[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127330-en":3,"doc-seo-127330-105":30,"detail-sidebar-cat-0-en-105":92},{"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":20,"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":29},127330,962085570644,"Evangeline","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Machine learning pipeline for microparticle size classification in self-mixing interferometric signals for flow cytometry","Self-mixing interferometry (SMI) enables compact, label-free microparticle sensing for flow cytometry, but reliable size classification is hindered by noise, experimental variability, and limited interpretability of signal modulation during particle passage. This research integrates machine learning models into the SMI processing chain to strengthen feature extraction and improve classification robustness under practical conditions. Three ML pipelines are assessed, reaching 98% accuracy for discriminating particle sizes of 2, 4, and 10 µm. The results indicate scalable deployment for diverse particle analysis tasks, supporting medical diagnostics and industrial quality control.","TYPE Original Research PUBLISHED 05 September 2025 DOI 10.3389/fsens.2025.1662060  \nOPEN ACCESS  \nEDITED BY  \nLi-Peng Sun,  \nJinan University, China  \nREVIEWED BY  \nYanzhen Tan,  \nDongguan University of Technology, China Fei Xie,  \nHandan University, China  \n*CORRESPONDENCE  \nAdam Quotb,  \n [adam.quotb@laas.fr](adam.quotb@laas.fr)  \nRECEIVED 08 July 2025  \nACCEPTED 18 August 2025  \nPUBLISHED 05 September 2025  \nCITATION  \nSierra-Alarcón S, Perchoux J, Tronche C, Jayat F and Quotb A (2025) Machine learning pipeline for microparticle size classification in self-mixing interferometric signals for flow cytometry.  \nFront. Sens. 6:1662060 .  \ndoi: 10.3389/fsens.2025.1662060  \nCOPYRIGHT  \n© 2025 Sierra-Alarcón, Perchoux, Tronche, Jayat and Quotb. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.  \nMachine learning pipeline for microparticle size classification in self-mixing interferometric signals for flow cytometry  \nSebastián Sierra-Alarcón, Julien Perchoux, Clément Tronche, Francis Jayat and Adam Quotb*  \nINP, CNRS, LAAS-CNRS, Université de Toulouse, Toulouse, France  \nSelf-mixing interferometry (SMI) is an emerging optical sensing technique for detecting and classifying microparticles in non-contact and label-free flowmetry applications. High precision and reliability are essential for its integration into medical diagnostics, such as blood analysis, and quality control in chemical manufacturing processes. While theoretical models describe SMI-induced signal modulations caused by particle passage, challenges persist due to signal noise, variability, and interpretability under experimental conditions. This study enhances SMI-based particle size classification by integrating machine learning (ML) models to improve feature extraction and classification accuracy. Three ML pipelines are evaluated, achieving 98% classification accuracy in distinguishing particles of different sizes (2, 4, and 10 µm) . The high classification accuracy demonstrates the scalability of our approach, ensuring its applicability across diverse particle analysis scenarios.  \nKEYWORDS  \nself-mixing interferometry, micro-particle size classification, machine learning, flow citometry, signal processing  \n1 Introduction  \nSelf-mixing interferometry (SMI), also known as optical feedback interferometry (OFI), has gained significant attention due to its versatility and cost-effectiveness in sensing applications (Perchoux et al., 2016; Donati and Norgia, 2014; Quotb et al., 2021; Taimreet al., 2015). This laser-based technique relies on the interference between emitted laser light and backscattered light from an external target, enabling the development of compact, lowcost, and high-resolution optical sensors. One of the key research areas in SMI is its application in a microfluidic context, particularly for single-particle analysis, with the goal of establishing an SMI-based label-free flow cytometry system for medical sensing.  \nSince the initial demonstrations of detecting submicron and micron particles using SMI sensing, substantial progress has been made in understanding the signal modulation induced by single-particle interactions with the laser beam (Da Costa Moreira et al., 2017; Herbert et al., 2018) . These advances have enabled detection of particles as small as 100 nm (Zhao et al., 2023a) and led to the development of analytical models that enhance our understanding of SMI signals. This progress has also paved the way for the first SMIbased flow cytometers, capable of detecting polystyrene beads and even classifying cancer cells (Zhao [Y. et](Y. et) al., 2020; Zhao et al., 2019","cbCairJR4ZuAC7ae","https://ap.wps.com/l/cbCairJR4ZuAC7ae","pdf",2155673,1,12,"English","en",105,"# Introduction\n## Self-mixing interferometry and sensing context\n## Signal-processing challenges for microparticle classification\n## Machine learning motivation and pipeline overview","[{\"question\":\"What problem does the study address in SMI-based flow cytometry?\",\"answer\":\"It targets persistent difficulties in extracting clear particle signatures from noisy SMI signals and improving reliable microparticle size classification under experimental variability.\"},{\"question\":\"How does the proposed approach improve particle size classification?\",\"answer\":\"It integrates machine learning models into the SMI signal processing workflow to enhance feature extraction and classification accuracy beyond classical signal processing alone.\"},{\"question\":\"What classification performance is reported for different particle sizes?\",\"answer\":\"The evaluated ML pipelines achieve 98% accuracy for distinguishing microparticles with sizes of 2, 4, and 10 µm.\"}]","Machine learning pipeline for microparticle size classification in self-mixing interferometric signals for flow cytometry | PDF",1785938324,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"machine-learning-pipeline-for-microparticle-size-classication-in-self-mixing-interferometric-signals-for-ow-cytometry","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-pipeline-for-microparticle-size-classication-in-self-mixing-interferometric-signals-for-ow-cytometry/127330/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-22","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the study address in SMI-based flow cytometry?","Question",{"text":76,"@type":77},"It targets persistent difficulties in extracting clear particle signatures from noisy SMI signals and improving reliable microparticle size classification under experimental variability.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the proposed approach improve particle size classification?",{"text":81,"@type":77},"It integrates machine learning models into the SMI signal processing workflow to enhance feature extraction and classification accuracy beyond classical signal processing alone.",{"name":83,"@type":74,"acceptedAnswer":84},"What classification performance is reported for different particle sizes?",{"text":85,"@type":77},"The evaluated ML pipelines achieve 98% accuracy for distinguishing microparticles with sizes of 2, 4, and 10 µm.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":122},"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]