[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126776-en":3,"doc-seo-126776-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},126776,962084926284,"Aurora","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","A machine learning pipeline for membrane segmentation of cryo-electron tomograms","This work describes a learning pipeline for segmenting and identifying cell membrane structures from cryo-electron tomograms, a setting where traditional tools struggle due to low signal-to-noise ratio and missing-wedge artifacts. The pipeline begins with supervised learning using a special convolutional neural network trained on simulated data, then extends via semi-supervised reinforcement learning and/or region merging to reconnect disconnected components. Finally, parametric or non-parametric fitting improves results and quantifies uncertainties using domain-driven priors and constraints, validated on two real tomogram datasets.","Lawrence Berkeley National Laboratory LBL Publications  \nTitle  \nA machine learning pipeline for membrane segmentation of cryo-electron tomograms  \nPermalink  \n[https://escholarship.org/uc/item/9sk89395](https://escholarship.org/uc/item/9sk89395)  \nAuthors  \nZhou, Li  \nYang, Chao Gao, Weiguo et al.  \nPublication Date  \n2023  \nDOI  \n10.1016/j.jocs.2022.101904  \nCopyright Information  \nThis work is made available under the terms of a Creative Commons Attribution License, available at [https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)  \nPeer reviewed  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nJournal of Computational Science 66 (2023) 101904  \n| A machine learning pipeline for membrane segmentation ofcryo-electron tomograms |  |  |  |\n| --- | --- | --- | --- |\n| Li Zhou a, Chao Yang b,∗, Weiguo Gao a,d, Talita Percianoc, Karen M. Davies f, Nicholas K. Sauterea School of Mathematical Sciences, Fudan University, Shanghai, 200433, China\u003Cbr>b Applied Mathematics and Computational Research Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USAc Scientific Data Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA\u003Cbr>d School of Data Science, Fudan University, Shanghai, 200433, China\u003Cbr>e Molecular Biophysics and Integrated Bioimaging Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USAf Electron Bio-Imaging Center, Diamond Lightsource, Harwell Science and Innovation Campus, Didcot, OX11 0DE, UK |  |  |  |\n| A R T I C L E I N F O |  | A B S T R A C T |  |\n| Keywords:\u003Cbr>Image segmentation Machine learning Membrane structure Reinforcement learning Gaussian process Uncertainty quantification |  | We describe how to use several machine learning techniques organized in a learning pipeline to segment and identify cell membrane structures from cryo electron tomograms. These tomograms are difficult to analyze with traditional segmentation tools. The learning pipeline in our approach starts from supervised learning via a special convolutional neural network trained with simulated data. It continues with semi-supervised reinforcement learning and/or a region merging technique that tries to piece together disconnected components belonging to the same membrane structure. A parametric or non-parametric fitting procedure is then used to enhance the segmentation results and quantify uncertainties in the fitting. Domain knowledge is used in generating the training data for the neural network and in guiding the fitting procedure through the use of appropriately chosen priors and constraints. We demonstrate that the approach proposed here works well for extracting membrane surfaces in two real tomogram datasets. |  |\n\n1. Introduction  \nDespite the tremendous progress made in biological imaging that has yielded tomograms with ever-higher resolutions, the interpretation of data (e.g., the segmentation of cell tomograms into organelles and proteins) remains a challenging task. The difficulty is most extreme, in our experience, in the case of cryo-electron tomography (cryo-ET), where the samples exhibit inherently low contrast due to the limited electron dose that can be applied during imaging, before radiation damage occurs. The resulting tomograms thus have a low signal-to-noise ratio (SNR), as well as missing-wedge artifacts caused by the limited sample tilt range that is accessible during imaging [1]. Fig. 1 shows two cryo-EM tomogram slices from two different datasets. These tomogram slices show a number of circularly shaped membrane structures with proteins (visible as small dots) inside and outside the membrane surfaces.  \nOur objective is to identify and isolate from such tomograms multiple cellular substructures such as membranes and protein complexes that can be analyzed further. This objective is often achieved through  \nan image segmentation procedure. Currently, such a procedure i","cbCaia8fvY20X9WI","https://ap.wps.com/l/cbCaia8fvY20X9WI","pdf",4270263,1,14,"English","en",105,"# Introduction\n## Problem: segmentation challenges in cryo-electron tomography\n## Limitations of manual and existing automated methods\n## Motivation for learning-based approaches","[{\"question\":\"Why are cryo-electron tomograms difficult to segment automatically?\",\"answer\":\"Low signal-to-noise ratio from limited electron dose and missing-wedge artifacts make membrane structures hard to delineate with traditional segmentation tools.\"},{\"question\":\"How does the proposed pipeline start?\",\"answer\":\"It begins with supervised learning using a special convolutional neural network trained on simulated data informed by domain knowledge.\"},{\"question\":\"What methods are used after the initial neural-network segmentation?\",\"answer\":\"The approach applies semi-supervised reinforcement learning and/or a region merging technique to assemble disconnected membrane components, then uses fitting procedures to enhance segmentation and quantify uncertainties.\"}]","A machine learning pipeline for membrane segmentation of cryo-electron tomograms | PDF",1785934726,35,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"a-machine-learning-pipeline-for-membrane-segmentation-of-cryo-electron-tomograms","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/a-machine-learning-pipeline-for-membrane-segmentation-of-cryo-electron-tomograms/126776/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why are cryo-electron tomograms difficult to segment automatically?","Question",{"text":75,"@type":76},"Low signal-to-noise ratio from limited electron dose and missing-wedge artifacts make membrane structures hard to delineate with traditional segmentation tools.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed pipeline start?",{"text":80,"@type":76},"It begins with supervised learning using a special convolutional neural network trained on simulated data informed by domain knowledge.",{"name":82,"@type":73,"acceptedAnswer":83},"What methods are used after the initial neural-network segmentation?",{"text":84,"@type":76},"The approach applies semi-supervised reinforcement learning and/or a region merging technique to assemble disconnected membrane components, then uses fitting procedures to enhance segmentation and quantify uncertainties.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]