[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119775-en":3,"doc-seo-119775-105":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},119775,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","Machine learning framework to segment sarcomeric structures in SMLM data - Automated structure selection and classification","Object detection is effective for image analysis but does not directly transfer to pointillist datasets generated by single molecule localization microscopy (SMLM). This study develops a supervised machine-learning framework that automates segmentation and averaging for sarcomere structures. Using simulations to create large labeled training sets, the trained model locates and classifies relevant protein localizations with high accuracy. Results are validated against prior manual evaluations, and simulation data are shown to be suitable for training. The method generalizes to other SMLM structures.","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nMachine learning framework to segment sarcomeric structuresinSMLM data  \nDániel Varga1*, Szilárd Szikora2, Tibor Novák1, Gergely Pap3, Gábor Lékó4, József Mihály2,5 & Miklós Erdélyi1  \nObject detection is an image analysis task with a wide range of applications, which is difficult to accomplish with traditional programming. Recent breakthroughs in machine learning have made significant progress in this area. However, these algorithms are generally compatible with traditional pixelated images and cannot be directly applied for pointillist datasets generated by single molecule localization microscopy (SMLM) methods. Here, we have improved the averaging method developed for the analysis of SMLM images of sarcomere structures based on a machine learning object detection algorithm. The ordered structure of sarcomeres allows us to determine the location of the proteins more accurately by superimposing SMLM images of identically assembled proteins. However, the area segmentation process required for averaging can be extremely time-consuming and tedious. In this work, we have automated this process. The developed algorithm not only finds the regions of interest, but also classifies the localizations and identifies the true positive ones. For training, we used simulations to generate large amounts of labelled data. After tuning the neural network’s internal parameters, it could find the localizations associated with the structures we were looking for with high accuracy. We validated our results by comparing them with previous manual evaluations. It has also been proven that the simulations can generate data of sufficient quality for training. Our method is suitable for the identification of other types of structures in SMLM data.  \nSingle molecule localization microscopy (SMLM)1–4 has become a widely used and accepted tool in molecular cell biology research5. By utilizing the localization of single molecules, previously unseen spatial resolution (∼ 10 nm) has been achieved in the optical regime6. The raw data provided by SMLM is a point cloud, i.e. a list of spatial coordinates of the localized emitters, which is fundamentally different from the pixelated images of conventional optical microscopes. Consequently, the interpretation, quantification and visualization of such data require new approaches and solutions. Conventional pixelated images can be generated from the localization data7–11, however such conversion introduces a loss of information12–14. Therefore, the direct extraction of the relevant information from the raw localization data requires extra effort. Another hurdle of the interpretation of SMLM measurements is its labour intensity. Data evaluation often requires the analysis of data belonging to many identical structures. Selecting the structures of interest and analyzing them individually is time consuming and tedious if performed manually. To this end, object classification15 and structure averaging16 methods have been developed and made public recently. Machine learning algorithms are gaining widespread attention for the analysis of complex data17. Sometimes, it is difficult to write an exact algorithm that the computer can follow to solve a specific task. In such cases, one option is to use machine learning methods. If we know the possible response signal of the system for a given input, supervised machine learning can be applied. Otherwise, without prior knowledge, non-supervised machine learning algorithms can be used to find patterns in the data or label data points. Artificial Neural Networks (ANNs) are widely used in supervised machine learning. They are made up of artificial neurons that can receive and process input data, and subsequently provide an output. Neurons with similar functions are grouped together to form layers. The machine tunes the internal parameters of the neural network based on a known training dataset so that it","cbCaibL2nwjK7RGe","https://ap.wps.com/l/cbCaibL2nwjK7RGe","pdf",2782159,1,10,"English","en",105,"# Introduction\n## Background on SMLM and data challenges\n## Why machine learning and object detection are needed\n# Proposed workflow\n## Supervised learning for localization classification\n## Automated selection for structure averaging\n# Training and validation\n## Simulation-based labeled data generation\n## Comparison with manual evaluations\n# Applicability and generalization","[{\"question\":\"Why can’t conventional image-based algorithms be directly applied to SMLM data?\",\"answer\":\"SMLM raw data are point clouds of spatial coordinates rather than pixelated images, and converting them to pixels can introduce information loss. This makes direct use of typical pixel-oriented methods difficult.\"},{\"question\":\"What does the proposed framework automate in the sarcomere analysis pipeline?\",\"answer\":\"It automates the area segmentation step required for structure averaging by directly using localization coordinates. The algorithm both finds regions of interest and classifies localizations, identifying true positives.\"},{\"question\":\"How is the model trained and how is accuracy validated?\",\"answer\":\"Training relies on simulations to generate large labeled datasets. After tuning neural network parameters, the results are validated by comparison with previous manual evaluations.\"}]","Machine learning framework to segment sarcomeric structures in SMLM data - Automated structure selection and classification | PDF",1785726254,25,{"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},"machine-learning-framework-to-segment-sarcomeric-structures-in-smlm-data-automated-structure-selection-and-classification","",{"@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/machine-learning-framework-to-segment-sarcomeric-structures-in-smlm-data-automated-structure-selection-and-classification/119775/",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},"Why can’t conventional image-based algorithms be directly applied to SMLM data?","Question",{"text":75,"@type":76},"SMLM raw data are point clouds of spatial coordinates rather than pixelated images, and converting them to pixels can introduce information loss. This makes direct use of typical pixel-oriented methods difficult.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What does the proposed framework automate in the sarcomere analysis pipeline?",{"text":80,"@type":76},"It automates the area segmentation step required for structure averaging by directly using localization coordinates. The algorithm both finds regions of interest and classifies localizations, identifying true positives.",{"name":82,"@type":73,"acceptedAnswer":83},"How is the model trained and how is accuracy validated?",{"text":84,"@type":76},"Training relies on simulations to generate large labeled datasets. After tuning neural network parameters, the results are validated by comparison with previous manual evaluations.","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},[93,97,101,105,110,115,120,123,128,131,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]