[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-137938-105":59,"doc-detail-137938-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","machine-learning-for-biomedical-imaging-sequence-models-for-continuous-cell-cycle-stage-prediction","Machine Learning for Biomedical Imaging - Sequence Models for Continuous Cell Cycle Stage Prediction","","The study addresses the need to understand continuous cell cycle dynamics while avoiding limitations of fluorescent reporters such as Fucci, which require genetic engineering and consume fluorescence channels. It evaluates deep learning sequence models for predicting continuous Fucci signals using non-fluorescence brightfield imaging. A large dataset of 1.3 M images of dividing human RPE1 cells with full trajectories enables comparisons across single time-frame, causal state space, and bidirectional transformer models, showing strong gains and accurate G1/S transition prediction at 1-hour resolution.",{"@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":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/machine-learning-for-biomedical-imaging-sequence-models-for-continuous-cell-cycle-stage-prediction/137938/",{"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/machine-learning-for-biomedical-imaging-sequence-models-for-continuous-cell-cycle-stage-prediction/137938.png","ImageObject",300,407,{"name":92,"@type":93},"Aditya","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-09-20","2026-08-23",true,{"@type":102,"interactionType":103,"userInteractionCount":24},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why are Fucci fluorescent reporters limited for broader cell cycle experiments?","Question",{"text":112,"@type":113},"Fucci requires genetic engineering, occupies two fluorescence channels, and may interfere with endogenous cell-cycle regulation, limiting simultaneous study of other processes.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What imaging modality and prediction target does the study use?",{"text":117,"@type":113},"The study uses non-fluorescence brightfield microscopy and predicts continuous Fucci signals that represent cell cycle phases over time.",{"name":119,"@type":110,"acceptedAnswer":120},"Which model types were compared, and what was the main performance finding?",{"text":121,"@type":113},"The work compares single time-frame models with causal state space models and bidirectional transformer models. Both causal and transformer-based approaches outperform fixed-frame baselines and enable prediction of transitions like G1/S within 1-hour resolution.","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},137938,1787471127,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":24,"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":129,"read_time":144},962085564549,"https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45","Machine Learning for Biomedical Imaging  \nSequence models for continuous cell cycle stage prediction from brightfield images  \nAndrea Salati* 1 Louis-Alexandre Leger* 1 Maxine Leonardi* 1 Martin Weigert† 1,2,3 Felix Naef† 1  \n*  \nThese authors contributed equally † Shared supervision  \n1 Institute of Bioengineering, School of Life Sciences, EPFL, Lausanne, Switzerland  \n2 ScaDS.AI, Dresden/Leipzig, Germany  \n3 TUD Dresden University of Technology  \nAbstract  \nThe cell division cycle is a ubiquitous essential process across the tree of life. Understanding cell cycle dynamics is crucial for studying biological processes such as growth, development and disease progression. While fluorescent protein reporters like the Fucci system allow live monitoring of cell cycle phases, they require genetic engineering and occupy additional fluorescence channels, limiting broader applicability in complex experiments. In this study, we conduct a comprehensive evaluation of deep learning methods for predicting continuous Fucci signals using non-fluorescence brightfield imaging, a widely available label-free imaging modality. To that end, we generated a large dataset of 1 .3 M images of dividing human RPE1 cells with full cell cycle trajectories to quantitatively compare the predictive performance of distinct model categories including single time-frame models, causal state space models and bidirectional transformer models. We show that both causal and transformer-based models significantly outperform single-and fixed frame approaches, enabling the prediction of visually imperceptible transitions like G1/S within 1 hour resolution. Our findings underscore the importance of sequence models for accurate predictions of cell cycle dynamics and highlight their potential for label-free imaging.  \nKeywords  \nCell cycle prediction, label-free microscopy, sequence-models  \nArticle informations  \n[https://doi.org/10.59275/j.melba.2026-84ea](https://doi.org/10.59275/j.melba.2026-84ea) ©2026 Andrea Salati and Louis-Alexandre Leger and Maxine Leonardi and Martin Weigert and Felix  \nNaef. License: CC-BY 4 .0  \nVolume 2026, Received: 2025-12, Published 2026-07  \n[Corresponding author: felix.naef@epfl.ch](Corresponding author: felix.naef@epfl.ch)  \nSpecial issue: Medical Imaging with Deep Learning (MIDL) 2025  \nGuest editors: Lisa Koch, Ronald M. Summers, Chen Chen, Yan Zhuang  \n1. Introduction  \nThe cell cycle is the driving force behind the growth and development of all living organisms. This well-studied sequence of cellular events is tightly regulated and aberrationsin such mechanisms can lead to genomic instability. It is divided into distinct phases—G1, S, G2, and M—that coordinate cell growth, DNA replication, and division, respectively, to ensure accurate transmission of genetic material to daughter cells. Each phase is controlled by specific checkpoints that monitor cellular integrity and proper progression through the cycle. This well-studied sequence of  \ncellular events is tightly regulated and aberrations in such mechanisms can lead to genomic instability, a key driver of various diseases including cancer Kastan and Bartek (2004); Malumbres and Barbacid (2009) . Live cell fluorescence microscopy has become a powerful tool for studying cell cycle progression in real time, particularly through the genetic engineering of fluorescent reporters like the Fucci system Sakaue-Sawano et al. (2008); Stallaert et al. (2022) . This system enables the distinction of cell cycle phases from single images by fluorescently tagging the two proteins Cdt1 and Geminin, whose expression changes distinctively with the cell cycle (Figure 1) . Recently, such reporters  \nhave even been instrumental in connecting live-cell imaging with single-cell transcriptomics to link cell cycle states with gene expression programs Bues et al. (2025) . However, despite its utility, the classic Fucci system and recent variants Sakaue-Sawano et al. (2017); Grant et al. (2018) are limiting in","cbCaipkrnvearenY","https://ap.wps.com/l/cbCaipkrnvearenY","pdf",12425910,23,"English","# Introduction\n## Background on cell cycle and Fucci limitations\n## Brightfield imaging and need for temporal models\n## Study goal and evaluated sequence architectures","[{\"question\":\"Why are Fucci fluorescent reporters limited for broader cell cycle experiments?\",\"answer\":\"Fucci requires genetic engineering, occupies two fluorescence channels, and may interfere with endogenous cell-cycle regulation, limiting simultaneous study of other processes.\"},{\"question\":\"What imaging modality and prediction target does the study use?\",\"answer\":\"The study uses non-fluorescence brightfield microscopy and predicts continuous Fucci signals that represent cell cycle phases over time.\"},{\"question\":\"Which model types were compared, and what was the main performance finding?\",\"answer\":\"The work compares single time-frame models with causal state space models and bidirectional transformer models. Both causal and transformer-based approaches outperform fixed-frame baselines and enable prediction of transitions like G1/S within 1-hour resolution.\"}]","Machine Learning for Biomedical Imaging - Sequence Models for Continuous Cell Cycle Stage Prediction | PDF",58]