{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T18:04:41Z","timestamp":1785175481291,"version":"3.55.0"},"reference-count":28,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T00:00:00Z","timestamp":1785110400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["22K15675"],"award-info":[{"award-number":["22K15675"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016846","name":"Shimadzu","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016846","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008660","name":"Kurozumi Medical Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008660","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Morinomiyako Medical Research Foundation"},{"name":"Charitable Trust Laboratory Medical Research Promotion Fund"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>The morphological classification of microbial cultures and colonies requires specialized knowledge and experience; therefore, automation in this field remains limited. This study examines the feasibility of automating the identification of pathogenic microbial species from colony images of cultured microorganisms.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Two distinct image datasets were constructed for 10 clinically relevant species: a colony image dataset, consisting of individual colony images cropped, and a tile image dataset, generated by dividing entire images of the culture plate into tiles. Separate ResNet-50\u2013based models were trained in each dataset, and their outputs were integrated to evaluate the classification performance. Training was conducted using 10,048 colony images and 23,003 tile images collected from 418 strains, and performance was assessed with five-fold cross-validation (K\u2009=\u20095).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The colony image model achieved a sensitivity of 0.934 and a specificity of 0.993, while the tile image model achieved a sensitivity of 0.918 and a specificity of 0.991. Integration of the two models into an ensemble model further improved performance, yielding a sensitivity of 0.955 and a specificity of 0.995 when tested on 76 independent strains.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The ensemble model approach provides high accuracy and robustness, suggesting its potential technical contributions to microbial identification in clinical microbiology laboratories.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0353761","type":"journal-article","created":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T17:37:22Z","timestamp":1785173842000},"page":"e0353761","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual-input deep learning system for microbial identification from blood agar plates"],"prefix":"10.1371","volume":"21","author":[{"given":"Takao","family":"Naito","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5519-7408","authenticated-orcid":true,"given":"Satomi","family":"Takei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shigeki","family":"Misawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miyuki","family":"Kuribara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3734-0346","authenticated-orcid":true,"given":"Yoko","family":"Tabe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,7,27]]},"reference":[{"issue":"1","key":"pone.0353761.ref001","doi-asserted-by":"crossref","first-page":"6839","DOI":"10.4081\/idr.2017.6839","article-title":"Advances in Rapid Identification and Susceptibility Testing of Bacteria in the Clinical Microbiology Laboratory: Implications for Patient Care and Antimicrobial Stewardship Programs","volume":"9","author":"FP Maurer","year":"2017","journal-title":"Infect Dis Rep"},{"issue":"8","key":"pone.0353761.ref002","doi-asserted-by":"crossref","DOI":"10.1128\/jcm.00241-22","article-title":"The Hidden Crisis in the Times of COVID-19: Critical Shortages of Medical Laboratory Professionals in Clinical Microbiology","volume":"60","author":"AL Leber","year":"2022","journal-title":"J Clin Microbiol"},{"key":"pone.0353761.ref003","doi-asserted-by":"crossref","first-page":"1200994","DOI":"10.3389\/frai.2023.1200994","article-title":"Machine learning algorithms in microbial classification: a comparative analysis","volume":"6","author":"Y Wu","year":"2023","journal-title":"Front Artif Intell"},{"issue":"6","key":"pone.0353761.ref004","article-title":"A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis","volume":"1","author":"X Liu","year":"2019","journal-title":"Lancet Digit Health"},{"issue":"7","key":"pone.0353761.ref005","article-title":"Deep Learning Frameworks for Rapid Gram Stain Image Data Interpretation: Protocol for a Retrospective Data Analysis","volume":"9","author":"H Kim","year":"2020","journal-title":"JMIR Res Protoc"},{"issue":"9","key":"pone.0353761.ref006","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0184554","article-title":"Deep learning approach to bacterial colony classification","volume":"12","author":"B Zieli\u0144ski","year":"2017","journal-title":"PLoS One"},{"key":"pone.0353761.ref007","author":"S Majchrowska","year":"2021"},{"issue":"9","key":"pone.0353761.ref008","doi-asserted-by":"crossref","DOI":"10.1128\/spectrum.02885-24","article-title":"Implementation of convolutional neural networks for microbial colony recognition","volume":"13","author":"F Kong","year":"2025","journal-title":"Microbiol Spectr"},{"issue":"3","key":"pone.0353761.ref009","doi-asserted-by":"crossref","DOI":"10.3390\/app16031313","article-title":"Bacterial colony counting and classification system based on deep learning model","volume":"16","author":"C Pintavirooj","year":"2026","journal-title":"Appl Sci"},{"issue":"19","key":"pone.0353761.ref010","doi-asserted-by":"crossref","first-page":"10568","DOI":"10.3390\/app131910568","article-title":"Microbial Colony Detection Based on Deep Learning","volume":"13","author":"F Yang","year":"2023","journal-title":"Appl Sci"},{"issue":"11","key":"pone.0353761.ref011","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Y Lecun","year":"1998","journal-title":"Proc IEEE"},{"issue":"1","key":"pone.0353761.ref012","doi-asserted-by":"crossref","first-page":"13385","DOI":"10.1038\/s41598-019-49942-z","article-title":"A novel automated image analysis system using deep convolutional neural networks can assist to differentiate MDS and AA","volume":"9","author":"K Kimura","year":"2019","journal-title":"Sci Rep"},{"issue":"6","key":"pone.0353761.ref013","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"ImageNet classification with deep convolutional neural networks","volume":"60","author":"A Krizhevsky","year":"2017","journal-title":"Commun ACM"},{"key":"pone.0353761.ref014","author":"K Simonyan","year":"2014"},{"issue":"2","key":"pone.0353761.ref015","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1109\/72.279181","article-title":"Learning long-term dependencies with gradient descent is difficult","volume":"5","author":"Y Bengio","year":"1994","journal-title":"IEEE Trans Neural Netw"},{"key":"pone.0353761.ref016","unstructured":"Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of AISTATS. 2010. p. 249\u201356."},{"key":"pone.0353761.ref017","author":"K He","year":"2016"},{"key":"pone.0353761.ref018","article-title":"Efficient ResNets: Residual network design","author":"A Thakur","year":"2023","journal-title":"CVPR"},{"key":"pone.0353761.ref019","article-title":"Biologically inspired deep residual networks for computer vision applications","author":"P Varghese","year":"2022","journal-title":"CVPR"},{"key":"pone.0353761.ref020","doi-asserted-by":"crossref","first-page":"645972","DOI":"10.3389\/fmicb.2021.645972","article-title":"Efficient Detection of Longitudinal Bacteria Fission Using Transfer Learning in Deep Neural Networks","volume":"12","author":"C Garcia-Perez","year":"2021","journal-title":"Front Microbiol"},{"key":"pone.0353761.ref021","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1016\/j.procs.2021.01.025","article-title":"Deep Learning in Image Classification using Residual Network (ResNet) Variants for Detection of Colorectal Cancer","volume":"179","author":"D Sarwinda","year":"2021","journal-title":"Procedia Comput Sci"},{"key":"pone.0353761.ref022","first-page":"833","article-title":"Stochastic neighbor embedding","volume-title":"Advances in Neural Information Processing Systems","author":"GE Hinton","year":"2002"},{"issue":"2","key":"pone.0353761.ref023","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1111\/j.1574-6976.2011.00298.x","article-title":"Applications of MALDI-TOF mass spectrometry in clinical diagnostic microbiology","volume":"36","author":"A Croxatto","year":"2012","journal-title":"FEMS Microbiol Rev"},{"issue":"7","key":"pone.0353761.ref024","doi-asserted-by":"crossref","first-page":"1905","DOI":"10.1007\/s00216-011-4877-7","article-title":"Use of the MALDI BioTyper system with MALDI-TOF mass spectrometry for rapid identification of microorganisms","volume":"400","author":"K Sogawa","year":"2011","journal-title":"Anal Bioanal Chem"},{"key":"pone.0353761.ref025","unstructured":"Clinical and Laboratory Standards Institute (CLSI). Methods for the identification of cultured microorganisms using matrix-assisted laser desorption\/ionization time-of-flight mass spectrometry; Approved Guideline. CLSI document M58. 2017."},{"key":"pone.0353761.ref026","author":"Z Zhang","year":"2018"},{"issue":"7553","key":"pone.0353761.ref027","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"Y LeCun","year":"2015","journal-title":"Nature"},{"key":"pone.0353761.ref028","first-page":"2579","article-title":"Visualization of data using t-SNE","volume":"9","author":"L van der Maaten","year":"2008","journal-title":"J Mach Learn Res"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0353761","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T17:37:27Z","timestamp":1785173847000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0353761"}},"subtitle":[],"editor":[{"given":"Mariselvam","family":"Ramaiah","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7,27]]},"references-count":28,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7,27]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0353761","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,27]]}}}