differences and similarities in false interpretations by AI CAD and radiologists in screening mammography\u003Cbr>1,2MATTIE SALIM, MD, PhD, 1,3KARIN DEMBROWER, MD, PhD, 4MARTIN EKLUND, PhD, 5KEVIN SMITH, PhD and\u003Cbr>1,2FREDRIK STRAND, MD, PhD\u003Cbr>1Department of Oncology and Pathology, Karolinska Institute, Karolinska University Hospital, Stockholm, Sweden\u003Cbr>2Department of Radiology, Breast Radiology, Karolinska University Hospital, Stockholm, Sweden\u003Cbr>3Department of Radiology, Breast Radiology, Capio Sankt Görans Hospital, Stockholm, Sweden\u003Cbr>4Department of Medical Epidemiology and Biostatistics, Karolinska Institute, Stockholm, Sweden\u003Cbr>5Science for Life Laboratory, KTH Royal Insitute of Technology, Stockholm, Sweden\u003Cbr>Address correspondence to: Dr Mattie Salim\u003Cbr>[E-mail:](E-mail: mattie.salim@ki.se)[ mattie.salim@ki.se](E-mail: mattie.salim@ki.se) |  |\n| Objective: We aimed to evaluate the false interpretations between artificial intelligence (AI) and radiologists in screening mammography to get a better understanding of how the distribution of diagnostic mistakes might change when moving from entirely radiologistdriven to AI-integrated breast cancer screening. Methods and materials: This retrospective case–control study was based on a mammography screening cohort from 2008 to 2015. The final study population included screening examinations for 714 women diagnosed with breast cancer and 8029 randomly selected healthy controls. Oversampling of controls was applied to attain a similar cancer proportion as in the source screening cohort. We examined how false-positive (FP) and falsenegative (FN) assessments by AI, the first reader (RAD 1) and the second reader (RAD 2), were associated with age, density, tumor histology and cancer invasiveness ina single-and double-reader setting.\u003Cbr>Results: For each reader, the FN assessments were distributed between low-and high-density females with 53 (42%) and 72 (58%) for AI; 59 (36%) and 104 (64%) for RAD 1 and 47 (36%) and 84 (64%) for RAD 2. The\u003Cbr>corresponding numbers for FP assessments were 1820 (47%) and 2016 (53%) for AI; 1568 (46%) and 1834 (54%) for RAD 1 and 1190 (43%) and 1610 (58%) for RAD 2. For ductal cancer, the FN assessments were 79 (77%) for AI CAD; with 120 (83%) for RAD 1 and with 96 (16%) for RAD 2. For the double-reading simulation, the FP assessments were distributed between younger and older females with 2828 (2 . 5%) and 1554 (1 .4%) for RAD 1 + RAD 2; 3850 (3 .4%) and 2940 (2 . 6%) for AI+RAD 1 and 3430 (3%) and 2772 (2 . 5%) for AI+RAD 2. Conclusion: The most pronounced decrease in FN assessments was noted for females over the age of 55 and for high density-women. In conclusion, AI could have an important complementary role when combined with radiologists to increase sensitivity for high-density and older females.\u003Cbr>Advances in knowledge: Our results highlight the potential impact of integrating AI in breast cancer screening, particularly to improve interpretation accuracy. The use of AI could enhance screening outcomes for highdensity and older females. |  |\n| INTRODUCTION\u003Cbr>Population-based breast cancer screening is being used in health programs all around the world and was fully implemented ","cbCaibvJTCLHmmuq","https://ap.wps.com/l/cbCaibvJTCLHmmuq","pdf",370590,"English","# Objective\n# Methods and materials\n## Study design and population\n## Reading strategies and error definitions\n# Results\n# Conclusion\n# Advances in knowledge\n# Introduction\n# Methods","[{\"question\":\"What was the main objective of the study?\",\"answer\":\"To evaluate differences and similarities in false interpretations between AI CAD and radiologists in screening mammography and to understand how diagnostic mistake distributions may change when AI is integrated into screening.\"},{\"question\":\"How were false positives and false negatives analyzed?\",\"answer\":\"False-positive and false-negative assessments by AI, RAD 1, and RAD 2 were examined in both single-reader and double-reader simulation settings, with associations tested against age, density, tumor histology, and invasiveness.\"},{\"question\":\"What did the study conclude about which groups benefited most from AI?\",\"answer\":\"The most pronounced decrease in false-negative assessments was observed for women over age 55 and for those with high breast density, suggesting a complementary AI role when combined with radiologists to improve sensitivity in these groups.\"}]","Differences and similarities in false interpretations by AI CAD and radiologists in screening mammography | PDF",1790564530]