[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-355733-105":59,"doc-detail-355733-en":131},{"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":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","deep-learning-endomicroscope-with-large-field-of-view-and-depth-of-field-for-real-time-in-vivo-imaging-of-epithelial-cancer-hallmarks-research-article","Deep-learning endomicroscope with large field-of-view and depth-of-field for real-time in vivo imaging of epithelial cancer hallmarks - Research article","","In vivo microscopy (IVM) improves early detection of epithelial precancer but is limited by trade-offs among resolution, field-of-view (FOV), and depth-of-field (DOF), restricting its ability to assess large, heterogeneous lesions. PrecisionView is a compact, deep learning-enabled endomicroscope that combines a deep learning-optimized phase mask with real-time reconstruction. It achieves a 20 mm2 FOV and 500 µm DOF at 4 µm resolution, generating coregistered maps of epithelial nuclear morphology and subsurface microvasculature. Imaging oral cavity volunteers and cervical specimens reveals lesion-associated microscopic patterns, supporting point-of-care early cancer detection.",{"@graph":69,"@context":123},[70,84,106],{"@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/deep-learning-endomicroscope-with-large-field-of-view-and-depth-of-field-for-real-time-in-vivo-imaging-of-epithelial-cancer-hallmarks-research-article/355733/",{"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/deep-learning-endomicroscope-with-large-field-of-view-and-depth-of-field-for-real-time-in-vivo-imaging-of-epithelial-cancer-hallmarks-research-article/355733.png","ImageObject",300,407,{"name":92,"@type":93},"Terk","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-09-22",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",13,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What limitations of conventional in vivo microscopy motivate this work?","Question",{"text":113,"@type":114},"Conventional IVM is constrained by coupled trade-offs among resolution, field-of-view, and depth-of-field, resulting in a field-of-view too small to cover typical suspicious lesions. It also makes comprehensive examination difficult and can introduce gaps when mosaicking is used.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does PrecisionView overcome these constraints?",{"text":118,"@type":114},"PrecisionView integrates a deep learning-optimized phase mask with real-time reconstruction. This enables wide-area visualization while maintaining cellular resolution and extended depth-of-field.",{"name":120,"@type":111,"acceptedAnswer":121},"What cancer hallmarks does PrecisionView assess in vivo?",{"text":122,"@type":114},"PrecisionView enables assessment of two key epithelial cancer hallmarks: epithelial cell nuclear morphology and subsurface microvasculature. It does this using fluorescence and reflectance imaging.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},355733,1790308561,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":41,"preview_page_count":19,"preview_urls":146},1099525198933,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","RESEARCH ARTICLE  \nENGINEERING  \n OPEN ACCESS  \nDeep-learning endomicroscope with large field-of-view and depth-of-field for real-time in vivo imaging of epithelial cancer hallmarks  \nHuayu Houa, 1 , Jimin Wua, b, 1 , Jinyun Liua, Vivek Boominathanb , Argaja Shendea, Karthik Golia, Jennifer Carnsa, Richard A. Schwarza, Ann M. Gillenwaterc, Preetha Ramalingamd, Mila P. Salcedoe, Kathleen M. Schmelere, Tomasz S. Tkaczyka, b, Jacob T. Robinsona, b,f,  \nAshok Veeraraghavanb,g,2 , and Rebecca R. Richards-Kortuma,2  Affiliations are included on p. 12.  \nContributed by Rebecca R. Richards-Kortum; received January 23, 2026; accepted April 9, 2026; reviewed by Audrey Bowden, Nicholas James Durr, and Milind Rajadhyaksha  \nIn vivo microscopy (IVM) has shown great promise to improve early detection of epithelial precancer, but it suffers from fundamental trade-offs that limit the resolution, field-of-view (FOV) and depth-of-field (DOF). Here, we present PrecisionView, a compact, deep learning-enabled endomicroscope that breaks these constraints and achieves 20 mm2 FOVand 500 µm DOF with 4 µm resolution, representing approximately 5× increase in FOVand 8× larger DOF compared to conventional IVM with similar resolution. PrecisionView integrates a deep learning-optimized phase mask and real-time reconstruction, enabling rapid in vivo assessment of two key hallmarks of cancer: epithelial cell nuclear morphology and subsurface microvasculature through fluorescence and reflectance imaging. By imaging the oral cavity of healthy volunteers and cervical specimens with precancerous lesions, PrecisionView generates large-scale (1 to 3 cm2) coregistered maps of cellular and vascular structures, revealing distinct microscopic patterns associated with anatomic structures and precancerous lesions. Our results suggest the potential of this computational endomicroscope to address the unmet need for early cancer detection at the point of care.  \ndeep learning | endomicroscopy | extended depth-of-field | large field-of-view | in vivo imaging  \nCancer is a leading cause of premature death worldwide (1, 2), and epithelial cancers account for 80 to 90% of all cancer cases (3). Most epithelial cancer patients are diagnosed with late-stage disease due to a lack of effective diagnostic methods, resulting in low overall 5-y survival rates (4, 5). Histopathologic examination of tissue biopsy is the gold standard to diagnose dysplasia and cancer. However, biopsy is an invasive procedure and requires substantial infrastructure to prepare and interpret histology slides. In the case of large, heterogeneous lesions, only limited tissue areas can be assessed with biopsy. Because most suspicious lesions are benign (6, 7), it is extremely challenging even for experts to determine where and when to perform invasive biopsy (8, 9). As a result, the accuracy of pathologic diagnosis suffers from sampling error (10, 11). In vivo microscopy (IVM) has shown promise to improve the early detection of epithelial cancers ( 11–13) . The morphological hallmarks of cancer, including alterations in neoplastic cell nuclei and supporting microvasculature, provide predictive hallmarks of precancer (9, 14–20) . Simultaneous assessment of changes in both cell nuclei and micro vasculature can potentially improve accuracy for early cancer and precancer detection. Pilot studies have demonstrated promising clinical performance of IVM for a variety of cancer types (9, 18–20). However, clinical translation of IVM is hindered by fundamental limitations of conventional optics. The field-of-view (FOV) of current IVM is too small (usually \u003C0 .5 mm2) relative to typical size (~cm2) of suspicious lesions (19–32) . The scale-dependent geometric aberrations from miniature optics (33) or the small size of image relay probes (20, 21, 23–25, 30) fundamentally restrict the FOV of imaging systems. It is difficult to fully examine large, heterogeneous lesions at risk with current IVM to identify which regions may","cbCaipWNyIj107Qv","https://ap.wps.com/l/cbCaipWNyIj107Qv","pdf",6796829,12,"English","# Significance\n## Problem: trade-offs in conventional IVM\n## Approach: PrecisionView endomicroscope\n## Results: wide-area coregistered cellular and vascular maps","[{\"question\":\"What limitations of conventional in vivo microscopy motivate this work?\",\"answer\":\"Conventional IVM is constrained by coupled trade-offs among resolution, field-of-view, and depth-of-field, resulting in a field-of-view too small to cover typical suspicious lesions. It also makes comprehensive examination difficult and can introduce gaps when mosaicking is used.\"},{\"question\":\"How does PrecisionView overcome these constraints?\",\"answer\":\"PrecisionView integrates a deep learning-optimized phase mask with real-time reconstruction. This enables wide-area visualization while maintaining cellular resolution and extended depth-of-field.\"},{\"question\":\"What cancer hallmarks does PrecisionView assess in vivo?\",\"answer\":\"PrecisionView enables assessment of two key epithelial cancer hallmarks: epithelial cell nuclear morphology and subsurface microvasculature. It does this using fluorescence and reflectance imaging.\"}]","Deep-learning endomicroscope with large field-of-view and depth-of-field for real-time in vivo imaging of epithelial cancer hallmarks - Research article | PDF",1790120672,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/6ae9e3a0602266e7b2c24083ecd67268.webp",983,1316,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/fe2d2853069ce821dfbec8d5681b5b03.webp",982,1315,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/8613d32cbd45f35f2c394b59baabc6d1.webp",981,1313,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/d1a2364efc0890728c9ef2d0d05b6896.webp",980,1312]