{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T17:57:53Z","timestamp":1791223073557,"version":"4.1.0"},"reference-count":39,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:00:00Z","timestamp":1791158400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000288","name":"Royal Society","doi-asserted-by":"publisher","award":["NA"],"award-info":[{"award-number":["NA"]}],"id":[{"id":"10.13039\/501100000288","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Electrospun nanocomposite biomaterials are promising candidates for blood-contacting medical devices owing to their high surface area, tunable nanoscale morphology, and biomimetic replication of the native extracellular matrix. However, conventional hemocompatibility assessments rely heavily on biological assays. These methods require blood samples, specialized reagents, and consumables, thereby inherently increasing costs, resource demands, and laboratory waste. To mitigate these limitations, sustainable evaluation strategies that leverage physicochemical features are highly desirable.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methodology<\/jats:title>\n                    <jats:p>In this study, we present a deep learning framework for predicting the hemocompatibility of electrospun nanofibres directly from scanning electron microscopy (SEM) images. Pretrained convolutional neural network models, namely VGG19, ResNet50, and InceptionV3, were fine-tuned to classify scanning electron microscopy (SEM) images of nanofibres as haemocompatible or non-haemocompatible. To ensure data robustness, an Albumentations-based augmentation strategy was implemented, and predictive reliability was further optimized using a majority-voting ensemble learning approach.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among the individual architectures evaluated, InceptionV3 demonstrated superior performance, achieving a precision of 0.98, a recall of 1.00, and an F1-score of 0.99. The ensemble model exhibited comparable robustness, reaching an overall accuracy of 99%. Furthermore, explainable AI (XAI) techniques, specifically LIME and Integrated Gradients, confirmed that the network\u2019s predictions were driven by physiologically relevant microstructural features of the nanofibres.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This artificial intelligence-assisted, SEM image-based physicochemical approach offers an eco-friendly pre-screening strategy that significantly reduces reliance on blood-based assays and associated laboratory consumables. Ultimately, this framework aligns with ISO 10993 guidelines by using SEM-derived physicochemical information as a pre-screening tool to support subsequent biological evaluation, thereby enabling efficient, regulatory-compliant biomaterial development.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0359594","type":"journal-article","created":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T17:32:39Z","timestamp":1791221559000},"page":"e0359594","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Sustainable hemocompatibility prediction of electrospun nanomaterials using SEM-driven CNN ensemble learning aligned with ISO 10993"],"prefix":"10.1371","volume":"21","author":[{"given":"Narasimhan","family":"Kumaravelu","sequence":"first","affiliation":[{"name":"SASTRA Deemed to be University","place":["Thanjavur, Tamil Nadu, India"],"department":["School of Electrical and Electronics Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adalarasu","family":"Kanagasabai","sequence":"additional","affiliation":[{"name":"SASTRA Deemed to be University","place":["Thanjavur, Tamil Nadu, India"],"department":["School of Electrical and Electronics Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1718-6167","authenticated-orcid":true,"given":"Preetham Raj","family":"Aravindan","sequence":"additional","affiliation":[{"name":"SASTRA Deemed to be University","place":["Thanjavur, Tamil Nadu, India"],"department":["School of Electrical and Electronics Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Surya Murugan","family":"Moorthy Sathyanarayana","sequence":"additional","affiliation":[{"name":"SASTRA Deemed to be University","place":["Thanjavur, Tamil Nadu, India"],"department":["School of Electrical and Electronics Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2785-137X","authenticated-orcid":true,"given":"Saravana Kumar","family":"Jaganathan","sequence":"additional","affiliation":[{"name":"Institute of Research and Development, Duy Tan University","place":["Da Nang, Vietnam"]},{"name":"Duy Tan University","place":["Da Nang, Vietnam"],"department":["School of Engineering & Technology"]},{"name":"University of Leicester","place":["Leicester, United Kingdom"],"department":["Biomedical Engineering Research Group, School of Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,5]]},"reference":[{"key":"pone.0359594.ref001","unstructured":"Grand View Research. Biomaterials Market Size, Share & Trends Analysis Report, 2024\u20132030. 2024."},{"issue":"1","key":"pone.0359594.ref002","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1002\/adhm.201100021","article-title":"Electrospun nanofibers for regenerative medicine","volume":"1","author":"W Liu","year":"2012","journal-title":"Adv Healthc Mater"},{"issue":"1","key":"pone.0359594.ref003","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1186\/s13036-022-00286-9","article-title":"A critical review of fibrous polyurethane-based vascular tissue engineering scaffolds","volume":"16","author":"S Fathi-Karkan","year":"2022","journal-title":"J Biol Eng"},{"issue":"8","key":"pone.0359594.ref004","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1007\/s13205-018-1356-2","article-title":"Electrospun polyurethane nanofibrous composite impregnated with metallic copper for wound-healing application","volume":"8","author":"SK Jaganathan","year":"2018","journal-title":"3 Biotech"},{"issue":"10","key":"pone.0359594.ref005","article-title":"Engineering electrospun multicomponent polyurethane scaffolding platform comprising grapeseed oil and honey\/propolis for bone tissue regeneration","volume":"13","author":"CY Chao","year":"2018","journal-title":"PLoS One"},{"key":"pone.0359594.ref006","year":"2017"},{"issue":"5","key":"pone.0359594.ref007","doi-asserted-by":"crossref","first-page":"1285","DOI":"10.1109\/TMI.2016.2528162","article-title":"Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning","volume":"35","author":"H-C Shin","year":"2016","journal-title":"IEEE Trans Med Imaging"},{"key":"pone.0359594.ref008","author":"K He","year":"2015"},{"key":"pone.0359594.ref009","author":"K Simonyan","year":"2014"},{"issue":"15","key":"pone.0359594.ref010","doi-asserted-by":"crossref","first-page":"2223","DOI":"10.1016\/S0266-3538(03)00178-7","article-title":"A review on polymer nanofibers by electrospinning and their applications in nanocomposites","volume":"63","author":"Z-M Huang","year":"2003","journal-title":"Composites Science and Technology"},{"issue":"11","key":"pone.0359594.ref011","doi-asserted-by":"crossref","first-page":"7440","DOI":"10.1039\/D3RA08738G","article-title":"Surface modification strategies for improved hemocompatibility of polymeric materials: A comprehensive review","volume":"14","author":"A Bhattacharjee","year":"2024","journal-title":"RSC Adv"},{"issue":"1","key":"pone.0359594.ref012","doi-asserted-by":"crossref","first-page":"184","DOI":"10.3390\/biom13010184","article-title":"Recent progress of electrospun herbal medicine nanofibres","volume":"13","author":"H Liu","year":"2023","journal-title":"Biomolecules"},{"issue":"1","key":"pone.0359594.ref013","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1108\/PRT-07-2020-0072","article-title":"Physico-chemical and mechanical properties of novel electrospun polyurethane composite with enhanced blood compatibility","volume":"51","author":"MP Mani","year":"2021","journal-title":"PRT"},{"issue":"5","key":"pone.0359594.ref014","doi-asserted-by":"crossref","first-page":"1315","DOI":"10.3892\/etm.2021.10750","article-title":"Biocompatibility assessment of biomaterials used in orthopedic devices: An overview (Review)","volume":"22","author":"B Huzum","year":"2021","journal-title":"Exp Ther Med"},{"key":"pone.0359594.ref015","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/B978-0-08-100497-5.00004-5","article-title":"Developing standards and test protocols for testing the hemocompatibility of biomaterials","volume-title":"Hemocompatibility of Biomaterials for Clinical Applications","author":"S Braune","year":"2018"},{"issue":"7","key":"pone.0359594.ref016","doi-asserted-by":"crossref","first-page":"1590","DOI":"10.3390\/cancers13071590","article-title":"Novel transfer learning approach for medical imaging with limited labeled data","volume":"13","author":"L Alzubaidi","year":"2021","journal-title":"Cancers (Basel)"},{"issue":"5","key":"pone.0359594.ref017","doi-asserted-by":"crossref","first-page":"327","DOI":"10.3390\/machines10050327","article-title":"Research of U-Net-Based CNN architectures for metal surface defect detection","volume":"10","author":"I Konovalenko","year":"2022","journal-title":"Machines"},{"key":"pone.0359594.ref018","first-page":"100135","article-title":"Classification of scanning electron microscope images of pharmaceutical excipients using deep convolutional neural networks with transfer learning","volume":"4","author":"H Iwata","year":"2022","journal-title":"Int J Pharm X"},{"issue":"4","key":"pone.0359594.ref019","doi-asserted-by":"crossref","DOI":"10.1002\/widm.1249","article-title":"Ensemble learning: A survey","volume":"8","author":"O Sagi","year":"2018","journal-title":"WIREs Data Min & Knowl"},{"issue":"18","key":"pone.0359594.ref020","doi-asserted-by":"crossref","first-page":"5278","DOI":"10.3390\/ma14185278","article-title":"Artificial intelligence aided design of tissue engineering scaffolds employing virtual tomography and 3D convolutional neural networks","volume":"14","author":"MD Bermejillo Barrera","year":"2021","journal-title":"Materials"},{"issue":"5","key":"pone.0359594.ref021","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1109\/TMI.2016.2535302","article-title":"Convolutional neural networks for medical image analysis: Full training or fine tuning?","volume":"35","author":"N Tajbakhsh","year":"2016","journal-title":"IEEE Trans Med Imaging"},{"key":"pone.0359594.ref022","doi-asserted-by":"crossref","DOI":"10.7717\/peerj-cs.1031","article-title":"Ensemble of adapted convolutional neural networks (CNN) methods for classifying colon histopathological images","volume":"8","author":"D Albashish","year":"2022","journal-title":"PeerJ Comput Sci"},{"key":"pone.0359594.ref023","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1007\/978-981-15-1967-3_8","article-title":"Ensemble Learning","author":"Z-H Zhou","year":"2021","journal-title":"Machine Learning. Springer Singapore"},{"key":"pone.0359594.ref024","doi-asserted-by":"crossref","unstructured":"Ribeiro MT, Singh S, Guestrin C. Why should I trust you?: Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016. 1135\u201344. https:\/\/doi.org\/10.1145\/2939672.2939778","DOI":"10.1145\/2939672.2939778"},{"key":"pone.0359594.ref025","first-page":"3699","article-title":"Machine learning in biomaterials, biomechanics\/mechanobiology, and biofabrication: State of the art and perspective","volume":"31","author":"C Wu","year":"2024","journal-title":"Archives of Computational Methods in Engineering"},{"key":"pone.0359594.ref026","article-title":"Explainable Artificial Intelligence for Breast Tumour Classification: Helpful or Harmful.","author":"A Rafferty","year":"2022","journal-title":"Interpretability of Machine Intelligence in Medical Image Computing. iMIMIC 2022. Lecture Notes in Computer Science, vol 13611. Springer, Cham"},{"issue":"4","key":"pone.0359594.ref027","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1007\/s00424-024-02997-y","article-title":"Explainable artificial intelligence for spectroscopy data: A review","volume":"477","author":"J Contreras","year":"2025","journal-title":"Pflugers Arch"},{"key":"pone.0359594.ref028","author":"M Sundararajan","year":"2017"},{"issue":"2","key":"pone.0359594.ref029","doi-asserted-by":"crossref","first-page":"125","DOI":"10.3390\/info11020125","article-title":"Albumentations: Fast and flexible image augmentations","volume":"11","author":"A Buslaev","year":"2020","journal-title":"Information"},{"issue":"3","key":"pone.0359594.ref030","doi-asserted-by":"crossref","first-page":"932","DOI":"10.1038\/s41591-024-03416-6","article-title":"A generalist medical language model for disease diagnosis assistance","volume":"31","author":"X Liu","year":"2025","journal-title":"Nat Med"},{"issue":"13","key":"pone.0359594.ref031","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1049\/el:20080522","article-title":"Scope of validity of PSNR in image\/video quality assessment","volume":"44","author":"Q Huynh-Thu","year":"2008","journal-title":"Electron Lett"},{"issue":"7","key":"pone.0359594.ref032","doi-asserted-by":"crossref","DOI":"10.1007\/s10586-025-05281-5","article-title":"Explainable artificial intelligence for medical imaging systems using deep learning: a comprehensive review","volume":"28","author":"EH Houssein","year":"2025","journal-title":"Cluster Comput"},{"key":"pone.0359594.ref033","first-page":"109559","article-title":"The effectiveness of data augmentation in porous substrate, nanowire, fiber and tip images at the level of deep learning intelligence","volume":"202","author":"K Yao","year":"2021","journal-title":"Materials & Design"},{"key":"pone.0359594.ref034","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","article-title":"Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI","volume":"58","author":"A Barredo Arrieta","year":"2020","journal-title":"Information Fusion"},{"issue":"11","key":"pone.0359594.ref035","doi-asserted-by":"crossref","first-page":"1335","DOI":"10.2217\/nnm-2017-0017","article-title":"Recent advances in electrospun nanofibers for wound healing","volume":"12","author":"S Chen","year":"2017","journal-title":"Nanomedicine (Lond)"},{"key":"pone.0359594.ref036","first-page":"435","article-title":"Product evaluation: Blood compatibility studies","author":"A Bhatt","year":"2023","journal-title":"Biomed Prod Mater Eval"},{"key":"pone.0359594.ref037","doi-asserted-by":"crossref","first-page":"1288539","DOI":"10.3389\/fbioe.2023.1288539","article-title":"Biomimetic electrospun nanofibrous scaffold for tissue engineering: Preparation, optimization by design of experiments (DOE), in-vitro and in-vivo characterization","volume":"11","author":"S Anjum","year":"2023","journal-title":"Front Bioeng Biotechnol"},{"issue":"2","key":"pone.0359594.ref038","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1021\/acsbiomaterials.0c01589","article-title":"Hemocompatibility evaluation of biomaterials-The crucial impact of analyzed area","volume":"7","author":"JC Clauser","year":"2021","journal-title":"ACS Biomater Sci Eng"},{"key":"pone.0359594.ref039","doi-asserted-by":"crossref","first-page":"14095","DOI":"10.1007\/s10853-024-09994-7","article-title":"Machine learning applications for electrospun nanofibres: A review","volume":"59","author":"B Subeshan","year":"2024","journal-title":"J Mater Sci"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0359594","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T17:32:48Z","timestamp":1791221568000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0359594"}},"subtitle":[],"editor":[{"given":"Christophe","family":"Egles","sequence":"first","affiliation":[{"name":"Universit\u00e9 de Rouen Normandie","place":["FRANCE"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,5]]},"references-count":39,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,5]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0359594","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,5]]}}}