[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-331393-105":59,"doc-detail-331393-en":131},{"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":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","deep-learning-artificial-intelligence-predicts-homologous-recombination-deficiency-and-platinum-response-from-histologic-slides","Deep Learning Artificial Intelligence Predicts Homologous Recombination Deficiency and Platinum Response From Histologic Slides","","DeepHRD is a deep learning platform designed to predict homologous recombination deficiency (HRD) directly from routine hematoxylin and eosin (H&E) stained histopathological slides. Training used breast and ovarian cancers from TCGA, then testing compared DeepHRD against four standard molecular HRD assays across independent datasets. In breast cancer, DeepHRD achieved AUCs around 0.76–0.81 and identified HRD tumors linked to improved platinum-specific outcomes and longer progression-free survival. Transfer learning to high-grade serous ovarian cancer further associated predicted HRD with better overall survival after first-line and neoadjuvant platinum therapy.",{"@graph":69,"@context":123},[70,84,106],{"@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-artificial-intelligence-predicts-homologous-recombination-deficiency-and-platinum-response-from-histologic-slides/331393/",{"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-artificial-intelligence-predicts-homologous-recombination-deficiency-and-platinum-response-from-histologic-slides/331393.png","ImageObject",300,407,{"name":92,"@type":93},"Rowan","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-06","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",15,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does the study address regarding HRD testing?","Question",{"text":113,"@type":114},"Standard HRD diagnostics often require molecular profiling, which is not universally available due to tissue and workflow constraints.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does DeepHRD predict HRD?",{"text":118,"@type":114},"DeepHRD uses deep learning to classify HRD directly from images of routine H&E-stained histopathological slides.",{"name":120,"@type":111,"acceptedAnswer":121},"What clinical outcome relationships were reported for predicted HRD?",{"text":122,"@type":114},"In platinum-treated settings, samples predicted as HRD showed improved complete response and longer progression-free survival in metastatic breast cancer cohorts, and better overall survival after platinum therapy in high-grade serous ovarian cancer through transfer learning.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},331393,1790167910,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":41,"preview_page_count":4},1099514067415,"https://ap-avatar.wpscdn.com/avatar/100002539d78ffe74a7?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779092875211072502","Original Reports | Breast Cancer  \nDeep Learning Artificial Intelligence Predicts Homologous Recombination Deficiency and Platinum Response From Histologic Slides  \nErik N. Bergstrom, PhD1,2,3  ; Ammal Abbasi, BS1,2,3  ; Marcos Daz-Gay, PhD1,2,3  ; Lock Galland, PhD4,5,6,7; Sylvain Ladoire, MD4,5,6,7  ; Scott M. Lippman, MD1 ; and Ludmil B. Alexandrov, PhD1,2,3,8   \nDOI [https://doi.org/10.1200/JCO.23.02641](https://doi.org/10.1200/JCO.23.02641)  \n\n| ABSTRACT |  |\n| --- | --- |\n| PURPOSE | Cancers with homologous recombination deficiency (HRD) can benefit from platinum salts and poly(ADP-ribose) polymerase inhibitors. Standard diagnostic tests for detecting HRD require molecular profiling, which is not universally available. |\n| METHODS | We trained DeepHRD, a deep learning platform for predicting HRD from hematoxylin and eosin (H&E)–stained histopathological slides, using primary breast (n 5 1,008) and ovarian (n 5 459) cancers from The Cancer Genome Atlas (TCGA). DeepHRD was compared with four standard HRD molecular tests using breast (n 5 349) and ovarian (n 5 141) cancers from multiple independent datasets, including platinum-treated clinical cohorts with RECIST progression-free survival (PFS), complete response (CR), and overall survival (OS) endpoints. |\n| RESULTS | DeepHRD predicted HRD from held-out H&E-stained breast cancer slides in TCGA with an AUC of 0.81 (95% CI, 0.77 to 0.85) . This performance was confirmed in two independent primary breast cancer cohorts (AUC, 0.76 [95% CI, 0.71 to 0.82]). In an external platinum-treated metastatic breast cancer cohort, samples predicted as HRD had higher complete CR (AUC, 0.76 [95% CI, 0.54 to 0. 93]) with 3 .7-fold increase in median PFS (14 .4 v 3. 9 months; P 5 . 0019) and hazard ratio (HR) of 0.45 (P 5 .0047) . There were no significant differences in nonplatinum treatment outcome by predicted HRD status in three breast cancer cohorts, including CR (AUC, 0.39) and PFS (HR, 0.98, P 5 .95) in taxane-treated metastatic breast cancer. Through transfer learning to high-grade serous ovarian cancer, DeepHRD-predicted HRD samples had better OS after first-line (HR, 0.46; P 5 .030) and neoadjuvant (HR, 0.49; P 5 .015) platinum therapy in two cohorts. |\n| CONCLUSION | DeepHRD can predict HRD in breast and ovarian cancers directly from routine H&E slides across multiple external cohorts, slide scanners, and tissue fixation variables. When compared with molecular testing, DeepHRD classified 1.8-to 3.1-fold more patients with HRD, which exhibited better OS in high-grade serous ovarian cancer and platinum-specific PFS in metastatic breast cancer. |\n\nACCOMPANYING CONTENT  \n Editorial, p. 3513  Data Sharing Statement  \n Data Supplement  \nAccepted May 28, 2024 Published July 31, 2024  \nJ Clin Oncol 42:3550-3560 © 2024 by American Society of Clinical Oncology  \nView Online Article  \nCreative Commons Attribution Non-Commercial No Derivatives 4.0 License  \nINTRODUCTION  \nPrecision oncology aims to optimally select treatment for each patient with cancer by first identifying and subsequently targeting molecular defects in the patient’s tumor.1 Mechanistic studies and clinical trials in breast and ovarian cancers have shown that defective homologous recombination repair confers selective therapeutic vulnerability to platinum salts and poly(ADP-ribose) polymerase (PARP) inhibitors.2 ,3 Traditionally, homologous recombination deficiency (HRD) has been attributed to germline variants,  \nsomatic mutations, or epigenetic dysregulation of BRCA1 and BRCA2 .2 Additionally, defects in other homologous recombination pathway genes (eg, PALB2 and RAD51) have the potential to cause HRD.4,5 Importantly, cancers harboring HRD exhibit characteristic patterns of genomic instability,6 gene expression,7 and somatic mutations.8  \nThe US Food and Drug Administration (FDA) has approved two HRD companion diagnostic (CDx) tests for patients with ovarian and breast cancers.3,9 Myriad myChoice CDx and FoundationOne CDx determine HRD ","cbCaisDULVeJdLer","https://ap.wps.com/l/cbCaisDULVeJdLer","pdf",1205563,12,"English","# Abstract\n## Purpose\n## Methods\n## Results\n## Conclusion\n# Introduction\n# Context\n## Key Objective\n## Knowledge Generated\n## Relevance","[{\"question\":\"What problem does the study address regarding HRD testing?\",\"answer\":\"Standard HRD diagnostics often require molecular profiling, which is not universally available due to tissue and workflow constraints.\"},{\"question\":\"How does DeepHRD predict HRD?\",\"answer\":\"DeepHRD uses deep learning to classify HRD directly from images of routine H\\u0026E-stained histopathological slides.\"},{\"question\":\"What clinical outcome relationships were reported for predicted HRD?\",\"answer\":\"In platinum-treated settings, samples predicted as HRD showed improved complete response and longer progression-free survival in metastatic breast cancer cohorts, and better overall survival after platinum therapy in high-grade serous ovarian cancer through transfer learning.\"}]","Deep Learning Artificial Intelligence Predicts Homologous Recombination Deficiency and Platinum Response From Histologic Slides | PDF",1789993107]