[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-343045-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-343045-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","unsupervised-representation-learning-of-chromatin-images-identifies-changes-in-cell-state-and-tissue-organization-in-dcis","Unsupervised representation learning of chromatin images identifies changes in cell state and tissue organization in DCIS","","Unsupervised representation learning is used on chromatin image tissue microarray data to characterize ductal carcinoma in situ (DCIS). The study analyzes 560 samples from 122 female patients across three disease stages and 11 phenotypic categories, identifying eight morphological cell states and tissue features. Cell-state proportions vary by stage, and tissue-level spatial organization changes across stages, predicting disease stage and phenotypic category. Chromatin imaging is presented as a simple, effective tumor biomarker.",{"@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/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/unsupervised-representation-learning-of-chromatin-images-identifies-changes-in-cell-state-and-tissue-organization-in-dcis/343045/",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/unsupervised-representation-learning-of-chromatin-images-identifies-changes-in-cell-state-and-tissue-organization-in-dcis/343045.png","ImageObject",300,407,{"name":42,"@type":43},"Oliver","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-26","2026-09-22",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",6,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What dataset and scale does the study use for chromatin imaging?","Question",{"text":63,"@type":64},"The work builds a large-scale tissue microarray dataset with chromatin images from 560 samples across 122 female patients, covering three disease stages and 11 phenotypic categories.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How many cell states and tissue features does the method identify?",{"text":68,"@type":64},"The model identifies eight morphological cell states and tissue features that mark DCIS.",{"name":70,"@type":61,"acceptedAnswer":71},"What biological or clinical insights are gained from analyzing spatial organization?",{"text":72,"@type":64},"Tissue-level analysis reveals significant changes in the spatial organization of cell states across disease stages, and these changes are predictive of disease stage and phenotypic category.","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},343045,1790813820,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,105,110,114,119,122,126],{"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":55,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},7,"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"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":111,"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":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":108,"preview_page_count":33,"preview_urls":145},8796095461610,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Article [https://doi.org/10.1038/s41467-024-50285-1](https://doi.org/10.1038/s41467-024-50285-1)  \nUnsupervised representation learning of chromatin images identiﬁes changes in cell state and tissue organization in DCIS  \nReceived: 4 April 2023  \n\n| Accepted: 5 July 2024 |\n| --- |\n| |\n| Check for updates |\n\nXinyi Zhang 1,2, Saradha Venkatachalapathy3,4, Daniel Paysan 3,4, Paulina Schaerer3,4, Claudio Tripodo 5,6, Caroline Uhler 1,2  &  \nG. V. Shivashankar 3,4   \nDuctal carcinoma in situ (DCIS) is a pre-invasive tumor that can progress to invasive breast cancer, a leading cause of cancer death. We generate a largescale tissue microarray dataset of chromatin images, from 560 samples from 122 female patients in 3 disease stages and 11 phenotypic categories. Using representation learning on chromatin images alone, without multiplexed staining or high-throughput sequencing, we identify eight morphological cell states and tissue features marking DCIS. All cell states are observed in all disease stages with different proportions, indicating that cell states enriched in invasive cancer exist in small fractions in normal breast tissue. Tissue-level analysis reveals signiﬁcant changes in the spatial organization of cell states across disease stages, which is predictive of disease stage and phenotypic category. Taken together, we show that chromatin imaging represents a powerful measure of cell state and disease stage of DCIS, providing a simple and effective tumor biomarker.  \nBreast cancer is the most commonly diagnosed cancer (11.7%) and is a leading cause of cancer death (6.9%)1. Ductal carcinoma in situ (DCIS) accounts for about 25% of breast cancer diagnosis2–4. Currently, breastconserving treatment and mastectomy are recommended depending on the extent of DCIS, but there is high variability and disagreement regarding the choice of treatment4,5. In addition, surgery may not always be necessary for DCIS patients: a recent study found no difference in survival rates between patients with low-grade DCIS who received or did not receive surgery4,6. But in the absence of locoregional therapies after the diagnosis of DCIS, the 10-year cumulative incidence rate of invasive cancer is about 15% and the all-cause mortality rate is about 24%7. Thus, it is important to understand the mechanism of DCIS in order to recommend the appropriate treatment without overtreating patients.  \nDCIS is characterized by the abnormal proliferation of luminal cells in the breast ducts. When DCIS progresses into Invasive Ductal  \nCarcinoma (IDC), the cells contained in the ducts inﬁltrate the ductal basement membrane and migrate into the surrounding stroma4,8. The tissue microenvironment surrounding the ducts is known to inﬂuence tumor growth and progression, but if and how DCIS transitions to IDC is less understood9–12. Clinically, the characterization of nuclear morphology is often used for the diagnosis of cancer type and stage, including the assessment of nuclear grade in DCIS13–15. However, DCIS patients often exhibit heterogeneity in nuclear grades, and a previous study found a lack of signiﬁcant association between nuclear grade and DCIS recurrence or the development of IDC16. For example, with the current diagnosis guidelines that include nuclear shape and tissue morphology, it is still difﬁcult to distinguish borderline atypical hyperplasia and low-grade DCIS17,18. An attempt to associate the nuclear grade with more quantitative measurements identiﬁed manually selected image features of cell nuclei from H&E stains that could predict nuclear grade  \n1Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, USA. 2Eric and Wendy Schmidt Center, Broad Institute of MIT and Harvard, Cambridge, USA. 3Department of Health Sciences and Technology, ETH Zurich, Switzerland. 4Laboratory of Nanoscale Biology, Paul Scherrer Institute, Villigen, Switzerland. 5Tumor Immunology Unit, University of Palermo, Palermo, Ita","cbCaihAZ8EOal3xC","https://ap.wps.com/l/cbCaihAZ8EOal3xC","pdf",4639680,16,"English","# Study rationale\n## DCIS progression and clinical uncertainty\n## Limits of current grading and omics approaches\n# Method and dataset\n## Tissue microarray chromatin images\n## Unsupervised representation learning\n# Findings\n## Eight morphological cell states\n## Tissue-level spatial organization changes\n# Implications\n## Chromatin imaging as a biomarker","[{\"question\":\"What dataset and scale does the study use for chromatin imaging?\",\"answer\":\"The work builds a large-scale tissue microarray dataset with chromatin images from 560 samples across 122 female patients, covering three disease stages and 11 phenotypic categories.\"},{\"question\":\"How many cell states and tissue features does the method identify?\",\"answer\":\"The model identifies eight morphological cell states and tissue features that mark DCIS.\"},{\"question\":\"What biological or clinical insights are gained from analyzing spatial organization?\",\"answer\":\"Tissue-level analysis reveals significant changes in the spatial organization of cell states across disease stages, and these changes are predictive of disease stage and phenotypic category.\"}]","Unsupervised representation learning of chromatin images identifies changes in cell state and tissue organization in DCIS | PDF",1790049578,[146,150,154,158],{"page_no":22,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/722c6614c094b3839d03dcff9bb03df1.webp",983,1305,{"page_no":26,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/d481267cef10748832284903fdc063fd.webp",982,1304,{"page_no":30,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/925cf732906f72df9c00dd5985015c2a.webp",981,1303,{"page_no":33,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/1423575a68a9bd518df16907632718e5.webp",980,1301]