{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T23:33:29Z","timestamp":1792625609833,"version":"4.5.0"},"reference-count":59,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T00:00:00Z","timestamp":1701216000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Cell. Infect. Microbiol."],"abstract":"<jats:sec><jats:title>Objective<\/jats:title><jats:p>Nocardia is clinically rare but highly pathogenic in clinical practice. Due to the lack of Nocardia screening methods, Nocardia is often missed in diagnosis, leading to worsening the condition. Therefore, this paper proposes a Nocardia screening method based on neural networks, aiming at quick Nocardia detection in sputum specimens with low costs and thereby reducing the missed diagnosis rate.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Firstly, sputum specimens were collected from patients who were infected with Nocardia, and a part of the specimens were mixed with new sputum specimens from patients without Nocardia infection to enhance the data diversity. Secondly, the specimens were converted into smears with Gram staining. Images were captured under a microscope and subsequently annotated by experts, creating two datasets. Thirdly, each dataset was divided into three subsets: the training set, the validation set and the test set. The training and validation sets were used for training networks, while the test set was used for evaluating the effeteness of the trained networks. Finally, a neural network model was trained on this dataset, with an image of Gram-stained sputum smear as input, this model determines the presence and locations of Nocardia instances within the image.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>After training, the detection network was evaluated on two datasets, resulting in classification accuracies of 97.3% and 98.3%, respectively. This network can identify Nocardia instances in about 24 milliseconds per image on a personal computer. The detection metrics of mAP50 on both datasets were 0.780 and 0.841, respectively.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The Nocardia screening method can accurately and efficiently determine whether Nocardia exists in the images of Gram-stained sputum smears. Additionally, it can precisely locate the Nocardia instances, assisting doctors in confirming the presence of Nocardia.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fcimb.2023.1270289","type":"journal-article","created":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T04:54:06Z","timestamp":1701233646000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Clinical screening of Nocardia in sputum smears based on neural networks"],"prefix":"10.3389","volume":"13","author":[{"given":"Hong","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanmeng","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaqi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tongyang","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,11,29]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"5791","DOI":"10.1007\/s00521-022-06960-9","article-title":"Literature review: Efficient deep neural networks techniques for medical image analysis","volume":"34","author":"Abdou","year":"2022","journal-title":"Neural Computing Appl."},{"key":"B2","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1186\/s12879-021-06416-w","article-title":"Case report: pulmonary nocardiosis caused by Nocardia exalbida in an immunocompetent patient","volume":"21","author":"Abe","year":"2021","journal-title":"BMC Infect. Dis."},{"key":"B3","doi-asserted-by":"publisher","first-page":"105020","DOI":"10.1016\/j.cmpb.2019.105020","article-title":"Recognition of peripheral blood cell images using convolutional neural networks","volume":"180","author":"Acevedo","year":"2019","journal-title":"Comput. Methods programs biomed."},{"key":"B4","doi-asserted-by":"publisher","first-page":"702","DOI":"10.1111\/j.1346-8138.2010.01166.x","article-title":"A novel case of nocardiosis with skin lesion due to Nocardia araoensis","volume":"38","author":"Akasaka","year":"2011","journal-title":"J. Dermatol."},{"key":"B5","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/s15010-009-9193-9","article-title":"Nocardiosis: updated clinical review and experience at a tertiary center","volume":"38","author":"Ambrosioni","year":"2010","journal-title":"Infection"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10916-018-1088-1","article-title":"Medical image analysis using convolutional neural networks: a review","volume":"42","author":"Anwar","year":"2018","journal-title":"J. Med. Syst."},{"key":"B7","first-page":"177","article-title":"Large-scale machine learning with stochastic gradient descent","author":"Bottou","year":"2010"},{"key":"B8","doi-asserted-by":"publisher","first-page":"106767","DOI":"10.1016\/j.compeleceng.2020.106767","article-title":"Medical image registration using deep neural networks: a comprehensive review","volume":"87","author":"Boveiri","year":"2020","journal-title":"Comput. Electr. Eng."},{"key":"B9","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1128\/CMR.19.2.259-282.2006","article-title":"Clinical and laboratory features of the nocardia spp. Based on current molecular taxonomy","volume":"19","author":"Brown-Elliott","year":"2006","journal-title":"Clin. Microbiol. Rev."},{"key":"B10","doi-asserted-by":"publisher","first-page":"713","DOI":"10.21037\/atm.2020.02.44","article-title":"A review of the application of deep learning in medical image classification and segmentation","volume":"8","author":"Cai","year":"2020","journal-title":"Ann. Trans. Med."},{"key":"B11","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.3389\/fmicb.2016.00542","article-title":"Shortcomings of the commercial MALDI-TOF MS database and use of MLSA as an arbiter in the identification of nocardia species","volume":"7","author":"Carrasco","year":"2016","journal-title":"Front. Microbiol."},{"key":"B13","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1016\/j.jinf.2006.08.003","article-title":"Nocardia species infections in a large county hospital in Miami: 6 years experience","volume":"54","author":"Castro","year":"2007","journal-title":"J. Infect."},{"key":"B14","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1186\/s12890-023-02434-3","article-title":"Co-infection with Mycobacterium tuberculosis and Nocardia farcinica in a COPD patient: a case report","volume":"23","author":"Chen","year":"2023","journal-title":"BMC Pulm. Med."},{"key":"B15","doi-asserted-by":"publisher","first-page":"3663","DOI":"10.21037\/apm-20-1301","article-title":"Diagnosis and treatment of lymphocutaneous dermatosis caused by Nocardia brasiliensis: a case report","volume":"9","author":"Chen","year":"2020","journal-title":"Ann. Palliative Med."},{"key":"B16","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.ijid.2019.10.032","article-title":"A multicentre analysis of Nocardia pneumonia in Spain: 2010\u20132016","volume":"90","author":"Ercibengoa","year":"2020","journal-title":"Int. J. Infect. Dis."},{"key":"B17","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1016\/j.micpath.2017.11.012","article-title":"Nocardiosis from 1888 to 2017","volume":"114","author":"Fatahi-Bafghi","year":"2018","journal-title":"Microb. Pathog."},{"key":"B18","first-page":"457","article-title":"Nocardiosis","author":"Filice","year":"2001","journal-title":"Respir. infections"},{"key":"B19","doi-asserted-by":"publisher","first-page":"738","DOI":"10.1016\/j.jiac.2016.08.004","article-title":"Clinical characteristics of pulmonary nocardiosis in immunocompetent patients","volume":"22","author":"Fujita","year":"2016","journal-title":"J. Infection Chemother."},{"key":"B20","first-page":"1440","article-title":"Fast r-cnn","author":"Girshick","year":"2015"},{"key":"B21","first-page":"580","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"Girshick","year":"2014"},{"key":"B22","first-page":"2961","article-title":"Mask r-cnn","author":"He","year":"2017"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.1016\/j.procs.2022.01.135","article-title":"A Review of Yolo algorithm developments","volume":"199","author":"Jiang","year":"2022","journal-title":"Proc. Comput. Sci."},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2021.669552","article-title":"Case report: A severe and multi-site nocardia farcinica infection rapidly and precisely identified by metagenomic next-generation sequencing","volume":"8","author":"Jiao","year":"2021","journal-title":"Front. Med."},{"key":"B25","doi-asserted-by":"publisher","first-page":"3157","DOI":"10.1007\/s00253-020-10387-4","article-title":"Classification of foodborne bacteria using hyperspectral microscope imaging technology coupled with convolutional neural networks","volume":"104","author":"Kang","year":"2020","journal-title":"Appl. Microbiol. Biotechnol."},{"key":"B26","doi-asserted-by":"publisher","first-page":"60778","DOI":"10.1007\/s11356-021-14983-3","article-title":"A convolutional neural network approach for detection of E. coli bacteria in water","volume":"28","author":"Khan","year":"2021","journal-title":"Environ. Sci. pollut. R."},{"key":"B27","first-page":"425","article-title":"A survey on machine learning techniques for breast cancer diagnosis and detection","author":"Kulkarni","year":"2021"},{"key":"B28","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":"Microscopy Res. technique"},{"key":"B29","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1093\/clinids\/22.6.891","article-title":"Nocardiosis","volume":"22","author":"Lerner","year":"1996","journal-title":"Clin. Infect. Dis."},{"key":"B30","doi-asserted-by":"publisher","first-page":"1346","DOI":"10.1080\/22221751.2022.2069514","article-title":"Identification of a novel drug-resistant community-acquired Nocardia spp. in a patient with bronchiectasis","volume":"11","author":"Li","year":"2022","journal-title":"Emerging Microbes Infections"},{"key":"B31","doi-asserted-by":"publisher","first-page":"36188","DOI":"10.1109\/ACCESS.2018.2846685","article-title":"Combining convolutional neural network with recursive neural network for blood cell image classification","volume":"6","author":"Liang","year":"2018","journal-title":"IEEE Access"},{"key":"B32","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"B33","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"B34","first-page":"21","article-title":"Ssd: Single shot multibox detector","author":"Liu","year":"2016"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2022\/9580991","article-title":"Deep neural networks for medical image segmentation","volume":"2022","author":"Malhotra","year":"2022","journal-title":"J. Healthcare Eng."},{"key":"B36","doi-asserted-by":"publisher","first-page":"14272","DOI":"10.1038\/s41598-020-71214-4","article-title":"Clinical correlates of nocardiosis","volume":"10","author":"Margalit","year":"2020","journal-title":"Sci. Rep."},{"key":"B37","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1016\/j.cmi.2020.12.019","article-title":"How do I manage nocardiosis","volume":"27","author":"Margalit","year":"2021","journal-title":"Clin. Microbiol. Infection"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1371\/journal.ppat.1008280","article-title":"Pathogenic Nocardia: A diverse genus of emerging pathogens or just poorly recognized","volume":"16","author":"Mehta","year":"2020","journal-title":"PloS Pathog."},{"key":"B39","doi-asserted-by":"publisher","first-page":"105175","DOI":"10.1016\/j.compbiomed.2021.105175","article-title":"Greedy Autoaugment for classification of mycobacterium tuberculosis image via generalized deep CNN using mixed pooling based on minimum square rough entropy","volume":"141","author":"Momeny","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"B40","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1111\/imj.14068","article-title":"Nocardiosis: 7-year experience at an Australian tertiary hospital","volume":"49","author":"Paige","year":"2019","journal-title":"Internal Med. J."},{"key":"B41","first-page":"290","article-title":"A comparison of deep learning CNN architecture models for classifying bacteria","author":"Poomrittigul","year":"2022"},{"key":"B42","doi-asserted-by":"publisher","first-page":"3233","DOI":"10.3390\/app10093233","article-title":"Transfer learning with deep convolutional neural network (CNN) for pneumonia detection using chest X-ray","volume":"10","author":"Rahman","year":"2020","journal-title":"Appl. Sci."},{"key":"B43","first-page":"779","article-title":"You only look once: Unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"B44","first-page":"7263","article-title":"YOLO9000: better, faster, stronger","author":"Redmon","year":"2017"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1804.02767","article-title":"Yolov3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv preprint arXiv:1804.02767"},{"key":"B46","doi-asserted-by":"publisher","first-page":"91","DOI":"10.5555\/2969239.2969250","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B47","doi-asserted-by":"publisher","first-page":"113991","DOI":"10.1016\/j.bios.2022.113991","article-title":"Separation-free bacterial identification in arbitrary media via deep neural network-based SERS analysis","volume":"202","author":"Rho","year":"2022","journal-title":"Biosens. Bioelectron."},{"key":"B48","doi-asserted-by":"publisher","first-page":"e00002","DOI":"10.1128\/JCM.00002-18","article-title":"Clinical assessment of a nocardia PCR-based assay for diagnosis of nocardiosis","volume":"56","author":"Rouzaud","year":"2018","journal-title":"J. Clin. Microbiol."},{"key":"B49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s12065-020-00540-3","article-title":"Convolutional neural networks in medical image understanding: a survey","volume":"15","author":"Sarvamangala","year":"2022","journal-title":"Evolutionary Intell."},{"key":"B50","doi-asserted-by":"publisher","first-page":"4497","DOI":"10.1128\/JCM.41.10.4497-4501.2003","article-title":"Nocardiosis: review of clinical and laboratory experience","volume":"41","author":"Saubolle","year":"2003","journal-title":"J. Clin. Microbiol."},{"key":"B51","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1186\/s40001-021-00562-2","article-title":"A case report of brain abscess caused by Nocardia farcinica","volume":"26","author":"Song","year":"2021","journal-title":"Eur. J. Med. Res."},{"key":"B52","doi-asserted-by":"publisher","first-page":"e00027","DOI":"10.1128\/cmr.00027-21","article-title":"Updated review on nocardia species: 2006\u20132021","volume":"35","author":"Traxler","year":"2022","journal-title":"Clin. Microbiol. Rev."},{"key":"B53","first-page":"325","article-title":"Bacterial strain classification using convolutional neural network for automatic bacterial disease diagnosis","author":"Trivedi","year":"2023"},{"key":"B54","first-page":"7464","article-title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","author":"Wang","year":"2023"},{"key":"B55","doi-asserted-by":"publisher","first-page":"865","DOI":"10.1007\/s10096-023-04619-4","article-title":"Molecular detection of Nocardia: development and application of a real-time PCR assay in sputum and bronchoalveolar lavage fluid samples","volume":"42","author":"Wang","year":"2023","journal-title":"Eur. J. Clin. Microbiol."},{"key":"B56","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":"B57","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1097\/TP.0000000000004343","article-title":"Outcomes of nocardiosis and treatment of disseminated infection in solid organ transplant recipients","volume":"107","author":"Yetmar","year":"2023","journal-title":"Transplantation"},{"key":"B58","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.media.2019.02.010","article-title":"Medical image classification using synergic deep learning","volume":"54","author":"Zhang","year":"2019","journal-title":"Med. image Anal."},{"key":"B59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.7759\/cureus.4759","article-title":"Ten year review of pulmonary nocardiosis: a series of 55 cases","volume":"11","author":"Zia","year":"2019","journal-title":"Cureus"}],"container-title":["Frontiers in Cellular and Infection Microbiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcimb.2023.1270289\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T04:54:09Z","timestamp":1701233649000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcimb.2023.1270289\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,29]]},"references-count":59,"alternative-id":["10.3389\/fcimb.2023.1270289"],"URL":"https:\/\/doi.org\/10.3389\/fcimb.2023.1270289","relation":{},"ISSN":["2235-2988"],"issn-type":[{"value":"2235-2988","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,29]]},"article-number":"1270289"}}