{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T20:13:43Z","timestamp":1784924023828,"version":"3.55.0"},"reference-count":49,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>Acid-fast bacillus (AFB) detection by microscopy remains a cornerstone of laboratory diagnosis for mycobacterial infections, despite the limitations of variable sensitivity, labor-intensive workflows, and interobserver variability. Recent advances in artificial intelligence, particularly deep learning, offer promising solutions to automate and augment AFB detection on microscopy images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A systematic review was conducted in accordance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, with protocol registration in PROSPERO (registration No. CRD42025633886). PubMed and Embase were searched for studies published in the past decade that applied deep learning\u2013based methods to microscopy-based AFB detection. Eligible studies included original research and review articles using Ziehl-Neelsen\u2013stained or auramine-stained specimens and reporting quantitative diagnostic performance metrics. Data on model architectures, annotation strategies, evaluation metrics, and accuracy were extracted. A forest plot was constructed to summarize pooled accuracy estimates across eligible studies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Forty-nine studies met the inclusion criteria. Deep learning models, including convolutional neural networks, object detectors, and transformer-based architectures, demonstrated high accuracies (80%-98%), despite substantial heterogeneity. Weakly supervised learning, multiview and z-stack imaging, and domain adaptation techniques are being used to address variability in staining, focus, and laboratory conditions. Object detection and segmentation models have enabled improved bacillus localization and quantification, while foundation models and transfer learning approaches are reducing annotation burden and improving generalizability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Deep learning\u2013based AFB detection systems demonstrate high accuracy and strong potential to enhance tuberculosis microscopy. Heterogeneity in study design and limited external validation, however, highlight the need for standardized evaluation and multicenter clinical studies before widespread implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/ajcp\/aqag083","type":"journal-article","created":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T19:40:21Z","timestamp":1784922021000},"source":"Crossref","is-referenced-by-count":0,"title":["Deep learning\u2013based detection of acid-fast bacilli in microscopy images: a systematic review"],"prefix":"10.1093","volume":"166","author":[{"given":"Kanika","family":"Rastogi","sequence":"first","affiliation":[{"name":"Department of Pathology, Vardhman Mahavir Medical College & Safdarjung Hospital , New Delhi,","place":["India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lavleen","family":"Singh","sequence":"additional","affiliation":[{"name":"Department of Pathology, All India Institute of Medical Sciences , New Delhi,","place":["India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aparajita","family":"Khan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Indian Institute of Technology (BHU), Varanasi , Uttar Pradesh,","place":["India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Partha Pratim","family":"Roy","sequence":"additional","affiliation":[{"name":"Department of Computer Science & Engineering, Indian Institute of Technology Dhanbad , Jharkhand,","place":["India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Venkateswaran K","family":"Iyer","sequence":"additional","affiliation":[{"name":"Department of Pathology, All India Institute of Medical Sciences , New Delhi,","place":["India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,7,24]]},"reference":[{"key":"2026072415401602100_aqag083-B1","volume-title":"WHO Operational Handbook on Tuberculosis. Module 3: Diagnosis","author":"World Health Organization","year":"2025"},{"key":"2026072415401602100_aqag083-B2","volume-title":"Global Tuberculosis Report 2025.","author":"World Health Organization","year":"2025"},{"key":"2026072415401602100_aqag083-B3","doi-asserted-by":"publisher","first-page":"1734","DOI":"10.3390\/microorganisms12081734","article-title":"Pulmonary tuberculosis diagnosis using an intelligent microscopy scanner and image recognition model for improved acid-fast bacilli detection in smears","volume":"12","author":"Chen","year":"2024","journal-title":"Microorganisms"},{"key":"2026072415401602100_aqag083-B4","volume-title":"Toman\u2019s Tuberculosis: Case Detection, Treatment, and Monitoring\u2014Questions and Answers.","author":"Frieden","year":"2004","edition":"2nd ed"},{"key":"2026072415401602100_aqag083-B5","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1016\/S1473-3099(03)00609-1","article-title":"Clinical diagnosis of smear-negative pulmonary tuberculosis in low-income countries: the current evidence","volume":"3","author":"Siddiqi","year":"2003","journal-title":"Lancet Infect Dis"},{"key":"2026072415401602100_aqag083-B6","doi-asserted-by":"publisher","first-page":"1418","DOI":"10.3390\/life14111418","article-title":"AI-based analysis of Ziehl-Neelsen-stained sputum smears for Mycobacterium tuberculosis as a screening method for active tuberculosis","volume":"14","author":"Witarto","year":"2024","journal-title":"Life (Basel)"},{"key":"2026072415401602100_aqag083-B7","doi-asserted-by":"publisher","article-title":"Automatic detection of bacilli bacteria from Ziehl-Neelsen sputum smear images","author":"Shwetha","DOI":"10.1109\/C2I454156.2021.96892832021"},{"key":"2026072415401602100_aqag083-B8","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/j.rti.2004.05.007","article-title":"Identification of tuberculosis bacteria based on shape and color","volume":"10","author":"Forero","year":"2004","journal-title":"Real-Time Imaging"},{"key":"2026072415401602100_aqag083-B9","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1117\/12.506800","article-title":"Automatic identification techniques of tuberculosis bacteria","volume":"5203","author":"Forero","year":"2003","journal-title":"Proc SPIE"},{"key":"2026072415401602100_aqag083-B10","doi-asserted-by":"crossref","article-title":"Automatic classification of tuberculosis bacteria using neural network","author":"Rulaningtyas","DOI":"10.1109\/ICEEI.2011.6021502"},{"key":"2026072415401602100_aqag083-B11","doi-asserted-by":"publisher","first-page":"e0106923","DOI":"10.1128\/jcm.01069-23","article-title":"Retrospective validation of MetaSystems\u2019 deep-learning-based digital microscopy platform with assistance compared to manual fluorescence microscopy for detection of mycobacteria","volume":"62","author":"Desruisseaux","year":"2024","journal-title":"J Clin Microbiol"},{"key":"2026072415401602100_aqag083-B12","doi-asserted-by":"publisher","first-page":"8497","DOI":"10.3390\/s22218497","article-title":"Evaluation of an AI-based TB AFB smear screening system for laboratory diagnosis on routine practice","volume":"22","author":"Fu","year":"2022","journal-title":"Sensors (Basel)"},{"key":"2026072415401602100_aqag083-B13","doi-asserted-by":"publisher","first-page":"102212","DOI":"10.1016\/j.tube.2022.102212","article-title":"Novel TB smear microscopy automation system in detecting acid-fast bacilli for tuberculosis\u2014a multi-center double blind study","volume":"135","author":"Huang","year":"2022","journal-title":"Tuberculosis (Edinb)"},{"key":"2026072415401602100_aqag083-B14","doi-asserted-by":"publisher","first-page":"396","DOI":"10.3390\/bioengineering10040396","article-title":"Tumor cellularity assessment of breast histopathological slides via instance segmentation and pathomic features explainability","volume":"10","author":"Altini","year":"2023","journal-title":"Bioengineering (Basel)"},{"key":"2026072415401602100_aqag083-B15","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1109\/TCBB.2021.3138189","article-title":"Weakly supervised deep nuclei segmentation with sparsely annotated bounding boxes for DNA image cytometry","volume":"20","author":"Liang","year":"2023","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"2026072415401602100_aqag083-B16","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1806.00593","article-title":"BoxNet: deep learning based biomedical image segmentation using boxes only annotation","volume-title":"arXiv","author":"Yang"},{"key":"2026072415401602100_aqag083-B17","doi-asserted-by":"publisher","first-page":"110554","DOI":"10.1016\/j.compbiomed.2025.110554","article-title":"Streamlining tuberculosis detection with foundation model-based weakly supervised transformer","volume":"195","author":"Bed\u0151h\u00e1zi","year":"2025","journal-title":"Comput Biol Med"},{"key":"2026072415401602100_aqag083-B18","doi-asserted-by":"publisher","first-page":"1579","DOI":"10.11591\/eei.v14i2.9250","article-title":"Multimodal deep learning from sputum image segmentation to classify Mycobacterium tuberculosis using IUATLD assessment","volume":"14","author":"Saurina","year":"2025","journal-title":"Bulletin Eei"},{"key":"2026072415401602100_aqag083-B19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1409.1556","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"arXiv","author":"Simonyan"},{"key":"2026072415401602100_aqag083-B20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1512.03385","article-title":"Deep residual learning for image recognition","volume-title":"arXiv","author":"He"},{"key":"2026072415401602100_aqag083-B21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1608.0699","article-title":"Densely connected convolutional networks","volume-title":"arXiv","author":"Huang"},{"key":"2026072415401602100_aqag083-B22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1905.11946","article-title":"EfficientNet: rethinking model scaling for convolutional neural networks","volume-title":"arXiv","author":"Tan"},{"key":"2026072415401602100_aqag083-B23","doi-asserted-by":"publisher","first-page":"2358654","DOI":"10.1080\/08839514.2024.2358654","article-title":"Applied artificial intelligence and prospect of Internet of Everything (IoE) for the detection of tuberculosis","volume":"38","author":"Omodamilola","year":"2024","journal-title":"Appl Artif Intell"},{"key":"2026072415401602100_aqag083-B24","doi-asserted-by":"publisher","first-page":"1937","DOI":"10.1007\/s11277-024-11587-1","article-title":"Artificial intelligence-based deep learning architecture for tuberculosis detection","volume":"138","author":"Gupta","year":"2024","journal-title":"Wireless Pers Commun"},{"key":"2026072415401602100_aqag083-B25","doi-asserted-by":"publisher","first-page":"e52784","DOI":"10.7759\/cureus.52784","article-title":"Performance evaluation of no-code artificial intelligence models for the detection of acid-fast bacilli: a comparative analysis of three models","volume":"16","author":"Arya","year":"2024","journal-title":"Cureus"},{"key":"2026072415401602100_aqag083-B26","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1002\/jemt.23217","article-title":"An effective and accurate identification system of Mycobacterium tuberculosis using convolution neural networks","volume":"82","author":"Kuok","year":"2019","journal-title":"Microsc Res Tech"},{"key":"2026072415401602100_aqag083-B27","doi-asserted-by":"publisher","first-page":"108167","DOI":"10.1016\/j.compbiomed.2024.108167","article-title":"Automatic bright-field smear microscopy for diagnosis of pulmonary tuberculosis","volume":"172","author":"Serr\u00e3o","year":"2024","journal-title":"Comput Biol Med"},{"key":"2026072415401602100_aqag083-B28","doi-asserted-by":"publisher","first-page":"108531","DOI":"10.1016\/j.bspc.2025.108531","article-title":"Multi-task deep learning for bacilli detection and counting in sputum smear microscopy","volume":"112","author":"De Carvalho Brito","year":"2026","journal-title":"Biomed Signal Process Control"},{"key":"2026072415401602100_aqag083-B29","doi-asserted-by":"publisher","first-page":"104300","DOI":"10.1016\/j.medengphy.2025.104300","article-title":"ResGloTBNet: an interpretable deep residual network with global long-range dependency for tuberculosis screening of sputum smear microscopy images","volume":"137","author":"Yan","year":"2025","journal-title":"Med Eng Phys"},{"key":"2026072415401602100_aqag083-B30","doi-asserted-by":"publisher","first-page":"2230","DOI":"10.3390\/diagnostics13132230","article-title":"A study of Mycobacterium tuberculosis detection using different neural networks in autopsy specimens","volume":"13","author":"Lee","year":"2023","journal-title":"Diagnostics"},{"key":"2026072415401602100_aqag083-B31","doi-asserted-by":"publisher","first-page":"107518","DOI":"10.1016\/j.cmpb.2023.107518","article-title":"Multilayer outperforms single-layer slide scanning in AI-based classification of whole slide images with low-burden acid-fast mycobacteria (AFB)","volume":"234","author":"Nurzynska","year":"2023","journal-title":"Comput Methods Programs Biomed"},{"key":"2026072415401602100_aqag083-B32","doi-asserted-by":"publisher","first-page":"107217","DOI":"10.1016\/j.bspc.2024.107217","article-title":"Towards multi-view sputum smear quality classification","volume":"102","author":"Xu","year":"2025","journal-title":"Biomed Signal Process Control"},{"key":"2026072415401602100_aqag083-B33","doi-asserted-by":"publisher","first-page":"027503","DOI":"10.1117\/1.JMI.4.2.027503","article-title":"Ziehl-Neelsen sputum smear microscopy image database: a resource to facilitate automated bacilli detection for tuberculosis diagnosis","volume":"4","author":"Shah","year":"2017","journal-title":"J Med Imaging (Bellingham)"},{"key":"2026072415401602100_aqag083-B34","doi-asserted-by":"publisher","first-page":"034505","DOI":"10.1117\/1.JMI.12.3.034505","article-title":"Image database with slides prepared by the Ziehl-Neelsen method for training automated detection and counting systems for tuberculosis bacilli","volume":"12","author":"Gomide","year":"2025","journal-title":"J Med Imaging (Bellingham)"},{"key":"2026072415401602100_aqag083-B35","doi-asserted-by":"publisher","first-page":"51364","DOI":"10.1109\/ACCESS.2024.3386208","article-title":"A novel digitized microscopic images of ZN-stained sputum smear and its classification based on IUATLD grades","volume":"12","author":"Aulia","year":"2024","journal-title":"IEEE Access"},{"key":"2026072415401602100_aqag083-B36","doi-asserted-by":"publisher","DOI":"10.25452\/figshare.plus.27209667.v1","article-title":"DDS1: Dataset of patch images derived from sputum smear microscopy images for the development of bacillus detection methods","author":"Costa","year":"2025","journal-title":"Figshare+. Dataset"},{"key":"2026072415401602100_aqag083-B37","doi-asserted-by":"publisher","first-page":"4884","DOI":"10.1038\/s41467-021-25221-2","article-title":"Deep learning-based transformation of H&E-stained tissues into special stains","volume":"12","author":"de Haan","year":"2021","journal-title":"Nat Commun"},{"key":"2026072415401602100_aqag083-B38","doi-asserted-by":"publisher","first-page":"S24","DOI":"10.1016\/j.ijtb.2025.11.004","article-title":"Deep learning for automated sputum smear microscopy in tuberculosis diagnosis","volume":"72(suppl 3)","author":"Kokane","year":"2025","journal-title":"Indian J Tuberc"},{"key":"2026072415401602100_aqag083-B39","doi-asserted-by":"publisher","first-page":"709","DOI":"10.3390\/diagnostics12030709","article-title":"Deep-learning-aided detection of mycobacteria in pathology specimens increases the sensitivity in early diagnosis of pulmonary tuberculosis compared with bacteriology tests","volume":"12","author":"Zaizen","year":"2022","journal-title":"Diagnostics (Basel)"},{"key":"2026072415401602100_aqag083-B40","doi-asserted-by":"publisher","first-page":"866","DOI":"10.1097\/PAS.0000000000002223","article-title":"Combining artificial intelligence and simplified image processing for the automatic detection of Mycobacterium tuberculosis in acid-fast stain: a cross-institute training and validation study","volume":"48","author":"Wang","year":"2024","journal-title":"Am J Surg Pathol"},{"key":"2026072415401602100_aqag083-B41","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/j.pbiomolbio.2022.03.004","article-title":"Computational techniques for the automated detection of Mycobacterium tuberculosis from digitized sputum smear microscopic images: a systematic review","volume":"171","author":"Kotei","year":"2022","journal-title":"Prog Biophys Mol Biol"},{"key":"2026072415401602100_aqag083-B42","doi-asserted-by":"publisher","first-page":"1032467","DOI":"10.3389\/fpubh.2022.1032467","article-title":"Sputum smears quality inspection using an ensemble feature extraction approach","volume":"10","author":"Kiflie","year":"2022","journal-title":"Front Public Health"},{"key":"2026072415401602100_aqag083-B43","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1136\/amiajnl-2011-000089","article-title":"Automation bias: a systematic review of frequency, effect mediators, and mitigators","volume":"19","author":"Goddard","year":"2012","journal-title":"J Am Med Inform Assoc"},{"key":"2026072415401602100_aqag083-B44","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1186\/s12911-020-01332-6","article-title":"Explainability for artificial intelligence in healthcare: a multidisciplinary perspective","volume":"20","author":"Amann","year":"2020","journal-title":"BMC Med Inform Decis Mak"},{"key":"2026072415401602100_aqag083-B45","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1186\/s12916-019-1426-2","article-title":"Key challenges for delivering clinical impact with artificial intelligence","volume":"17","author":"Kelly","year":"2019","journal-title":"BMC Med"},{"key":"2026072415401602100_aqag083-B46","doi-asserted-by":"publisher","first-page":"101993","DOI":"10.1016\/j.tube.2020.101993","article-title":"Machine-assisted interpretation of auramine stains substantially increases through-put and sensitivity of microscopic tuberculosis diagnosis","volume":"125","author":"Horvath","year":"2020","journal-title":"Tuberculosis (Edinb)"},{"key":"2026072415401602100_aqag083-B47","doi-asserted-by":"publisher","first-page":"103565","DOI":"10.1016\/j.labinv.2024.103565","article-title":"AI-based automated microscopy vs. manual smear review for the diagnosis of acid-fast bacilli in auramine-stained smears: an updated meta-analysis","volume":"105","author":"Carrillo-Ng","year":"2025","journal-title":"Lab Invest"},{"key":"2026072415401602100_aqag083-B48","doi-asserted-by":"publisher","first-page":"1936","DOI":"10.21037\/jtd.2018.01.91","article-title":"Automatic detection of Mycobacterium tuberculosis using artificial intelligence","volume":"10","author":"Xiong","year":"2018","journal-title":"J Thorac Dis"},{"key":"2026072415401602100_aqag083-B49","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1093\/ajcp\/aqaa215","article-title":"Artificial intelligence-based screening for mycobacteria in whole-slide images of tissue samples","volume":"156","author":"Pantanowitz","year":"2021","journal-title":"Am J Clin Pathol"}],"container-title":["American Journal of Clinical Pathology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/ajcp\/article-pdf\/166\/1\/aqag083\/69970723\/aqag083.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ajcp\/article-pdf\/166\/1\/aqag083\/69970723\/aqag083.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T19:40:24Z","timestamp":1784922024000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/ajcp\/article\/doi\/10.1093\/ajcp\/aqag083\/8741655"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":49,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,7,6]]}},"URL":"https:\/\/doi.org\/10.1093\/ajcp\/aqag083","relation":{},"ISSN":["0002-9173","1943-7722"],"issn-type":[{"value":"0002-9173","type":"print"},{"value":"1943-7722","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,7]]},"published":{"date-parts":[[2026,7]]},"article-number":"aqag083"}}