[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-339797-105":59,"doc-detail-339797-en":130},{"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":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","latent-diffusion-models-with-image-derived-annotations-for-enhanced-ai-assisted-cancer-diagnosis-in-histopathology-339797","Latent Diffusion Models with Image-Derived Annotations for Enhanced AI-Assisted Cancer Diagnosis in Histopathology","","Artificial intelligence image analysis can support diagnostic histopathology, yet supervised approaches require large annotated datasets. This work proposes a method to build structured text prompts from automatically extracted image features for latent diffusion models, addressing the common lack of detailed textual descriptions. Experiments use the PCam dataset with weak tissue annotations for healthy versus cancerous patches, improving FID by 88.6 when image-derived features are included. The study also evaluates detectability by pathologists and shows synthetic data trains AI models effectively.",{"@graph":69,"@context":122},[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/latent-diffusion-models-with-image-derived-annotations-for-enhanced-ai-assisted-cancer-diagnosis-in-histopathology-339797/339797/",{"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/latent-diffusion-models-with-image-derived-annotations-for-enhanced-ai-assisted-cancer-diagnosis-in-histopathology-339797/339797.png","ImageObject",300,407,{"name":92,"@type":93},"Noah","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-22","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":19},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why are annotated datasets important for AI-assisted histopathology diagnosis?","Question",{"text":112,"@type":113},"Supervised AI methods require large-scale annotated datasets to learn diagnostic patterns reliably in histopathology tasks.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the proposed method generate prompts for latent diffusion models?",{"text":117,"@type":113},"It constructs structured textual prompts from automatically extracted image features, instead of relying on detailed textual descriptions that are often unavailable in this domain.",{"name":119,"@type":110,"acceptedAnswer":120},"What effects did image-derived features have on synthetic image quality and evaluation?",{"text":121,"@type":113},"Including image-derived features in the prompt improved Fréchet Inception Distance (FID) by 88.6, and pathologists showed difficulty detecting synthetic images, with median sensitivity/specificity of 0.55/0.55.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},339797,1790650044,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":34,"category_name":35,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":19,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":26},8796095462418,"https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780","diagnostics  \nArticle  \nLatent Diffusion Models with Image-Derived Annotations for Enhanced AI-Assisted Cancer Diagnosis in Histopathology  \nPedro Osorio 1, *, Guillermo Jimenez-Perez 1, Javier Montalt-Tordera 1 , Jens Hooge 1, Guillem Duran-Ballester 1, Shivam Singh 1, Moritz Radbruch 2, Ute Bach 2, Sabrina Schroeder 2, Krystyna Siudak 2, Julia Vienenkoetter 2, Bettina Lawrenz 2 and Sadegh Mohammadi 1  \nCitation: Osorio, P.; Jimenez-Perez, G.; Montalt-Tordera, J.; Hooge, J.;  \nDuran-Ballester, G.; Singh, S.;  \nRadbruch, M.; Bach, U.; Schroeder, S.; Siudak, K.; et al. Latent Diffusion Models with Image-Derived Annotations for Enhanced  \nAI-Assisted Cancer Diagnosis in Histopathology. Diagnostics 2024, 14, 1442. [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)diagnostics14131442  \nAcademic Editor: Francesca Sanguedolce  \nReceived: 3 May 2024  \nRevised: 19 June 2024  \nAccepted: 26 June 2024  \nPublished: 5 July 2024  \nCopyright: © 2024 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 ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) .  \n1 Decision Science & Advanced Analytics, Bayer AG, 13353 Berlin, Germany; [guillermo.jimenezperez@bayer.com](guillermo.jimenezperez@bayer.com) (G.J.-P.); [javier.montalttordera@bayer.com](javier.montalttordera@bayer.com) (J.M.-T.); [jens.hooge@bayer.com](jens.hooge@bayer.com) (J.H.); [guillem.duranballester@bayer.com](guillem.duranballester@bayer.com) (G.D.-B.); [shivam.singh2@bayer.com](shivam.singh2@bayer.com) (S.S.); [sadegh.mohammadi@bayer.com](sadegh.mohammadi@bayer.com) (S.M.)  \n2 Pathology and Clinical Pathology, Bayer AG, 13353 Berlin, Germany; [moritz.radbruch@bayer.com](moritz.radbruch@bayer.com) (M.R.); [ute.bach@bayer.com](ute.bach@bayer.com) (U.B.); [sabrina.schroeder@bayer.com](sabrina.schroeder@bayer.com) (S.S.); [krystyna.siudak@bayer.com](krystyna.siudak@bayer.com) (K.S.); [julia.vienenkoetter@bayer.com](julia.vienenkoetter@bayer.com) (J.V.); [bettina.lawrenz@bayer.com](bettina.lawrenz@bayer.com) (B.L.)  \n* [Correspondence: pedro.osorio1@bayer.com](Correspondence: pedro.osorio1@bayer.com)  \nAbstract: Artificial Intelligence (AI)-based image analysis has immense potential to support diagnostic histopathology, including cancer diagnostics. However, developing supervised AI methods requires large-scale annotated datasets. A potentially powerful solution is to augment training data with synthetic data. Latent diffusion models, which can generate high-quality, diverse synthetic images, are promising. However, the most common implementations rely on detailed textual descriptions, which are not generally available in this domain. This work proposes a method that constructs structured textual prompts from automatically extracted image features. We experiment with the PCam dataset, composed of tissue patches only loosely annotated as healthy or cancerous. We show that including image-derived features in the prompt, as opposed to only healthy and cancerous labels, improves the Fréchet Inception Distance (FID) by 88.6 . We also show that pathologists find it challenging to detect synthetic images, with a median sensitivity/specificity of 0.55/0.55 . Finally, we show that synthetic data effectively train AI models.  \nKeywords: synthetic data; histopathology; generative AI; diffusion models; cancer detection; AI in health care; digital health; medical imaging  \n1. Introduction  \nHistopathology is considered the gold standard for cancer diagnostics. It entails the microscopic examination of tissue samples to identify signs of disease. These tissue samples, usually obtained through surgical resections or biopsies, are prepared and examined using hematoxylin and eosin (H&E) staining protocols. Subsequently, they can be digitized ","cbCaiuJsdy217nSx","https://ap.wps.com/l/cbCaiuJsdy217nSx","pdf",44235119,24,"English","# Abstract\n# Introduction\n## Histopathology and digital images\n## Challenges in datasets and model reliability\n# Background\n## Generative models for data scarcity, imbalance, and privacy","[{\"question\":\"Why are annotated datasets important for AI-assisted histopathology diagnosis?\",\"answer\":\"Supervised AI methods require large-scale annotated datasets to learn diagnostic patterns reliably in histopathology tasks.\"},{\"question\":\"How does the proposed method generate prompts for latent diffusion models?\",\"answer\":\"It constructs structured textual prompts from automatically extracted image features, instead of relying on detailed textual descriptions that are often unavailable in this domain.\"},{\"question\":\"What effects did image-derived features have on synthetic image quality and evaluation?\",\"answer\":\"Including image-derived features in the prompt improved Fréchet Inception Distance (FID) by 88.6, and pathologists showed difficulty detecting synthetic images, with median sensitivity/specificity of 0.55/0.55.\"}]","Latent Diffusion Models with Image-Derived Annotations for Enhanced AI-Assisted Cancer Diagnosis in Histopathology | PDF",1790032286]