[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-362938-105":59,"doc-detail-362938-en":130},{"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":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","machine-learning-based-tumor-segmentation-and-classification-using-dynamic-optical-contrast-imaging-for-thyroid-cancer","Machine-learning-based tumor segmentation and classification using dynamic optical contrast imaging for thyroid cancer","","Machine-learning integrated dynamic optical contrast imaging (DOCI) is developed to distinguish thyroid cancer subtypes using label-free measurements of endogenous tissue autofluorescence lifetimes. The study addresses diagnostic limits of fine-needle aspiration by enabling spatially resolved, real-time potential for intraoperative tumor classification and margin assessment. A PCA plus logistic regression framework classifies tissue probabilities, while squeeze-and-excitation U-Net models perform tumor semantic segmentation, achieving high validation accuracy and strong Dice scores.",{"@graph":69,"@context":122},[70,84,105],{"@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/machine-learning-based-tumor-segmentation-and-classification-using-dynamic-optical-contrast-imaging-for-thyroid-cancer/362938/",{"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/machine-learning-based-tumor-segmentation-and-classification-using-dynamic-optical-contrast-imaging-for-thyroid-cancer/362938.png","ImageObject",300,407,{"name":92,"@type":93},"Bintang","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-31","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":39},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the study target in thyroid cancer diagnosis?","Question",{"text":112,"@type":113},"Diagnosis is challenging because benign and malignant nodules can overlap, and fine-needle aspiration often yields indeterminate results without spatial context. The work also targets the limited ability to assess tumor margins in real time.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the proposed method use dynamic optical contrast imaging (DOCI)?",{"text":117,"@type":113},"The approach measures autofluorescence lifetimes of endogenous fluorophores via label-free, multispectral DOCI. These measurements support distinguishing thyroid tissue subtypes and identifying cancerous regions.",{"name":119,"@type":110,"acceptedAnswer":120},"What modeling pipeline was used for classification and segmentation?",{"text":121,"@type":113},"Pixel-level PCA with logistic regression produces tissue probabilities aggregated by a regional majority-vote gate for normal, follicular, or papillary categorization. Tumor-specific squeeze-and-excitation U-Net models trained on voxel-only inputs perform semantic segmentation, with PCA-guided channel ablation enabling a compact channel subset.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},362938,1790366583,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":39,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145,"preview_page_count":19,"preview_urls":146},962085564381,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","RESEARCH PAPER  \nMachine-learning-based tumor segmentation and classification using dynamic optical contrast imaging for thyroid cancer  \nTyler Vasse,a,† Yazeed Alhiyari,b,† Lauran K. Evans,b Ramesh Shori,b  \nMaie St. John,b,* and Tuan Vo-Dinha,*  \naDuke University, Biomedical Engineering Department, Durham, North Carolina, United States bUniversity of California, Los Angeles, David Geffen School of Medicine, Los Angeles,  \nCalifornia, United States  \nStatement of Discovery  \nThis work uses machine learning combined with dynamic optical contrast imaging (DOCI), a label-free multispectral optical technique, to distinguish thyroid cancer subtypes based on endogenous tissue autofluorescence. This approach enables real-time, non-invasive tumor classification and margin assessment, with potential for intraoperative surgical guidance.  \nABSTRACT. Significance: Thyroid cancer is the most common endocrine malignancy, and diagnosis is often challenging due to overlapping features between benign and malignant nodules. Fine-needle aspiration, the clinical gold standard, frequently yields indeterminate results and lacks spatial context, leading to unnecessary surgeries. Real-time margin assessment also remains limited. There is a need for accurate, label-free, spatially resolved imaging. Dynamic optical contrast imaging (DOCI), which measures autofluorescence lifetimes of endogenous fluorophores, offers a promising platform for intraoperative cancer detection.  \nAim: We develop and evaluate a machine learning integrated DOCI framework to classify thyroid tissue subtypes and segment cancerous regions from ex vivo hyperspectral sections, with potential for real-time surgical use.  \nApproach: Fresh ex vivo thyroid specimens were imaged using a 23-channel DOCI acquisition. A pixel-level principal component analysis (PCA) and logistic regression classifier produced tissue probabilities, aggregated by a regional majority-vote gate to categorize specimens as normal, follicular, or papillary. Tumor-specific squeezeand-excitation U-Net models were trained on voxel-only inputs for semantic segmentation. PCA-guided channel ablation identified a reduced spectral subset, and the pipeline was retrained using a compact 12-channel input.  \nResults: The first two PCA components explained over 70% of spectral variance and yielded well-separated tissue clusters. The regional PCA classifier achieved 92.3% validation accuracy and 100% accuracy on the test set. Full 23-channel U-Net models delivered strong segmentation (papillary: Dice nonempty 0.829, balanced Dice 0.914; follicular: Dice nonempty 0.618, balanced Dice 0.809) . Reducedchannel models preserved most performance and improved follicular segmentation (Dice nonempty 0.762), confirming spectral redundancy.  \nConclusions: Integrating DOCI with interpretable machine learning enables accurate, label-free differentiation and segmentation of thyroid tissues. Channel  \n*Address all correspondence to Maie St. John, [mstjohn7@jh.edu](mstjohn7@jh.edu); Tuan Vo-Dinh, [tuan.vodinh@duke.edu](tuan.vodinh@duke.edu)[ ](tuan.vodinh@duke.edu)†These authors contributed to this work equally.  \nBiophotonics Discovery 015001-1 Jan–Mar 2026 • Vol. 3(1)  \nVasse et al.: Machine-learning-based tumor segmentation and classification. . .  \nreduction demonstrates that high performance is achievable with a compact spectral subset, supporting faster, more cost-efficient DOCI systems and future real-time intraoperative deployment.  \n© The Authors. Published by SPIE under a Creative Commons Attribution 4.0 International License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI. [DOI: 10.1117/1.BIOS.3.1.015001]  \nKeywords: machine learning; cancer detection; optical imaging; intraoperative imaging; thyroid cancer  \nPaper 250090GR received Aug. 4, 2025; revised Nov. 21, 2025; accepted Dec. 9, 2025; published Jan.  \n2, 2026 .  \n1 Introduction  \nThyroi","cbCaibzXYYLemye3","https://ap.wps.com/l/cbCaibzXYYLemye3","pdf",3896355,13,"English","# Abstract\n## Significance\n## Aim\n## Approach\n## Results\n## Conclusions\n# Introduction","[{\"question\":\"What problem does the study target in thyroid cancer diagnosis?\",\"answer\":\"Diagnosis is challenging because benign and malignant nodules can overlap, and fine-needle aspiration often yields indeterminate results without spatial context. The work also targets the limited ability to assess tumor margins in real time.\"},{\"question\":\"How does the proposed method use dynamic optical contrast imaging (DOCI)?\",\"answer\":\"The approach measures autofluorescence lifetimes of endogenous fluorophores via label-free, multispectral DOCI. These measurements support distinguishing thyroid tissue subtypes and identifying cancerous regions.\"},{\"question\":\"What modeling pipeline was used for classification and segmentation?\",\"answer\":\"Pixel-level PCA with logistic regression produces tissue probabilities aggregated by a regional majority-vote gate for normal, follicular, or papillary categorization. Tumor-specific squeeze-and-excitation U-Net models trained on voxel-only inputs perform semantic segmentation, with PCA-guided channel ablation enabling a compact channel subset.\"}]","Machine-learning-based tumor segmentation and classification using dynamic optical contrast imaging for thyroid cancer | PDF",1790149478,33,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/8769103fd2bed881e00f22e2d5303271.webp",983,1272,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/3c39956810a9621ef773681841718c09.webp",982,1270,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/26cdaf223be39e8bd2f81851608beea1.webp",981,1269,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/55af82885781bc79c5692dac99c72e0f.webp",980,1268]