[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-340277-105":59,"doc-detail-340277-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","a-multi-model-approach-integrating-whole-slide-imaging-and-clinicopathologic-features-to-predict-breast-cancer-recurrence-risk-build-a-low-risk-and-high-risk-binary-classification","A multi-model approach integrating whole-slide imaging and clinicopathologic features to predict breast cancer recurrence risk - build a low-risk and high-risk binary classification","","Breast cancer shows diverse morphology and biology, leading to different recurrence risks after treatment. Although Oncotype DX Breast Recurrence Score guides therapy in ER+/HER2− disease, it is costly, slow, and not widely accessible. This study develops a multi-model framework combining convolutional neural networks and vision transformers with clinicopathologic logistic regression to predict recurrence risk and split patients into low- and high-risk groups. Trained on 956 whole-slide images and validated on internal and external cohorts, it achieves strong AUC performance.",{"@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/a-multi-model-approach-integrating-whole-slide-imaging-and-clinicopathologic-features-to-predict-breast-cancer-recurrence-risk-build-a-low-risk-and-high-risk-binary-classification/340277/",{"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/a-multi-model-approach-integrating-whole-slide-imaging-and-clinicopathologic-features-to-predict-breast-cancer-recurrence-risk-build-a-low-risk-and-high-risk-binary-classification/340277.png","ImageObject",300,407,{"name":92,"@type":93},"Skyler","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-01","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 clinical problem does the study target?","Question",{"text":112,"@type":113},"It targets the need to predict breast cancer recurrence risk after treatment, especially where Oncotype DX testing is expensive, can delay care, and is not widely available.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the proposed method combine different data sources?",{"text":117,"@type":113},"The approach uses convolutional neural networks for feature extraction from whole-slide images and vision transformers for contextual aggregation, complemented by a logistic regression model analyzing clinicopathologic features for binary risk categorization.",{"name":119,"@type":110,"acceptedAnswer":120},"What dataset and evaluation strategy are used to test the model?",{"text":121,"@type":113},"The model is trained on 956 H&E whole-slide images from 950 ER+/HER2− patients with prior Oncotype DX testing, then evaluated on an internal test set (192 patients) and an external test set (405 patients).",{"name":123,"@type":110,"acceptedAnswer":124},"How accurate is the model compared across cohorts?",{"text":125,"@type":113},"It reports an AUC of 0.91 (95% CI: 0.87–0.95) on the internal set and an AUC of 0.84 (95% CI: 0.78–0.89) on the external cohort for predicting low- and high-recurrence risk categories based on the Oncotype DX recurrence score.","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},340277,1790735779,{"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":44,"language":143,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":144,"faqs":145,"seo_title":146,"seo_description":67,"update_tm":147,"read_time":148,"preview_page_count":19,"preview_urls":149},2336464648746,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","npj | breast cancer Article  \nPublished in partnership with the Breast Cancer Research Foundation  \n[https://doi.org/10.1038/s41523-024-00700-z](https://doi.org/10.1038/s41523-024-00700-z)  \n\n| A multi-model approach integrating whole-slide imaging and clinicopathologic features to predict breast cancer recurrence risk\u003Cbr> Check for updates |  |\n| --- | --- |\n| Manu Goyal 1 , Jonathan D. Marotti2, Adrienne A. Workman 2, Graham M. Tooker3, Seth K. Ramin  Elaine P. Kuhn 4, Mary D. Chamberlin5, Roberta M. diFlorio-Alexander3 & Saeed Hassanpour1,6,7 |  4\u003Cbr>, |\n\nBreast cancer is the most common malignancy affecting women worldwide and is notable for its morphologic and biologic diversity, with varying risks of recurrence following treatment. The Oncotype DX Breast Recurrence Score test is an important predictive and prognostic genomic assay for estrogen receptor positive/HER2 negative breast cancer that guides therapeutic strategies; however, such tests can be expensive, delay care, and are not widely available. The aim of this study was to develop a multi-model approach integrating the analysis of whole-slide images and clinicopathologic data to predict their associated breast cancer recurrence risks and categorize these patients into two risk groups according to the predicted score: low-risk and high-risk. The proposed novel methodology uses convolutional neural networks for feature extraction and vision transformers for contextual aggregation, complemented by a logistic regression model that analyzes clinicopathologic data forclassiﬁcation into two risk categories. This method was trained and tested on 956 hematoxylin and eosin-stained whole-slide images of 950 ER+/HER2 − breast cancer patients with corresponding clinicopathological features that had prior Oncotype DX testing. The model ’s performance was evaluated using an internal test set of 192 patients from Dartmouth Health and an external test set of 405patients from the University of Chicago. The multi-model approach achieved anAUC of0.91(95% CI: 0.87–0.95) on the internal set and an AUC of 0.84 (95% CI: 0.78–0.89) on the external cohort for predicting low-and high-breast cancer recurrence risk categories based on the Oncotype DX recurrence score. With further validation, the proposed methodology could provide an alternative to assist clinicians in personalizing treatment for breast cancer patients and potentially improving their outcomes.  \nBreast cancer remains the leading cause of cancer-related mortality among womenworldwide1. The American Cancer Society estimated approximately 284,200 new cases of breast cancer diagnosed in the United States in 2023, resulting in an estimated 44,130 deaths2. The prognosis and treatment of breast cancer are inﬂuenced by various factors, including age, ethnicity, tumor size, and molecular subtype (i.e., tumor biology)3. The Oncotype DX  \nBreast Recurrence Score test has become a crucial tool for clinical decisionmaking, particularly in hormone receptor (HR) positive/human epidermal growth factor receptor 2 (HER2) negative early-stage breast cancer, which represents about 70% of new cases in the United States4.  \nThe OncotypeDX testis a genomic assaythat assesses the expression of 21genes within a tumor sample to calculate a recurrence score ranging from  \n1Department of Biomedical Data Science, Dartmouth College, Hanover, NH, USA. 2Department of Pathology and Laboratory Medicine, Dartmouth Health, Lebanon, NH, USA. 3Department of Radiology, Dartmouth Health, Lebanon, NH, USA. 4Geisel School of Medicine, Dartmouth College,  \nHanover, NH, USA. 5Department of Medicine, Dartmouth Health, Lebanon, NH, USA. 6Department of Computer Science, Dartmouth College,  \nHanover, NH, USA. 7Department of Epidemiology, Dartmouth College, Hanover, NH, USA. [e-mail:](e-mail: Manu.Goyal@Dartmouth.edu)[ Manu.Goyal@Dartmouth.edu](e-mail: Manu.Goyal@Dartmouth.edu)  \n0 to 100. The recurrence score categories are typically divided into two groups: (1) Low risk ","cbCaiilxdpNmEP6r","https://ap.wps.com/l/cbCaiilxdpNmEP6r","pdf",1860409,"English","# Study objective and clinical motivation\n# Oncotype DX recurrence score background\n# Proposed multi-model methodology\n## Whole-slide feature extraction with CNNs\n## Contextual aggregation with vision transformers\n## Clinicopathologic logistic regression\n# Training and evaluation cohorts\n## Internal test set\n## External test set\n# Performance results and potential clinical value","[{\"question\":\"What clinical problem does the study target?\",\"answer\":\"It targets the need to predict breast cancer recurrence risk after treatment, especially where Oncotype DX testing is expensive, can delay care, and is not widely available.\"},{\"question\":\"How does the proposed method combine different data sources?\",\"answer\":\"The approach uses convolutional neural networks for feature extraction from whole-slide images and vision transformers for contextual aggregation, complemented by a logistic regression model analyzing clinicopathologic features for binary risk categorization.\"},{\"question\":\"What dataset and evaluation strategy are used to test the model?\",\"answer\":\"The model is trained on 956 H\\u0026E whole-slide images from 950 ER+/HER2− patients with prior Oncotype DX testing, then evaluated on an internal test set (192 patients) and an external test set (405 patients).\"},{\"question\":\"How accurate is the model compared across cohorts?\",\"answer\":\"It reports an AUC of 0.91 (95% CI: 0.87–0.95) on the internal set and an AUC of 0.84 (95% CI: 0.78–0.89) on the external cohort for predicting low- and high-recurrence risk categories based on the Oncotype DX recurrence score.\"}]","A multi-model approach integrating whole-slide imaging and clinicopathologic features to predict breast cancer recurrence risk - build a low-risk and high-risk binary classification | PDF",1790035480,23,[150,154,158,162],{"page_no":8,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/24f2f15aad4ce1e6dec6261e9600e124.webp",983,1305,{"page_no":14,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/367f1cbd0d7e3d499fdbf80691fd5ad1.webp",982,1304,{"page_no":81,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/f2b0f91a9cad5b71dfe438889b1002eb.webp",981,1303,{"page_no":19,"url":163,"width":164,"height":165},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/b4663e155aedccd5f30565ef0c8c46e7.webp",980,1301]