[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-126793-105":59,"doc-detail-126793-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","characterization-of-biological-particles-using-an-integrated-hyperspectral-imaging-and-machine-learning","Characterization of Biological Particles Using an Integrated Hyperspectral Imaging and Machine Learning","","Presentation describing how integrated hyperspectral imaging (HSI) and machine learning characterize biological nanoparticles, with emphasis on liposomes as drug-delivery vehicles. It outlines creating representative spectral profiles, generating spectral libraries using spectral angle matching (SAM), and classifying nanoparticle types with SVM and CNN models. The workflow supports detecting spectral patterns linked to drug loading, training on separate empty versus drug-loaded liposome imaging, and adapting CNN architectures to multi-band HSI data. Funding and project acknowledgments are included.",{"@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/characterization-of-biological-particles-using-an-integrated-hyperspectral-imaging-and-machine-learning/126793/",{"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/characterization-of-biological-particles-using-an-integrated-hyperspectral-imaging-and-machine-learning/126793.png","ImageObject",300,407,{"name":92,"@type":93},"Eliana","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-09-28","2026-08-05",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why are liposomes used as a focus for biological particle characterization?","Question",{"text":112,"@type":113},"Liposomes are biocompatible, non-toxic, and can carry versatile substances, making them ideal vehicles for drug distribution and delivery.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the presentation’s SAM-SVM workflow build and use spectral data?",{"text":117,"@type":113},"It generates spectral libraries for each nanoparticle type using spectral angle matching (SAM), then classifies nanoparticles using support vector machine (SVM) and convolutional neural network (CNN) techniques.",{"name":119,"@type":110,"acceptedAnswer":120},"What advantages does CNN provide compared with SVM in this framework?",{"text":121,"@type":113},"CNN can outperform SVM in capturing subtle input variations, such as small changes in spectral profiles, enabling effective classification across diverse biological particles.","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},126793,1785934809,{"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":34,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":8,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":129,"read_time":81},1099523882182,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","The 2024 GIRS Conference, Mar. 7, 2024  \nCharacterization of Biological Particles Using an Integrated  \nHyperspectral Imaging and Machine Learning Kaeul Lim, Arezoo Ardekani, Mechanical Engineering, Purdue University  \nMilestones & Deliverables  \n• Liposomes, with their biocompatibility, non-toxicity, and versatile substance-carrying capacity, serve as ideal vehicles  \nfor drug distribution and delivery.  \nEmpty  \nliposome   \n Drug-loaded  \nliposome  \n• A representative spectral profile of each nanomaterial is distinctive, which can be used to map drug loading and classify different nanoparticles.  \nHyperspectral Imaging System  \nHyperspectral imaging (HSI) provides both spectral and spatial information  \n• HSI techniques have emerged as smart analytical tools to cope with the increasing demand to attain both spectral and spatial information.  \n\n| SAM-SVM Algorithm Workflow |\n| --- |\n|  |\n| • For each nanoparticle type, spectral libraries are generated using spectral angle matching (SAM) method.\u003Cbr>• Different nanoparticles are classified through support vector machine (SVM) and convolutional neural network (CNN) techniques.\u003Cbr>Lipid Nanoparticle Characterization\u003Cbr>\u003Cbr>[1] Batrakova et al. 2022, U.S. Patent\u003Cbr>• By offering high-resolution spatial imaging and spectral characterization, the investigation into LNP drug loading becomes achievable.\u003Cbr>• Hyperspectral imaging can reveal hidden features of LNPs. |\n\nConvolutional Neural Network  \n• Compared to SVM model, CNN can outperform to capture subtle variations in input data, such as small changes in spectral profiles. This capability enables the effective classification of diverse biological particles.  \n• Advances in automated classification using CNN with hyperspectral datasets can expands our understanding of biophysical and chemical properties of nanoparticles.  \n• Given the nature of HSI data with multiple spectral bands, we need to adapt the CNN model architecture to effectively capture and process spectral information.  \nMultiple Particles Classification  \nEmpty liposome Drug-loaded liposome  \n• Liposomes are versatile molecules and can be classified in several ways based on their diversity and chemical properties.  \n• From label-free hyperspectral images, unique reference spectral profiles for each bio-nanoparticle.  \n• Independent imaging of both empty and drug loaded liposomes is conducted, and the resulting data are employed to train the machine learning model.  \nAcknowledgments  \n• We are grateful to the NSF Center for Bioanalytic Metrology for providing funding for this project, and to industry members of the CBM for valuable discussions.","cbCail64Pr8vK9nc","https://ap.wps.com/l/cbCail64Pr8vK9nc","pdf",709524,"English","# Milestones & Deliverables\n## Liposome role in drug delivery\n## Representative spectral profiles and drug loading mapping\n# Hyperspectral Imaging System\n## Spectral and spatial information\n## HSI as smart analytical tools\n# SAM-SVM Algorithm Workflow\n## Spectral angle matching library generation\n## SVM and CNN classification\n# Lipid Nanoparticle Characterization\n## High-resolution spatial imaging and spectral characterization\n## Hidden feature discovery\n# Convolutional Neural Network\n## Capturing subtle spectral variations\n## Multi-band architecture adaptation\n# Multiple Particles Classification\n## Label-free reference spectral profiles\n## Training with empty and drug-loaded imaging\n# Acknowledgments","[{\"question\":\"Why are liposomes used as a focus for biological particle characterization?\",\"answer\":\"Liposomes are biocompatible, non-toxic, and can carry versatile substances, making them ideal vehicles for drug distribution and delivery.\"},{\"question\":\"How does the presentation’s SAM-SVM workflow build and use spectral data?\",\"answer\":\"It generates spectral libraries for each nanoparticle type using spectral angle matching (SAM), then classifies nanoparticles using support vector machine (SVM) and convolutional neural network (CNN) techniques.\"},{\"question\":\"What advantages does CNN provide compared with SVM in this framework?\",\"answer\":\"CNN can outperform SVM in capturing subtle input variations, such as small changes in spectral profiles, enabling effective classification across diverse biological particles.\"}]","Characterization of Biological Particles Using an Integrated Hyperspectral Imaging and Machine Learning | PDF"]