{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T09:11:31Z","timestamp":1792746691382,"version":"4.5.0"},"reference-count":35,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2019,2,11]],"date-time":"2019-02-11T00:00:00Z","timestamp":1549843200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["MOST 107\u20102634\u2010F\u2010006\u2010005"],"award-info":[{"award-number":["MOST 107\u20102634\u2010F\u2010006\u2010005"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["analyticalsciencejournals.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Microscopy Res &amp; Technique"],"published-print":{"date-parts":[[2019,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Tuberculosis (TB) remains the leading cause of morbidity and mortality from infectious disease in developing countries. The sputum smear microscopy remains the primary diagnostic laboratory test. However, microscopic examination is always time\u2010consuming and tedious. Therefore, an effective computer\u2010aided image identification system is needed to provide timely assistance in diagnosis. The current identification system usually suffers from complex color variations of the images, resulting in plentiful of false object detection. To overcome the dilemma, we propose a two\u2010stage <jats:italic>Mycobacterium tuberculosis<\/jats:italic> identification system, consisting of candidate detection and classification using convolution neural networks (CNNs). The refined Faster region\u2010based CNN was used to distinguish candidates of <jats:italic>M. tuberculosis<\/jats:italic> and the actual ones were classified by utilizing CNN\u2010based classifier. We first compared three different CNNs, including ensemble CNN, single\u2010member CNN, and deep CNN. The experimental results showed that both ensemble and deep CNNs were on par with similar identification performance when analyzing more than 19,000 images. A much better recall value was achieved by using our proposed system in comparison with conventional pixel\u2010based support vector machine method for <jats:italic>M. tuberculosis<\/jats:italic> bacilli detection.<\/jats:p>","DOI":"10.1002\/jemt.23217","type":"journal-article","created":{"date-parts":[[2019,2,11]],"date-time":"2019-02-11T09:39:32Z","timestamp":1549877972000},"page":"709-719","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":40,"title":["An effective and accurate identification system of <i>Mycobacterium tuberculosis<\/i> using convolution neural networks"],"prefix":"10.1002","volume":"82","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5958-1386","authenticated-orcid":false,"given":"Chan\u2010Pang","family":"Kuok","sequence":"first","affiliation":[{"name":"Department of Computer Science and Information Engineering National Cheng Kung University  Tainan Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming\u2010Huwi","family":"Horng","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering National Pingtung University  Pingtung Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu\u2010Ming","family":"Liao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering National Cheng Kung University  Tainan Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan\u2010Haw","family":"Chow","sequence":"additional","affiliation":[{"name":"Department of Pathology College of Medicine, National Cheng Kung University  Tainan Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yung\u2010Nien","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering National Cheng Kung University  Tainan Taiwan"},{"name":"MOST AI Biomedical Research Center  Tainan Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2019,2,11]]},"reference":[{"key":"e_1_2_6_2_1","doi-asserted-by":"crossref","unstructured":"Cao Y. Liu C. Liu B. Brunette M. J. Zhang N. Sun T. \u2026Curioso W. H.. (2016. Improving tuberculosis diagnostics using deep learning and mobile health technologies among resource\u2010poor and marginalized communities. InIEEE First International Conference on Connected Health: Applications Systems and Engineering Technologies (CHASE) Washington DC 274\u2013281.","DOI":"10.1109\/CHASE.2016.18"},{"key":"e_1_2_6_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"e_1_2_6_4_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022627411411"},{"key":"e_1_2_6_5_1","doi-asserted-by":"crossref","unstructured":"CostaFilho C. F. Levy P. C. Xavier C. M. Costa M. G. Fujimoto L. B. &Salem J.. (2012). Mycobacterium tuberculosis recognition with conventional microscopy. InAnnual International Conference of the IEEE Engineering in Medicine and Biology Society Engineering in Medicine and Biology Society (EMBC) San Diego CA 6263\u20136268.","DOI":"10.1109\/EMBC.2012.6347426"},{"key":"e_1_2_6_6_1","doi-asserted-by":"crossref","unstructured":"Dietterich T. G.(2000). Ensemble methods in machine learning. InInternational Workshop on Multiple Classifier Systems1\u201315.","DOI":"10.1007\/3-540-45014-9_1"},{"key":"e_1_2_6_7_1","doi-asserted-by":"crossref","unstructured":"Eggert C. Zecha D. Brehm S. &Lienhart R.. (2017). Improving Small Object Proposals for Company Logo Detection. InProceedings of the 2017 ACM on International Conference on Multimedia Retrieval Bucharest Romania 167\u2013174.","DOI":"10.1145\/3078971.3078990"},{"key":"e_1_2_6_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_2_6_9_1","doi-asserted-by":"crossref","unstructured":"Jia Y. Shelhamer E. Donahue J. Karayev S. Long J. Girshick R. \u2026Darrell T.. (2014). Caffe: Convolutional architecture for fast feature embedding. InProceedings of the 22nd ACM International Conference on Multimedia New York NY USA 675\u2013678.","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_2_6_10_1","doi-asserted-by":"crossref","unstructured":"Kang M. Leng X. Lin Z. &Ji K.. (2017). A modified faster R\u2010CNN based on CFAR algorithm for SAR ship detection. InInternational Workshop on Remote Sensing with Intelligent Processing (RSIP) Shanghai 1\u20134.","DOI":"10.1109\/RSIP.2017.7958815"},{"key":"e_1_2_6_11_1","doi-asserted-by":"crossref","unstructured":"Kant S. &Srivastava M. M.(2018).Towards automated tuberculosis detection using deep learning. arXiv preprint arXiv:1801.07080.","DOI":"10.1109\/SSCI.2018.8628800"},{"key":"e_1_2_6_12_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2818.2009.03308.x"},{"key":"e_1_2_6_13_1","unstructured":"Krizhevsky A. Sutskever I. &Hinton G. E.. (2012). Imagenet classification with deep convolutional neural networks. InAdvances in Neural Information Processing Systems (NIPS) Lake Tahoe Nevada USA 1097\u20131105."},{"key":"e_1_2_6_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_2_6_15_1","doi-asserted-by":"crossref","unstructured":"Li L. yan Shi D. &Xu J.. (2013). Color image segmentation based\u2010on svm using mixed features and combined kernel. InInternational Conference on Intelligent Science and Big Data Engineering Beijing China 401\u2013409.","DOI":"10.1007\/978-3-642-42057-3_51"},{"key":"e_1_2_6_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2017.03.017"},{"key":"e_1_2_6_17_1","unstructured":"Liao Y. M. Kuok C. P. &Sun Y. N.(2017). Mycobacterium tuberculosis detection using refined Faster R\u2010CNN. InProceeding of the 30th IPPR Conference on Computer Vision Graphics and Image Processing Nantou Taiwan C4\u20106."},{"key":"e_1_2_6_18_1","doi-asserted-by":"crossref","unstructured":"L\u00f3pez Y. P. Costa Filho C. F. Aguilera L. M. R. &Costa M. G. F.(2017). Automatic classification of light field smear microscopy patches using Convolutional Neural Networks for identifying mycobacterium tuberculosis. InCHILEAN Conference on Electrical Electronics Engineering Information and Communication Technologies (CHILECON)1\u20135.","DOI":"10.1109\/CHILECON.2017.8229512"},{"key":"e_1_2_6_19_1","unstructured":"Math Works : Neural Network Toolbox (R2016b)[Computer software]. (2016). Retrieved fromhttps:\/\/www.mathworks.com\/help\/nnet\/"},{"key":"e_1_2_6_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/jemt.22951"},{"key":"e_1_2_6_21_1","doi-asserted-by":"publisher","DOI":"10.1002\/jemt.22718"},{"key":"e_1_2_6_22_1","unstructured":"Ren S. He K. Girshick R. &Sun J.(2015). Faster r\u2010cnn: Towards real\u2010time object detection with region proposal networks. InAdvances in Neural Information Processing Systems (NIPS) Montreal Canada 91\u201399."},{"key":"e_1_2_6_23_1","doi-asserted-by":"crossref","unstructured":"Shah M. I. Mishra S. Sarkar M. &Sudarshan S. K.. (2016). Automatic detection and classification of tuberculosis bacilli from camera\u2010enabled Smartphone microscopic images. InFourth International Conference on Parallel Distributed and Grid Computing (PDGC) Waknaghat 287\u2013290.","DOI":"10.1109\/PDGC.2016.7913161"},{"key":"e_1_2_6_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2017.06.001"},{"key":"e_1_2_6_25_1","unstructured":"Simonyan K. &Zisserman A.(2014).Very deep convolutional networks for large\u2010scale image recognition. arXiv preprint arXiv:1409.1556."},{"key":"e_1_2_6_26_1","unstructured":"Silva J. F. Silva J. M. Pinho E. &Costa C. (2017). 3D\u2010CNN in drug resistance detection and tuberculosis classification. InCLEF2017 Working Notes CEUR Workshop Proceedings CEUR-WS.org."},{"key":"e_1_2_6_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2016.2594239"},{"key":"e_1_2_6_28_1","unstructured":"Springenberg J. T. Dosovitskiy A. Brox T. &Riedmiller M.(2014).Striving for simplicity: The all convolutional net. arXiv preprint arXiv:1412.6806."},{"key":"e_1_2_6_29_1","doi-asserted-by":"crossref","unstructured":"Szegedy C. Liu W. Jia Y. Sermanet P. Reed S. Anguelov D. \u2026 & Rabinovich A. (2015). Going deeper with convolutions. In Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Boston MA 1\u20139.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_2_6_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.08.008"},{"key":"e_1_2_6_31_1","unstructured":"World Health Organization(2017).Global tuberculosis report 2017. Rep. WHO\/HTM\/TB\/2017.23. WHO."},{"key":"e_1_2_6_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2017.2686418"},{"key":"e_1_2_6_33_1","doi-asserted-by":"crossref","unstructured":"Zeiler M. D. &Fergus R.(2014). Visualizing and understanding convolutional networks. InEuropean Conference on Computer Vision Zurich Switzerland 818\u2013833.","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"e_1_2_6_34_1","doi-asserted-by":"crossref","unstructured":"Zhai Y. Liu Y. Zhou D. &Liu S.(2010). Automatic identification of mycobacterium tuberculosis from ZN\u2010stained sputum smear: Algorithm and system design. InIEEE International Conference on Robotics and Biomimetics (ROBIO) Tianjin 41\u201346.","DOI":"10.1109\/ROBIO.2010.5723300"},{"key":"e_1_2_6_35_1","doi-asserted-by":"crossref","unstructured":"Zhang J. Hu H. Chen S. Huang Y. &Guan Q.(2016). Cancer cells detection in phase\u2010contrast microscopy images based on Faster R\u2010CNN. In9th International Symposium on Computational Intelligence and Design (ISCID) Hangzhou 1 pp.363\u2013367.","DOI":"10.1109\/ISCID.2016.1090"},{"key":"e_1_2_6_36_1","doi-asserted-by":"crossref","unstructured":"Zou A. M. Hou Z. G. &Tan M.. (2005). Support vector machines (SVM) for color image segmentation with applications to mobile robot localization problems. InInternational Conference on Intelligent Computing Hefei China 443\u2013452.","DOI":"10.1007\/11538356_46"}],"container-title":["Microscopy Research and Technique"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fjemt.23217","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jemt.23217","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/jemt.23217","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/analyticalsciencejournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jemt.23217","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T15:31:37Z","timestamp":1760628697000},"score":1,"resource":{"primary":{"URL":"https:\/\/analyticalsciencejournals.onlinelibrary.wiley.com\/doi\/10.1002\/jemt.23217"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,11]]},"references-count":35,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2019,6]]}},"alternative-id":["10.1002\/jemt.23217"],"URL":"https:\/\/doi.org\/10.1002\/jemt.23217","archive":["Portico"],"relation":{},"ISSN":["1059-910X","1097-0029"],"issn-type":[{"value":"1059-910X","type":"print"},{"value":"1097-0029","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,2,11]]},"assertion":[{"value":"2018-05-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-12-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-02-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}