[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-31514":3,"doc-seo-31514":26},{"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,"file_id":15,"file_url":16,"file_type":17,"file_size":18,"view_count":4,"is_deleted":4,"is_public":19,"is_downloadable":19,"audit_status":19,"page_count":11,"language":20,"language_code":21,"table_of_contents":22,"faqs":23,"seo_title":13,"seo_description":14,"update_tm":24,"read_time":25},31514,1099513958762,"Logic","https://ap-avatar.wpscdn.com/avatar/1000023916a998db790?_k=1776737595927829259",8,"Research & Report","Automated 3D Labelling of Fibroblasts and Endothelial Cells in SEM","This document details a methodology for automated 3D labeling of fibroblasts and endothelial cells within Scanning Electron Microscopy (SEM) datasets. The process begins with a 3D stack of 2D images, from which individual 2D images are extracted. A neural network is then employed to process these individual images. The neural network architecture is presented, featuring an encoder-decoder structure with progressive downsampling and upsampling to capture multi-scale features. The encoder reduces the spatial dimensions while increasing the number of feature channels, culminating in a compact representation. Subsequently, the decoder reconstructs the information, progressively increasing spatial resolution and decreasing feature channels. This specific architecture involves a series of convolutional layers and pooling operations in the encoder (e.g., 256x256 -> 126x126 -> 64x64 -> ... -> 1x1) and corresponding upsampling and convolutional layers in the decoder. The output of the neural network is a segmented image, where specific cell types or structures are highlighted with a distinct color, illustrated by blue regions in the output images. The workflow is visually represented in three diagrams: the first illustrates the input data and neural network processing, showing single 2D images from the stack feeding into the network and resulting in segmented outputs; the second details the U-Net-like network architecture; and the third provides a step-by-step overview with numbered stages, from the 3D image stack (1) to a single 2D image (2), the input to the neural network, the network's output segmentation (3, 4, 5), and the final labeled visual representation. This approach enables efficient and accurate identification and segmentation of cellular components in complex 3D microscopy data.","cbCaiaosYvfv3VJo","https://ap.wps.com/l/cbCaiaosYvfv3VJo","pdf",525240,1,"English","en","# 1. Introduction\n# 2. Methodology\n## 2.1 Data Acquisition\n## 2.2 Neural Network Architecture\n## 2.3 Segmentation Process\n# 3. Results\n# 4. Discussion\n# 5. Conclusion","[{\"question\":\"What is the primary goal of the described methodology?\",\"answer\":\"The primary goal is the automated 3D labeling of fibroblasts and endothelial cells in Scanning Electron Microscopy (SEM) datasets.\"},{\"question\":\"What type of neural network architecture is used in this process?\",\"answer\":\"A neural network with an encoder-decoder structure, similar to a U-Net, is employed for image segmentation.\"},{\"question\":\"What are the inputs and outputs of the neural network?\",\"answer\":\"The input to the neural network consists of single 2D images extracted from a 3D SEM image stack, and the output is a segmented image highlighting specific cellular structures in blue.\"}]",1779656447,20,{"code":4,"msg":27,"data":28},"ok",{"site_id":29,"language":21,"slug":30,"title":13,"keywords":31,"description":14,"schema_data":32,"social_meta":83,"head_meta":85,"extra_data":87,"updated_unix":24},105,"automated-3d-labelling-of-fibroblasts-and-endothelial-cells-in-sem","",{"@graph":33,"@context":82},[34,51,65],{"@type":35,"itemListElement":36},"BreadcrumbList",[37,41,45,48],{"item":38,"name":39,"@type":40,"position":19},"https://docshare.wps.com","Home","ListItem",{"item":42,"name":43,"@type":40,"position":44},"https://docshare.wps.com/document/","Document",2,{"item":46,"name":12,"@type":40,"position":47},"https://docshare.wps.com/document/research-report/",3,{"item":49,"name":13,"@type":40,"position":50},"https://docshare.wps.com/document/automated-3d-labelling-of-fibroblasts-and-endothelial-cells-in-sem/31514/",4,{"url":49,"name":13,"@type":52,"author":53,"headline":13,"publisher":55,"fileFormat":58,"description":14,"dateModified":59,"datePublished":59,"encodingFormat":58,"isAccessibleForFree":60,"interactionStatistic":61},"DigitalDocument",{"name":9,"@type":54},"Person",{"url":38,"name":56,"@type":57},"DocShare","Organization","application/pdf","2026-05-24",true,{"@type":62,"interactionType":63,"userInteractionCount":4},"InteractionCounter",{"@type":64},"ViewAction",{"@type":66,"mainEntity":67},"FAQPage",[68,74,78],{"name":69,"@type":70,"acceptedAnswer":71},"What is the primary goal of the described methodology?","Question",{"text":72,"@type":73},"The primary goal is the automated 3D labeling of fibroblasts and endothelial cells in Scanning Electron Microscopy (SEM) datasets.","Answer",{"name":75,"@type":70,"acceptedAnswer":76},"What type of neural network architecture is used in this process?",{"text":77,"@type":73},"A neural network with an encoder-decoder structure, similar to a U-Net, is employed for image segmentation.",{"name":79,"@type":70,"acceptedAnswer":80},"What are the inputs and outputs of the neural network?",{"text":81,"@type":73},"The input to the neural network consists of single 2D images extracted from a 3D SEM image stack, and the output is a segmented image highlighting specific cellular structures in blue.","https://schema.org",{"og:url":49,"og:type":84,"og:title":13,"og:site_name":56,"og:description":14},"article",{"robots":86,"canonical":49},"index,follow",{"doc_id":7,"site_id":29}]