[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120890-en":3,"doc-seo-120890-105":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},120890,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Deploying Machine Learning Based Segmentation for Scientific Imaging Analysis at Synchrotron Facilities - Research Overview","Scientific user facilities generate massive experimental and simulation image datasets, making image processing difficult in both scale and speed. Developing real-time algorithms that also correct artifacts and distortions requires substantial computation and specialized workflows. The DOE national laboratories’ MLExchange project addresses these constraints by providing web-based interactive interfaces for uploading, visualizing, labeling, training, and deploying machine learning models for tomography segmentation. The platform supports multiple ML and deep-learning methods and aims to improve performance on complex, low-contrast images.","Lawrence Berkeley National Laboratory LBL Publications  \nTitle  \nDeploying Machine Learning Based Segmentation for Scientific Imaging Analysis at Synchrotron Facilities.  \nPermalink  \n[https://escholarship.org/uc/item/838283kr](https://escholarship.org/uc/item/838283kr)  \nAuthors  \nHao, Guanhua  \nRoberts, Eric  \nChavez, Tannyet al.  \nPublication Date  \n2023  \nDOI  \n10.2352/ei.2023.35.9.ipas-290 Peer reviewed  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nAuthor Manuscr ipt Author Manuscr ipt Author Manuscr ipt Author Manuscript  \n\n|  | HHS Public Access\u003Cbr>Author manuscript\u003Cbr>IS&T Int Symp Electron Imaging. Author manuscript; available in PMC 2023 December 21. |\n| --- | --- |\n\nPublished in final edited form as:  \nIS&T Int Symp Electron Imaging. 2023 ; 35: . doi:10.2352/ei.2023.35.9.ipas-290 .  \nDeploying Machine Learning Based Segmentation for Scientific Imaging Analysis at Synchrotron Facilities  \nGuanhua Hao†,1 , Eric J. Roberts†,2,3 , Tanny Chavez 1 , Zhuowen Zhao 1 , Elizabeth A.  \nHolman 1 , Howard Yanxon4 , Adam Green 1 , Harinarayan Krishnan 1,2 , Daniela Ushizima2,5 , Dylan McReynolds 1 , Nicholas Schwarz4 , Petrus H. Zwart *,2,3 , Alexander Hexemer1 , Dilworth  \nY. Parkinson**,1  \n1Advanced Light Source (ALS), Lawrence Berkeley National Laboratory; Berkeley, CA 94720  \n2Center for Advanced Mathematics for Energy Research Applications (CAMERA), Lawrence Berkeley National Laboratory; Berkeley, CA 94720  \n3Molecular Biophysics and Integrated Bioimaging (MBIB), Lawrence Berkeley National Laboratory; Berkeley, CA 94720  \n4Advanced Photon Source (APS), Argonne National Laboratory; Lemont, IL 60439  \n5Computational Research Division (CRD), Lawrence Berkeley National Laboratory; Berkeley, CA 94720  \nAbstract  \nScientific user facilities present a unique set of challenges for image processing due to the large volume of data generated from experiments and simulations. Furthermore, developing and implementing algorithms for real-time processing and analysis while correcting for any artifacts or distortions in images remains a complex task, given the computational requirements of the processing algorithms. In a collaborative effort across multiple Department of Energy national laboratories, the ”MLExchange” project is focused on addressing these challenges. MLExchange is a Machine Learning framework deploying interactive web interfaces to enhance and accelerate data analysis. The platform allows users to easily upload, visualize, label, and train networks. The resulting models can be deployed on real data while both results and models could be shared with the scientists. The MLExchange web-based application for image segmentation allows for training, testing, and evaluating multiple machine learning models on hand-labeled tomography data. This environment provides users with an intuitive interface for segmenting images using a variety of machine learning algorithms and deep-learning neural networks. Additionally, these tools have the potential to overcome limitations in traditional image segmentation techniques, particularly for complex and low-contrast images.  \n*Corresponding author 1: phzwart@lbl.gov.†Authors contributed equally  \n**Corresponding author 2: [dyparkinson@lbl.gov](dyparkinson@lbl.gov).  \nAuthor Manuscr ipt Author Manuscr ipt Author Manuscr ipt Author Manuscript  \nHao et al. Page 2  \nIntroduction  \nThe scientific community relies on scientific instrumentation at light and neutron source user facilities to perform science that is impossible anywhere else. Beamlines are significant producers of scientific data, and image-based data constitutes a significant part of this, with many instruments producing terabytes of image data per day. Beyond the challenges of moving and storing data at high rates and volumes is the challenge of developing and implementing algorithms for processing and analyzing data in real-time to produce immediate results while accura","cbCaiveZaeCkJDoY","https://ap.wps.com/l/cbCaiveZaeCkJDoY","pdf",1776931,1,14,"English","en",105,"# Abstract\n# Introduction\n## Challenges in scientific imaging analysis\n## MLExchange platform and MLOps approach\n## Web-based image segmentation application","[{\"question\":\"What challenges do scientific user facilities face for image processing?\",\"answer\":\"They must handle very large volumes of image data and support real-time analysis while correcting artifacts or distortions. These needs make developing usable algorithms especially complex.\"},{\"question\":\"What is the MLExchange project designed to do?\",\"answer\":\"MLExchange provides a machine learning framework with interactive web interfaces to upload, visualize, label, train, and deploy models. It also enables sharing results and models with scientists.\"},{\"question\":\"How does the MLExchange segmentation application improve over traditional methods?\",\"answer\":\"It trains and evaluates multiple machine learning and deep-learning models on hand-labeled tomography data. This can better segment complex or low-contrast images where thresholding or watershed approaches may struggle.\"}]","Deploying Machine Learning Based Segmentation for Scientific Imaging Analysis at Synchrotron Facilities - Research Overview | PDF",1785732523,35,{"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},"deploying-machine-learning-based-segmentation-for-scientific-imaging-analysis-at-synchrotron-facilities-research-overview","",{"@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/deploying-machine-learning-based-segmentation-for-scientific-imaging-analysis-at-synchrotron-facilities-research-overview/120890/",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","2026-08-03",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},"What challenges do scientific user facilities face for image processing?","Question",{"text":75,"@type":76},"They must handle very large volumes of image data and support real-time analysis while correcting artifacts or distortions. These needs make developing usable algorithms especially complex.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the MLExchange project designed to do?",{"text":80,"@type":76},"MLExchange provides a machine learning framework with interactive web interfaces to upload, visualize, label, train, and deploy models. It also enables sharing results and models with scientists.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the MLExchange segmentation application improve over traditional methods?",{"text":84,"@type":76},"It trains and evaluates multiple machine learning and deep-learning models on hand-labeled tomography data. This can better segment complex or low-contrast images where thresholding or watershed approaches may struggle.","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"]