[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119506-en":3,"doc-seo-119506-105":29,"detail-sidebar-cat-0-en-105":89},{"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":11},119506,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Shape-based nanoparticle classification using machine learning - Workshop on Statistical and Machine Learning","Accurate nanoparticle (NP) classification by shape is essential for linking physical-chemical properties to bioactivity. Modern synthesis can produce diverse shapes, yet they are often characterized qualitatively. This study extracts NP contours from electron microscopy images to compute shape descriptors, including Fourier descriptors, aspect ratio, compactness, extent, irregularity, solidity, convexity, and Hu moment invariants. These descriptors feed machine learning models such as XGBoost, Random Forest, and neural networks, and their performances are compared using standard classification metrics.","Technological University Dublin  \nARROW@TU Dublin  \n\n| SAML-25 Workshop on Statistical and Machine Learning | Research Institutes/Centres/Groups |\n| --- | --- |\n| 2025-06-05\u003Cbr>Shape-based nanoparticle classification using machine learning\u003Cbr>Caitlin Caitlin Robertson\u003Cbr>TU Dublin, [c21495162@mytudublin.ie](c21495162@mytudublin.ie)\u003Cbr>Hender Lopez\u003Cbr>Technological University Dublin, [hender.lopezsilva@tudublin.ie](hender.lopezsilva@tudublin.ie)\u003Cbr>Follow this and additional works at: [https://arrow.tudublin.ie/saml](https://arrow.tudublin.ie/saml)\u003Cbr> Part of the Statistics and Probability Commons |  |\n\nRecommended Citation  \nCaitlin Robertson, Caitlin and Lopez, Hender, \"Shape-based nanoparticle classification using machine learning\" (2025) . SAML-25 Workshop on Statistical and Machine Learning. 21.  \n[https://arrow.tudublin.ie/saml/21](https://arrow.tudublin.ie/saml/21)  \nThis Conference Paper is brought to you by the EUt+ Academic Press a free to read and publish press of the European University of Technology.  \nThis work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.  \nShape-based nanoparticle classification using machine learning  \nCaitlin Robertson∗ [C21495162@mytudublin.ie](C21495162@mytudublin.ie)[ ](C21495162@mytudublin.ie)TU Dublin Dublin, Ireland  \nHender Lopez  \nTU Dublin Dublin, Ireland  \n[hender.lopezsilva@tudublin.ie](hender.lopezsilva@tudublin.ie)  \nAbstract  \nThe accurate classification of nanoparticles (NPs) based on their shapes is crucial for understanding their physical-chemical properties and predict their bioactivity. Nowadays, synthesis method are able to produce a broad range of shapes, such as spheres, cubes and branched NPs and commonly these NP shapes are only described qualitative. This study presents NP descriptors obtained from NPs contours extracted from electron microscopy images. Descriptors such as Fourier descriptors, aspect ratio, and compactness are then used as input for machine learning classifiers. In particular, XGBoost, Random Forest, and neural networks are explored and the their performances are compared and discussed.  \nKeywords  \nNanoparticle classification, Shape descriptors, Electron microscopy, Machine learning, XGBoost, Random Forest, Neural networks, Fourier descriptors, Hu moments, Principal Component Analysis (PCA), Image analysis  \n1 Introduction  \nIt has been shown that the shape of nanoparticles (NPs) plays a critical role in determining their cellular uptake, interactions with biomolecules, and in vivo bioactivity when exposed to living organisms [3] . Advances in synthesis methods now allow for the production of NPs in a wide variety of shapes, however, these shapes are typically described only qualitatively. Furthermore, quantitative measurement of the variability of these shapes has only recently been developed and is based on Fourier coefficients extracted from contours and then used as descriptors for unsupervised machine learning methods [2][4][1] . Despite the good classification performance reported in these works, the geometrical interpretation and their connection to physical-chemical properties of the NPs isnot straightforward. In this work, more intuitive shape descriptors are used to perform the classification of NP shapes. Using these descriptors, different machine learning algorithms are compared.  \n2 Results  \nThe contours of NPs used in this work are obtained from transmission electron microscopy and are available in [1] . The dataset of contours has 4 different NPs shapes: spheres, rods, urchin (spheroids with small tips) and stars (spheroids with long per) . The geometric properties used as descriptors are: the aspect ratio (the ratio of the major axis to the minor axis of the bounding ellipse around the contour), compactness (measures the similarity of the shape to a perfect circle), extent (measured as the ratio of the area of the contour to the area of its bounding box), irregularity (measures ","cbCaicjdiHwVrXoJ","https://ap.wps.com/l/cbCaicjdiHwVrXoJ","pdf",979105,1,3,"English","en",105,"# Abstract\n# Introduction\n# Results","[{\"question\":\"Why is shape-based nanoparticle classification important?\",\"answer\":\"The shape of nanoparticles affects cellular uptake, interactions with biomolecules, and in vivo bioactivity. Quantitative shape characterization helps move beyond purely qualitative descriptions.\"},{\"question\":\"What data and shape descriptors are used in the study?\",\"answer\":\"Contours are extracted from transmission electron microscopy images, then converted into geometric descriptors such as aspect ratio, compactness, extent, irregularity, solidity, convexity, and Hu moment invariants; Fourier coefficients are also considered.\"},{\"question\":\"Which machine learning methods perform best, and how are they evaluated?\",\"answer\":\"XGBoost achieves the highest accuracy (98.36%) and F1-score (98.90%). Models are evaluated using accuracy, precision, recall, and F1-score, with PCA reducing accuracy and removing Fourier descriptors further decreasing performance.\"}]","Shape-based nanoparticle classification using machine learning - Workshop on Statistical and Machine Learning | PDF",1785724695,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":84,"head_meta":86,"extra_data":88,"updated_unix":28},"shape-based-nanoparticle-classification-using-machine-learning-workshop-on-statistical-and-machine-learning","",{"@graph":35,"@context":83},[36,52,66],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,49],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":21},"https://docshare.wps.com/document/research-report/",{"item":50,"name":13,"@type":42,"position":51},"https://docshare.wps.com/document/shape-based-nanoparticle-classification-using-machine-learning-workshop-on-statistical-and-machine-learning/119506/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":23,"description":14,"dateModified":60,"datePublished":60,"encodingFormat":59,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":40,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":63,"interactionType":64,"userInteractionCount":4},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69,75,79],{"name":70,"@type":71,"acceptedAnswer":72},"Why is shape-based nanoparticle classification important?","Question",{"text":73,"@type":74},"The shape of nanoparticles affects cellular uptake, interactions with biomolecules, and in vivo bioactivity. Quantitative shape characterization helps move beyond purely qualitative descriptions.","Answer",{"name":76,"@type":71,"acceptedAnswer":77},"What data and shape descriptors are used in the study?",{"text":78,"@type":74},"Contours are extracted from transmission electron microscopy images, then converted into geometric descriptors such as aspect ratio, compactness, extent, irregularity, solidity, convexity, and Hu moment invariants; Fourier coefficients are also considered.",{"name":80,"@type":71,"acceptedAnswer":81},"Which machine learning methods perform best, and how are they evaluated?",{"text":82,"@type":74},"XGBoost achieves the highest accuracy (98.36%) and F1-score (98.90%). Models are evaluated using accuracy, precision, recall, and F1-score, with PCA reducing accuracy and removing Fourier descriptors further decreasing performance.","https://schema.org",{"og:url":50,"og:type":85,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":87,"canonical":50},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":90},[91,95,99,103,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":92,"show_sort_weight":93,"slug":94},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":96,"show_sort_weight":97,"slug":98},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":45,"category_name":100,"show_sort_weight":101,"slug":102},"Exam",70,"exam",{"id":104,"doc_module":4,"doc_module_name":45,"category_name":105,"show_sort_weight":106,"slug":107},5,"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":104,"slug":136},19,"General","general"]