[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-345874-105":59,"doc-detail-345874-en":134},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":127,"head_meta":129,"extra_data":131,"updated_unix":133},105,"en","deep-learning-for-early-breast-cancer-detection-on-contrast-enhanced-breast-mri-a-multicenter-study-research","Deep Learning for Early Breast Cancer Detection on Contrast-Enhanced Breast MRI - A Multicenter Study - Research","","Accurate visual categorization of small enhancing lesions on contrast-enhanced breast MRI remains challenging. This retrospective multicenter study developed a deep learning (DL) model to detect small (≤2 cm) invasive breast cancers using preoperative dynamic contrast-enhanced breast MRI from five hospitals, totaling 1721 women. Enhancing breast masses on early postcontrast T1-weighted images (14,917 cancer and 1,443 benign labeled images) served as ground truth, while three radiologists reviewed subcentimeter (≤1 cm) cancers for evaluation. The model achieved an AUPRC of 0.42 with sensitivity 83.2% and precision 33.2%, but subcentimeter performance was lower than radiologists. With DL assistance, radiologists improved mean precision from 72.9% to 83.2% without a significant sensitivity change, indicating DL as a supportive tool.",{"@graph":69,"@context":126},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/deep-learning-for-early-breast-cancer-detection-on-contrast-enhanced-breast-mri-a-multicenter-study-research/345874/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/deep-learning-for-early-breast-cancer-detection-on-contrast-enhanced-breast-mri-a-multicenter-study-research/345874.png","ImageObject",300,407,{"name":92,"@type":93},"Quinn","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-03","2026-09-22",true,{"@type":102,"interactionType":103,"userInteractionCount":39},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118,122],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the study address in contrast-enhanced breast MRI?","Question",{"text":112,"@type":113},"The study targets the difficulty of accurately visualizing and categorizing small enhancing lesions on contrast-enhanced breast MRI, especially for early detection of invasive breast cancers.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How was the DL model trained and validated in this multicenter study?",{"text":117,"@type":113},"It was trained on labeled enhancing breast masses from five hospitals (14,917 cancer and 1,443 benign images), with datasets split into training and validation, and additional hospitals used for an independent test set.",{"name":119,"@type":110,"acceptedAnswer":120},"How did the model perform for small and subcentimeter invasive breast cancers?",{"text":121,"@type":113},"For small (≤2 cm) enhancing masses, the DL model achieved AUPRC 0.42 with sensitivity 83.2% and precision 33.2%. For subcentimeter (≤1 cm) cancers, sensitivity and precision were lower than radiologists.",{"name":123,"@type":110,"acceptedAnswer":124},"Did the DL model help radiologists improve detection performance?",{"text":125,"@type":113},"With DL model assistance, radiologists’ mean precision for subcentimeter invasive breast cancers increased from 72.9% to 83.2%, while sensitivity did not change significantly (89.5% vs. 86.8%).","https://schema.org",{"og:url":83,"og:type":128,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":130,"canonical":83},"index,follow",{"doc_id":132,"site_id":62},345874,1790194060,{"code":4,"msg":5,"data":135},{"doc_id":132,"user_id":136,"nickname":92,"user_avatar":137,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":138,"file_id":139,"file_url":140,"file_type":141,"file_size":142,"view_count":39,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":143,"language":144,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":145,"faqs":146,"seo_title":147,"seo_description":67,"update_tm":148,"read_time":41,"preview_page_count":14,"preview_urls":149},962075114765,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","Article  \nDeep Learning for Early Breast Cancer Detection on Contrast-Enhanced Breast MRI: A Multicenter Study  \nNa Young Jung 1,†, Jihe Lim 2,†, Hyug-Gi Kim 3, Sung Hun Kim 4, Bobae Choi 5, Bo La Yun 6, Ga Eun Park 4, Jang-Hoon Oh 3, Bo Kyoung Seo 7,8 and Min Sun Bae 7,8, *  \nAcademic Editor: Saed Moradi  \nReceived: 7 June 2026  \nRevised: 7 July 2026  \nAccepted: 9 July 2026  \nPublished: 11 July 2026  \nCopyright: © 2026 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.  \n1 Department of Radiology, Eunpyeong St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul 03312, Republic of Korea; [nyjung1230@gmail.com](nyjung1230@gmail.com)  \n2 Department of Radiology, Hallym University Dongtan Sacred Heart Hospital, Hwaseong 18450, Republic of Korea; [itscindy21@hotmail.com](itscindy21@hotmail.com)  \n3 Department of Radiology, Kyung Hee University Hospital, Seoul 02447, Republic of Korea; [khyukgi@gmail.com](khyukgi@gmail.com) (H.-G.K.); [roineri5@gmail.com](roineri5@gmail.com) (J.-H.O.)  \n4 Department of Radiology, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, Seoul 06591, Republic of Korea; [rad-ksh@catholic.ac.kr](rad-ksh@catholic.ac.kr) (S.H.K.); [hoonhoony@naver.com](hoonhoony@naver.com) (G.E.P.)  \n5 Department of Radiology, Chungnam National University Hospital, Daejeon 35015, Republic of Korea; [med20@hanmail.net](med20@hanmail.net)  \n6 Department of Radiology, Seoul National University Bundang Hospital, Seongnam 13620, Republic of Korea; [yunbola@gmail.com](yunbola@gmail.com)  \n7 Department of Radiology, Korea University Ansan Hospital, Ansan 15355, Republic of Korea; [seoboky@korea.ac.kr](seoboky@korea.ac.kr)  \n8 Department of Radiology, Korea University College of Medicine, Seoul 02841, Republic of Korea  \n* [Correspondence: minsunb@gmail.com](Correspondence: minsunb@gmail.com)  \n† These authors have equally contributed to this work and share first authorship.  \nSimple Summary  \nFew studies have specifically evaluated artificial intelligence (AI) for detecting small invasive breast cancers on contrast-enhanced breast MRI. In this study, we included 1721 patients with single-site invasive breast cancer who underwent preoperative breast MRI. Datasets from three hospitals were randomly split into training (n = 1300, 76%) and validation (n = 91, 5%) sets, and datasets from two additional hospitals were used as an independent test set (n = 330, 19%) . In addition, a reader study was performed using subcentimeter (≤1 cm) invasive breast cancers in the test set (n = 76) . For subcentimeter (≤ 1 cm) invasive breast cancers presenting as enhancing masses on MRI, the deep learning (DL)-based detection model showed lower performance than breast imaging radiologists. With DL model assistance, radiologists achieved higher mean precision in detecting subcentimeter breast cancers, with no significant change in sensitivity.  \nAbstract  \nBackground/Objectives: Accurate visual categorization of small enhancing lesions on contrast-enhanced breast MRI remains challenging. The purpose of this study was to develop a deep learning (DL) model for detecting small (≤2 cm) invasive breast cancers using multi-institutional breast MRI data. Methods: This retrospective study included a total of 1721 women (mean age: 54 years; range, 21–87 years) with T1-stage invasive breast cancer across five hospitals. All patients underwent dynamic contrast-enhanced breast MRI before surgery between 2010 and 2020 . Enhancing breast masses on early postcontrast T1-weighted images (14,917 labeled cancer images and 1443 labeled benign images) were used as the ground truth. In this multicenter cancer-enriched cohort, a DL model was developed to distinguish cancerous lesions from noncancerous lesions. MR images were independently reviewed by three breast imaging radiologists to ","cbCail6IdQnU2rjJ","https://ap.wps.com/l/cbCail6IdQnU2rjJ","pdf",1044099,12,"English","# Simple Summary\n# Abstract\n# 1. Introduction\n## Breast MRI screening benefits and limitations","[{\"question\":\"What problem does the study address in contrast-enhanced breast MRI?\",\"answer\":\"The study targets the difficulty of accurately visualizing and categorizing small enhancing lesions on contrast-enhanced breast MRI, especially for early detection of invasive breast cancers.\"},{\"question\":\"How was the DL model trained and validated in this multicenter study?\",\"answer\":\"It was trained on labeled enhancing breast masses from five hospitals (14,917 cancer and 1,443 benign images), with datasets split into training and validation, and additional hospitals used for an independent test set.\"},{\"question\":\"How did the model perform for small and subcentimeter invasive breast cancers?\",\"answer\":\"For small (≤2 cm) enhancing masses, the DL model achieved AUPRC 0.42 with sensitivity 83.2% and precision 33.2%. For subcentimeter (≤1 cm) cancers, sensitivity and precision were lower than radiologists.\"},{\"question\":\"Did the DL model help radiologists improve detection performance?\",\"answer\":\"With DL model assistance, radiologists’ mean precision for subcentimeter invasive breast cancers increased from 72.9% to 83.2%, while sensitivity did not change significantly (89.5% vs. 86.8%).\"}]","Deep Learning for Early Breast Cancer Detection on Contrast-Enhanced Breast MRI - A Multicenter Study - Research | PDF",1790059206,[150,154],{"page_no":8,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-08/7a2367cc4a7a70068d8ddf0144c6555c.webp",983,1390,{"page_no":14,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-08/3a05869f7da65a07620761bbeb2345c1.webp",982,1388]