{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T17:32:57Z","timestamp":1793208777635,"version":"4.5.0"},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2023,10,12]],"date-time":"2023-10-12T00:00:00Z","timestamp":1697068800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000740","name":"University of St Andrews","doi-asserted-by":"publisher","award":["204821\/Z\/16\/Z"],"award-info":[{"award-number":["204821\/Z\/16\/Z"]}],"id":[{"id":"10.13039\/501100000740","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers in Biology and Medicine"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1016\/j.compbiomed.2023.107573","type":"journal-article","created":{"date-parts":[[2023,10,13]],"date-time":"2023-10-13T11:20:40Z","timestamp":1697196040000},"page":"107573","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":6,"special_numbering":"C","title":["Localization and phenotyping of tuberculosis bacteria using a combination of deep learning and SVMs"],"prefix":"10.1016","volume":"167","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0783-4879","authenticated-orcid":false,"given":"Marios","family":"Zachariou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ognjen","family":"Arandjelovi\u0107","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1841-985X","authenticated-orcid":false,"given":"Evelin","family":"Dombay","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4742-2791","authenticated-orcid":false,"given":"Wilber","family":"Sabiiti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bariki","family":"Mtafya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1575-4521","authenticated-orcid":false,"given":"Nyanda Elias","family":"Ntinginya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7888-5449","authenticated-orcid":false,"given":"Derek J.","family":"Sloan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.compbiomed.2023.107573_b1","unstructured":"World Health Organization, Global Tuberculosis Report, Tech. Rep., 2022, URL https:\/\/www.who.int\/teams\/global-tuberculosis-programme\/tb-reports\/global-tuberculosis-report-2022."},{"issue":"6907","key":"10.1016\/j.compbiomed.2023.107573_b2","doi-asserted-by":"crossref","first-page":"759","DOI":"10.1136\/bmj.307.6907.759","article-title":"Tuberculosis and poverty","volume":"307","author":"Spence","year":"1993","journal-title":"Br. Med. J."},{"key":"10.1016\/j.compbiomed.2023.107573_b3","series-title":"End TB strategy","author":"World Health Organization","year":"2015"},{"issue":"6","key":"10.1016\/j.compbiomed.2023.107573_b4","doi-asserted-by":"crossref","first-page":"570","DOI":"10.1016\/S1473-3099(06)70578-3","article-title":"Fluorescence versus conventional sputum smear microscopy for tuberculosis: a systematic review","volume":"9","author":"Steingart","year":"2006","journal-title":"Lancet Infect. Dis."},{"key":"10.1016\/j.compbiomed.2023.107573_b5","series-title":"Global Laboratory Initiative Advancing TB Diagnosis: Mycobacteriology Laboratory Manual","author":"Stop T. B. Partnership","year":"2014"},{"issue":"11","key":"10.1016\/j.compbiomed.2023.107573_b6","doi-asserted-by":"crossref","first-page":"1005","DOI":"10.1056\/NEJMoa0907847","article-title":"Rapid molecular detection of tuberculosis and rifampin resistance","volume":"363","author":"Boehme","year":"2010","journal-title":"N. Engl. J. Med."},{"issue":"6","key":"10.1016\/j.compbiomed.2023.107573_b7","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1016\/S2213-2600(13)70119-X","article-title":"Assessment of the sensitivity and specificity of Xpert MTB\/RIF assay as an early sputum biomarker of response to tuberculosis treatment","volume":"1","author":"Friedrich","year":"2013","journal-title":"Lancet Respir. Med."},{"key":"10.1016\/j.compbiomed.2023.107573_b8","series-title":"WHO Operational Handbook on Tuberculosis. Module 4: Treatment. Drug-Susceptible Tuberculosis Treatment","author":"World Health Organization","year":"2022"},{"key":"10.1016\/j.compbiomed.2023.107573_b9","doi-asserted-by":"crossref","DOI":"10.3389\/frabi.2022.928365","article-title":"Implications of drug-induced phenotypical resistance: Is isoniazid radicalizing M. tuberculosis?","volume":"1","author":"Hammond","year":"2022","journal-title":"Front. Antibiot."},{"issue":"6","key":"10.1016\/j.compbiomed.2023.107573_b10","doi-asserted-by":"crossref","DOI":"10.1371\/journal.ppat.1002093","article-title":"Mycobacterium tuberculosis uses host triacylglycerol to accumulate lipid droplets and acquires a dormancy-like phenotype in lipid-loaded macrophages","volume":"7","author":"Daniel","year":"2011","journal-title":"PLoS Pathog."},{"issue":"4","key":"10.1016\/j.compbiomed.2023.107573_b11","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pmed.0050075","article-title":"Cytological and transcript analyses reveal fat and lazy persister-like bacilli in tuberculous sputum","volume":"5","author":"Garton","year":"2008","journal-title":"PLoS Med."},{"issue":"10","key":"10.1016\/j.compbiomed.2023.107573_b12","doi-asserted-by":"crossref","first-page":"2823","DOI":"10.1093\/jac\/dkv178","article-title":"Phenotypic resistance in mycobacteria: is it because I am old or fat that I resist you?","volume":"70","author":"Hammond","year":"2015","journal-title":"J. Antimicrob. Chemother."},{"issue":"6","key":"10.1016\/j.compbiomed.2023.107573_b13","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0006077","article-title":"A novel in vitro multiple-stress dormancy model for mycobacterium tuberculosis generates a lipid-loaded, drug-tolerant, dormant pathogen","volume":"4","author":"Deb","year":"2009","journal-title":"PLoS One"},{"issue":"1","key":"10.1016\/j.compbiomed.2023.107573_b14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1093\/cid\/civ195","article-title":"Pharmacodynamic modeling of bacillary elimination rates and detection of bacterial lipid bodies in sputum to predict and understand outcomes in treatment of pulmonary tuberculosis","volume":"61","author":"Sloan","year":"2015","journal-title":"Clin. Infect. Dis."},{"issue":"9","key":"10.1016\/j.compbiomed.2023.107573_b15","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/s41579-022-00721-0","article-title":"Types and functions of heterogeneity in mycobacteria","volume":"20","author":"Chung","year":"2022","journal-title":"Nat. Rev. Microbiol."},{"issue":"6064","key":"10.1016\/j.compbiomed.2023.107573_b16","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1126\/science.1216166","article-title":"Asymmetry and aging of mycobacterial cells lead to variable growth and antibiotic susceptibility","volume":"335","author":"Aldridge","year":"2012","journal-title":"Science"},{"issue":"29","key":"10.1016\/j.compbiomed.2023.107573_b17","doi-asserted-by":"crossref","first-page":"8302","DOI":"10.1073\/pnas.1600372113","article-title":"Temporal and intrinsic factors of rifampicin tolerance in mycobacteria","volume":"113","author":"Richardson","year":"2016","journal-title":"Proc. Natl. Acad. Sci."},{"key":"10.1016\/j.compbiomed.2023.107573_b18","doi-asserted-by":"crossref","first-page":"2296","DOI":"10.3389\/fmicb.2017.02296","article-title":"Influence of stress and antibiotic resistance on cell-length distribution in mycobacterium tuberculosis clinical isolates","volume":"8","author":"Vijay","year":"2017","journal-title":"Front. Microbiol."},{"key":"10.1016\/j.compbiomed.2023.107573_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.ebiom.2022.103949","article-title":"Serial measurement of M. tuberculosis in blood from critically-ill patients with HIV-associated tuberculosis","volume":"78","author":"Barr","year":"2022","journal-title":"EBioMedicine"},{"key":"10.1016\/j.compbiomed.2023.107573_b20","article-title":"Priorities for Tuberculosis Bacteriology Services in Low-Income Countries","author":"Rieder","year":"2007","journal-title":"Bull. Int. Union Tuberc. Lung. Dis."},{"key":"10.1016\/j.compbiomed.2023.107573_b21","doi-asserted-by":"crossref","unstructured":"D. Vente, O. Arandjelovi\u0107, V.O. Baron, E. Dombay, S.H. Gillespie, Using Machine Learning for Automatic Estimation of M. Smegmatis Cell Count from Fluorescence Microscopy Images, in: International Workshop on Health Intelligence, 2019, pp. 57\u201368.","DOI":"10.1007\/978-3-030-24409-5_6"},{"key":"10.1016\/j.compbiomed.2023.107573_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.jocs.2022.101775","article-title":"Manifold learning methods for the diagnosis of ovarian cancer","volume":"63","author":"Yesilkaya","year":"2022","journal-title":"J. Comput. Sci."},{"issue":"11","key":"10.1016\/j.compbiomed.2023.107573_b23","doi-asserted-by":"crossref","DOI":"10.1063\/5.0069272","article-title":"Convolutional neural networks predict the onset of paroxysmal atrial fibrillation: Theory and applications","volume":"31","author":"Surucu","year":"2021","journal-title":"Chaos"},{"key":"10.1016\/j.compbiomed.2023.107573_b24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.trsl.2019.06.001","article-title":"Morphology-based classification of mycobacteria-infected macrophages with convolutional neural network: reveal EsxA-induced morphologic changes indistinguishable by naked eyes","volume":"212","author":"Bao","year":"2019","journal-title":"Transl. Res."},{"issue":"10","key":"10.1016\/j.compbiomed.2023.107573_b25","doi-asserted-by":"crossref","first-page":"6314","DOI":"10.1021\/acs.analchem.8b01128","article-title":"Phenotypic antimicrobial susceptibility testing with deep learning video microscopy","volume":"90","author":"Yu","year":"2018","journal-title":"Anal. Chem."},{"issue":"1","key":"10.1016\/j.compbiomed.2023.107573_b26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s42003-019-0480-9","article-title":"High-throughput time-resolved morphology screening in bacteria reveals phenotypic responses to antibiotics","volume":"2","author":"Zahir","year":"2019","journal-title":"Commun. Biol."},{"issue":"8","key":"10.1016\/j.compbiomed.2023.107573_b27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s12046-018-0878-y","article-title":"FHDT: fuzzy and hyco-entropy-based decision tree classifier for tuberculosis diagnosis from sputum images","volume":"43","author":"Mithra","year":"2018","journal-title":"S\u0101dhan\u0101"},{"issue":"7","key":"10.1016\/j.compbiomed.2023.107573_b28","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0218861","article-title":"Image processing for AFB segmentation in bacilloscopies of pulmonary tuberculosis diagnosis","volume":"14","author":"D\u00edaz-Huerta","year":"2019","journal-title":"PLoS One"},{"issue":"2","key":"10.1016\/j.compbiomed.2023.107573_b29","doi-asserted-by":"crossref","first-page":"96","DOI":"10.3390\/info13020096","article-title":"Tuberculosis bacteria detection and counting in fluorescence microscopy images using a multi-stage deep learning pipeline","volume":"13","author":"Zachariou","year":"2022","journal-title":"Information"},{"key":"10.1016\/j.compbiomed.2023.107573_b30","doi-asserted-by":"crossref","unstructured":"O. Ronneberger, P. Fischer, T. Brox, U-net: Convolutional networks for biomedical image segmentation, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, 2015, pp. 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"10.1016\/j.compbiomed.2023.107573_b31","doi-asserted-by":"crossref","unstructured":"M. Zachariou, O. Arandjelovi\u0107, E. Dombay, W. Sabiiti, B. Mtafya, D. Sloan, Extracting and Classifying Salient Fields of View From Microscopy Slides of Tuberculosis Bacteria, in: International Conference on Pattern Recognition and Artificial Intelligence, 2022, pp. 1\u201312.","DOI":"10.1007\/978-3-031-09037-0_13"},{"key":"10.1016\/j.compbiomed.2023.107573_b32","series-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"10.1016\/j.compbiomed.2023.107573_b33","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1214\/aoms\/1177729586","article-title":"A stochastic approximation method","author":"Robbins","year":"1951","journal-title":"Ann. Math. Stat."},{"key":"10.1016\/j.compbiomed.2023.107573_b34","first-page":"18795","article-title":"Adabelief optimizer: Adapting stepsizes by the belief in observed gradients","volume":"33","author":"Zhuang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compbiomed.2023.107573_b35","doi-asserted-by":"crossref","unstructured":"L.N. Smith, Cyclical learning rates for training neural networks, in: IEEE Winter Conference on Applications of Computer Vision, 2017, pp. 464\u2013472.","DOI":"10.1109\/WACV.2017.58"},{"key":"10.1016\/j.compbiomed.2023.107573_b36","series-title":"Dice loss for data-imbalanced NLP tasks","author":"Li","year":"2019"},{"key":"10.1016\/j.compbiomed.2023.107573_b37","doi-asserted-by":"crossref","unstructured":"X. Yue, N. Dimitriou, O. Arandjelovic, Colorectal cancer outcome prediction from H&E whole slide images using machine learning and automatically inferred phenotype profiles, in: 11th International Conference, Vol. 60, 2019, pp. 139\u2013149.","DOI":"10.29007\/n912"},{"issue":"8","key":"10.1016\/j.compbiomed.2023.107573_b38","doi-asserted-by":"crossref","first-page":"2662","DOI":"10.1016\/j.patcog.2014.02.006","article-title":"Hallucinating optimal high-dimensional subspaces","volume":"47","author":"Arandjelovi\u0107","year":"2014","journal-title":"Pattern Recognit."},{"issue":"3","key":"10.1016\/j.compbiomed.2023.107573_b39","doi-asserted-by":"crossref","first-page":"691","DOI":"10.1016\/j.bbe.2018.05.007","article-title":"Automatic detection of tuberculosis bacilli from microscopic sputum smear images using deep learning methods","volume":"38","author":"Panicker","year":"2018","journal-title":"Biocybern. Biomed. Eng."},{"key":"10.1016\/j.compbiomed.2023.107573_b40","doi-asserted-by":"crossref","unstructured":"V. Makkapati, R. Agrawal, R. Acharya, Segmentation and classification of tuberculosis bacilli from ZN-stained sputum smear images, in: International Conference on Automation Science and Engineering, ISBN: 1424445787, 2009, pp. 217\u2013220.","DOI":"10.1109\/COASE.2009.5234173"},{"issue":"2","key":"10.1016\/j.compbiomed.2023.107573_b41","first-page":"112","article-title":"Algorithms for the reduction of the number of points required to represent a digitized line or its caricature","volume":"10","author":"Douglas","year":"1973","journal-title":"Cartogr. Int. J. Geogr. Inf. Geovisualization"},{"key":"10.1016\/j.compbiomed.2023.107573_b42","doi-asserted-by":"crossref","unstructured":"R. Arandjelovi\u0107, A. Zisserman, Three things everyone should know to improve object retrieval, in: IEEE Conference on Computer Vision and Pattern Recognition, ISBN: 1467312282, 2012, pp. 2911\u20132918.","DOI":"10.1109\/CVPR.2012.6248018"},{"issue":"11","key":"10.1016\/j.compbiomed.2023.107573_b43","doi-asserted-by":"crossref","first-page":"1723","DOI":"10.1007\/s11263-018-1137-8","article-title":"Understanding and improving kernel local descriptors","volume":"127","author":"Mukundan","year":"2019","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.compbiomed.2023.107573_b44","article-title":"Working hard to know your neighbor\u2019s margins: Local descriptor learning loss","volume":"30","author":"Mishchuk","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compbiomed.2023.107573_b45","series-title":"Improving the HardNet Descriptor","author":"Pultar","year":"2020"},{"key":"10.1016\/j.compbiomed.2023.107573_b46","doi-asserted-by":"crossref","unstructured":"Y. Tian, X. Yu, B. Fan, F. Wu, H. Heijnen, V. Balntas, Sosnet: Second order similarity regularization for local descriptor learning, in: IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 11016\u201311025.","DOI":"10.1109\/CVPR.2019.01127"},{"key":"10.1016\/j.compbiomed.2023.107573_b47","doi-asserted-by":"crossref","unstructured":"V. Balntas, E. Riba, D. Ponsa, K. Mikolajczyk, Learning local feature descriptors with triplets and shallow convolutional neural networks, in: BMVC, Vol. 1, No. 2, 2016, p. 3.","DOI":"10.5244\/C.30.119"},{"key":"10.1016\/j.compbiomed.2023.107573_b48","series-title":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1","first-page":"886","article-title":"Histograms of oriented gradients for human detection","author":"Dalal","year":"2005"},{"key":"10.1016\/j.compbiomed.2023.107573_b49","doi-asserted-by":"crossref","unstructured":"T. Ojala, M. Pietikainen, D. Harwood, Performance evaluation of texture measures with classification based on Kullback discrimination of distributions, in: 12th International Conference on Pattern Recognition, Vol. 1, ISBN: 0818662654, 1994, pp. 582\u2013585.","DOI":"10.1109\/ICPR.1994.576366"},{"key":"10.1016\/j.compbiomed.2023.107573_b50","series-title":"International Joint Conference on Neural Networks","first-page":"1","article-title":"Employing domain specific discriminative information to address inherent limitations of the LBP descriptor in face recognition","author":"Fan","year":"2018"},{"key":"10.1016\/j.compbiomed.2023.107573_b51","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1016\/j.neucom.2013.09.010","article-title":"Multi-step-ahead time series prediction using multiple-output support vector regression","volume":"129","author":"Bao","year":"2014","journal-title":"Neurocomputing"},{"key":"10.1016\/j.compbiomed.2023.107573_b52","series-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016"},{"key":"10.1016\/j.compbiomed.2023.107573_b53","doi-asserted-by":"crossref","unstructured":"A. Beykikhoshk, O. Arandjelovi\u0107, D. Phung, S. Venkatesh, Overcoming data scarcity of Twitter: using tweets as bootstrap with application to autism-related topic content analysis, in: International Conference on Advances in Social Networks Analysis and Mining, 2015, pp. 1354\u20131361.","DOI":"10.1145\/2808797.2808908"},{"issue":"1","key":"10.1016\/j.compbiomed.2023.107573_b54","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1080\/07038992.2017.1259557","article-title":"Application of the dice coefficient to accuracy assessment of object-based image classification","volume":"43","author":"Guindon","year":"2017","journal-title":"Can. J. Remote Sens."}],"container-title":["Computers in Biology and Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0010482523010387?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0010482523010387?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T16:46:54Z","timestamp":1793206014000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0010482523010387"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":54,"alternative-id":["S0010482523010387"],"URL":"https:\/\/doi.org\/10.1016\/j.compbiomed.2023.107573","relation":{},"ISSN":["0010-4825"],"issn-type":[{"value":"0010-4825","type":"print"}],"subject":[],"published":{"date-parts":[[2023,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Localization and phenotyping of tuberculosis bacteria using a combination of deep learning and SVMs","name":"articletitle","label":"Article Title"},{"value":"Computers in Biology and Medicine","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compbiomed.2023.107573","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"107573"}}