[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-349472-105":59,"doc-detail-349472-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","development-and-validation-of-an-mri-based-deep-learning-system-for-triple-class-er-expression-classification-in-breast-cancer-a-large-scale-multicenter-study","Development and validation of an MRI-based deep learning system for triple-class ER expression classification in breast cancer - a large-scale multicenter study","","Estrogen receptor (ER) expression guides prognosis and endocrine therapy decisions in breast cancer, yet ER-low positive (1%–10%) disease remains biologically distinct with uncertain treatment response. To address invasive limitations of ER assessment, a non-invasive MRI-based deep learning system (BERC) was developed and validated to classify ER-negative, ER-low positive, and ER-high positive tumors using multicenter DCE-MRI data. A diagnostic evaluation quantified AUC, sensitivity, specificity, accuracy, PPV, and NPV, with interpretability assessed via t-SNE/UMAP and SHAP. ",{"@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":35,"@type":76,"position":81},"https://docshare.wps.com/document/healthcare/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/development-and-validation-of-an-mri-based-deep-learning-system-for-triple-class-er-expression-classification-in-breast-cancer-a-large-scale-multicenter-study/349472/",{"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/development-and-validation-of-an-mri-based-deep-learning-system-for-triple-class-er-expression-classification-in-breast-cancer-a-large-scale-multicenter-study/349472.png","ImageObject",300,407,{"name":92,"@type":93},"Anna Hans","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-22","2026-09-22",true,{"@type":102,"interactionType":103,"userInteractionCount":52},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118,122],{"name":109,"@type":110,"acceptedAnswer":111},"What clinical problem does the study address?","Question",{"text":112,"@type":113},"The study addresses the need for non-invasive classification of estrogen receptor (ER) status, especially the biologically distinct ER-low positive group with unclear endocrine therapy response.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How was the MRI-based model (BERC) developed and validated?",{"text":117,"@type":113},"BERC was developed using retrospectively analyzed pretreatment DCE-MRI data from 3500 breast cancer patients across six institutions, with tumor segmentation on DCE T1-weighted images using an automated deep learning algorithm and performance evaluation by AUC and related metrics.",{"name":119,"@type":110,"acceptedAnswer":120},"What results did the model achieve across training and testing sets?",{"text":121,"@type":113},"The model reached Micro-/Macro-average AUCs of 0.918/0.882 in training and 0.923/0.900 in internal validation, with external testing showing Micro-average AUCs from 0.828 to 0.923 and Macro-average AUCs from 0.825 to 0.905 across four centers.",{"name":123,"@type":110,"acceptedAnswer":124},"How was model interpretability assessed?",{"text":125,"@type":113},"Model interpretability was evaluated using t-SNE and UMAP for feature visualization, and SHAP analysis to interpret key predictive features.","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},349472,1790102391,{"code":4,"msg":5,"data":135},{"doc_id":132,"user_id":136,"nickname":92,"user_avatar":137,"doc_module":4,"category_id":34,"category_name":35,"doc_title":65,"doc_description":67,"doc_content":138,"file_id":139,"file_url":140,"file_type":141,"file_size":142,"view_count":52,"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":149},5909892332657,"https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d","Dai etal. BMC Medicine (2026) 24:396 BMC Medicine  \n[https://doi.org/10.1186/s12916-026-04912-x](https://doi.org/10.1186/s12916-026-04912-x)  \nRESEARCH Open Access  \nDevelopment and validation of an MRIbased deep learning system for triple-class ER expression classification in breast cancer: a large-scale multicenter study  \nYi Dai1†, Chinting Wong2,3†, Siyao Du4†, Zeyan Xu5†, Zhitao Wei2,3, Yanting Liang2,3, Chu Han2,3, Chun Lian 1, Dilinuer Aishanjiang1, Meiying Chen1, Rong Huang1, Jinrong Qu6, Lina Zhang7, Guanxun Cheng1, Xiang Zhang8*, Ying Wang9*, Zaiyi Liu2,3* and Zhenwei Shi2,3*  \nAbstract  \nBackground Estrogen receptor (ER) expression is a key prognostic and predictive marker in breast cancer. The 2020 ASCO/CAP guidelines classify tumors with ≥ 1% ER-positive nuclei as ER-positive, yet ER-low positive (1%–10%) breast cancer remains biologically distinct with an unclear response to endocrine therapy (ET) . Given the limitations of invasive ER assessment, we developed and validated an MRI-based deep learning system (BERC) for non-invasive classification of ER negative, ER-low positive, and ER-high positive breast cancer using multicenter data.  \nMethods This diagnostic study retrospectively analyzed pretreatment DCE-MRI data from 3500 breast cancer patients across six institutions (February 2016–August 2023) . Patients were categorized into ER negative, ER-low positive, and ER-high positive groups based on pathology. Tumor segmentation on DCET1-weighted images was performed using an automated deep learning algorithm. A DCE-MRI-based model was developed and evaluated for classification performance using the area under the receiver operating characteristic curve (AUC), along with sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) with 95%  \n\n| †These authors jointly supervised this work: Zhenwei Shi, Zaiyi Liu, Ying Wang and Xiang Zhang. |\n| --- |\n| †Chinting Wong, Siyao Du, Yi Dai and Zeyan Xu contributed equally to this work. |\n\n*Correspondence:  \nXiang Zhang [zhangx345@mail.sysu.edu.cn](zhangx345@mail.sysu.edu.cn)[ ](zhangx345@mail.sysu.edu.cn)Ying Wang [liuivy527@163.com](liuivy527@163.com)  \nZaiyi Liu  \n[liuzaiyi@gdph.org.cn](liuzaiyi@gdph.org.cn)[ ](liuzaiyi@gdph.org.cn)Zhenwei Shi [shizhenwei@gdph.org.cn](shizhenwei@gdph.org.cn)  \nFull list of author information is available at the end of the article  \nBackground  \nEstrogen receptor (ER) expression is prevalent in most invasive breast cancers, playing a pivotal role as a predictive and prognostic marker [1]. The 2020 American Society of Clinical Oncology/College of American Pathology (ASCO/CAP) guidelines define ER-positive breast cancer as specimens with 1% or greater tumor nuclei positivity for ER expression via validated immunohistochemistry (IHC) [2]. This threshold aids in identifying patients who are eligible for endocrine therapy (ET), while those with ER-negative tumors are more likely to benefit from chemotherapy and typically have a less favorable prognosis [3]. However, approximately 3% to 9% of breast cancer  \n© The Author(s) 2026. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain","cbCaiq8gdAKiht7s","https://ap.wps.com/l/cbCaiq8gdAKiht7s","pdf",5192299,14,"English","# Abstract\n## Background\n## Methods\n## Results\n## Conclusions\n## Keywords","[{\"question\":\"What clinical problem does the study address?\",\"answer\":\"The study addresses the need for non-invasive classification of estrogen receptor (ER) status, especially the biologically distinct ER-low positive group with unclear endocrine therapy response.\"},{\"question\":\"How was the MRI-based model (BERC) developed and validated?\",\"answer\":\"BERC was developed using retrospectively analyzed pretreatment DCE-MRI data from 3500 breast cancer patients across six institutions, with tumor segmentation on DCE T1-weighted images using an automated deep learning algorithm and performance evaluation by AUC and related metrics.\"},{\"question\":\"What results did the model achieve across training and testing sets?\",\"answer\":\"The model reached Micro-/Macro-average AUCs of 0.918/0.882 in training and 0.923/0.900 in internal validation, with external testing showing Micro-average AUCs from 0.828 to 0.923 and Macro-average AUCs from 0.825 to 0.905 across four centers.\"},{\"question\":\"How was model interpretability assessed?\",\"answer\":\"Model interpretability was evaluated using t-SNE and UMAP for feature visualization, and SHAP analysis to interpret key predictive features.\"}]","Development and validation of an MRI-based deep learning system for triple-class ER expression classification in breast cancer - a large-scale multicenter study | PDF",1790083475,35]