{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T15:43:11Z","timestamp":1785858191412,"version":"3.56.0"},"reference-count":30,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2021,11,28]],"date-time":"2021-11-28T00:00:00Z","timestamp":1638057600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100007591","name":"Akiyama Life Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007591","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Cancer Medicine"],"published-print":{"date-parts":[[2022,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>Although many cervical cytology diagnostic support systems have been developed, it is challenging to classify overlapping cell clusters with a variety of patterns in the same way that humans do. In this study, we developed a fast and accurate system for the detection and classification of atypical cell clusters by using a two\u2010step algorithm based on two different deep learning algorithms.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We created 919 cell images from liquid\u2010based cervical cytological samples collected at Sapporo Medical University and annotated them based on the Bethesda system as a dataset for machine learning. Most of the images captured overlapping and crowded cells, and images were oversampled by digital processing. The detection system consists of two steps: (1) detection of atypical cells using You Only Look Once v4 (YOLOv4) and (2) classification of the detected cells using ResNeSt. A label smoothing algorithm was used for the dataset in the second classification step. This method annotates multiple correct classes from a single cell image with a smooth probability distribution.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The first step, cell detection by YOLOv4, was able to detect all atypical cells above ASC\u2010US without any observed false negatives. The detected cell images were then analyzed in the second step, cell classification by the ResNeSt algorithm, which exhibited average accuracy and F\u2010measure values of 90.5% and 70.5%, respectively. The oversampling of the training image and label smoothing algorithm contributed to the improvement of the system's accuracy.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>This system combines two deep learning algorithms to enable accurate detection and classification of cell clusters based on the Bethesda system, which has been difficult to achieve in the past. We will conduct further research and development of this system as a platform for augmented reality microscopes for cytological diagnosis.<\/jats:p><\/jats:sec>","DOI":"10.1002\/cam4.4460","type":"journal-article","created":{"date-parts":[[2021,11,29]],"date-time":"2021-11-29T05:45:40Z","timestamp":1638164740000},"page":"520-529","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":43,"title":["A screening assistance system for cervical cytology of squamous cell atypia based on a two\u2010step combined CNN algorithm with label smoothing"],"prefix":"10.1002","volume":"11","author":[{"given":"Yuta","family":"Nambu","sequence":"first","affiliation":[{"name":"Department of Media Architecture Future University Hakodate  Hakodate Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7110-980X","authenticated-orcid":false,"given":"Tasuku","family":"Mariya","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecology Sapporo Medical University School of Medicine  Sapporo Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shota","family":"Shinkai","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecology Sapporo Medical University School of Medicine  Sapporo Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mina","family":"Umemoto","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecology Sapporo Medical University School of Medicine  Sapporo Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroko","family":"Asanuma","sequence":"additional","affiliation":[{"name":"Department of Pathology 1st Sapporo Medical University School of Medicine  Sapporo Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ikuma","family":"Sato","sequence":"additional","affiliation":[{"name":"Department of Media Architecture Future University Hakodate  Hakodate Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshihiko","family":"Hirohashi","sequence":"additional","affiliation":[{"name":"Department of Pathology 1st Sapporo Medical University School of Medicine  Sapporo Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Toshihiko","family":"Torigoe","sequence":"additional","affiliation":[{"name":"Department of Pathology 1st Sapporo Medical University School of Medicine  Sapporo Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuichi","family":"Fujino","sequence":"additional","affiliation":[{"name":"Department of Media Architecture Future University Hakodate  Hakodate Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tsuyoshi","family":"Saito","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecology Sapporo Medical University School of Medicine  Sapporo Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2021,11,28]]},"reference":[{"key":"e_1_2_10_2_1","first-page":"267","article-title":"Performance of the cytoanalyzer in recent clinical trials","volume":"29","author":"Spencer CC","year":"1962","journal-title":"J Natl Cancer Inst"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(68)90822-2"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/0146-664X(74)90029-X"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1093\/ajcp\/96.3.300"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1159\/000331542"},{"key":"e_1_2_10_7_1","volume-title":"Cytology: Diagnostic Principles and Clinical Correlates","author":"Cibas ES","year":"2021"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2013.2250984"},{"key":"e_1_2_10_9_1","unstructured":"GautamS HarinarayanKK JithN SaoAK BhavsarA NatarajanA.Considerations for a PAP Smear Image Analysis System with CNN Features.2018 June 01 2018:[arXiv:1806.09025 p.]. Available from:https:\/\/ui.adsabs.harvard.edu\/abs\/2018arXiv180609025G"},{"key":"e_1_2_10_10_1","unstructured":"JantzenJ NorupJ DouniasG BjerregaardB.Pap\u2010smear Benchmark Data for Pattern Classification. Nature inspired Smart Information Systems: EU co\u2010ordination action.NiSIS;2005:1\u20109."},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12938-019-0634-5"},{"key":"e_1_2_10_12_1","first-page":"86","volume-title":"Lecture Notes in Computer Science","author":"Nirmal Jith OU","year":"2018"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2013.12.012"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2017.2705583"},{"issue":"4","key":"e_1_2_10_15_1","first-page":"446","article-title":"Cervical cancer diagnosis based on random forest","volume":"13","author":"Guanglu Sun SL","year":"2017","journal-title":"Int J Performability Eng"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1155\/2015\/586928"},{"key":"e_1_2_10_17_1","unstructured":"BoraK ChowdhuryM MahantaLB KunduMK DasAK.Pap smear image classification using convolutional neural network. Proceedings of the Tenth Indian Conference on Computer Vision Graphics and Image Processing \u2010 ICVGIP \u2018162016. p.1\u20108."},{"key":"e_1_2_10_18_1","doi-asserted-by":"crossref","unstructured":"ZhangJ LiuY.Cervical cancer detection using SVM based feature screening. Lecture Notes in Computer Science.2004;3217(1 PART 2):873\u2010880.","DOI":"10.1007\/978-3-540-30136-3_106"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12938-016-0131-z"},{"key":"e_1_2_10_20_1","volume-title":"Cervical Cytology Intelligent Diagnosis Based On Object Detection Technology","author":"Meiquan X","year":"2018"},{"key":"e_1_2_10_21_1","unstructured":"RedmonJ DivvalaS GirshickR FarhadiA.You Only Look Once: Unified Real\u2010Time Object Detection. 2015 June 01 2015:[arXiv:1506.02640 p.]. Available from:https:\/\/ui.adsabs.harvard.edu\/abs\/2015arXiv150602640R"},{"key":"e_1_2_10_22_1","unstructured":"ZhangH WuC ZhangZ et al.ResNeSt: Split\u2010Attention Networks. 2020 April 01 2020:[arXiv:2004.08955 p.]. Available from:https:\/\/ui.adsabs.harvard.edu\/abs\/2020arXiv200408955Z"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"e_1_2_10_24_1","unstructured":"ZhongZ ZhengL KangG LiS YangY.Random Erasing Data Augmentation. 2017 August 01 2017:[arXiv:1708.04896 p.]. Available from:https:\/\/ui.adsabs.harvard.edu\/abs\/2017arXiv170804896Z"},{"key":"e_1_2_10_25_1","unstructured":"SzegedyC VanhouckeV IoffeS ShlensJ WojnaZ.Rethinking the Inception Architecture for Computer Vision. 2015 December 01 2015:[arXiv:1512.00567 p.]. Available from:https:\/\/ui.adsabs.harvard.edu\/abs\/2015arXiv151200567S"},{"key":"e_1_2_10_26_1","unstructured":"GirshickR DonahueJ DarrellT MalikJ.Rich feature hierarchies for accurate object detection and semantic segmentation. 2013 November 01 2013:[arXiv:1311.2524 p.]. Available from:https:\/\/ui.adsabs.harvard.edu\/abs\/2013arXiv1311.2524G"},{"key":"e_1_2_10_27_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. 2014 June 01 2014:[arXiv:1406.4729 p.]. Available from:https:\/\/ui.adsabs.harvard.edu\/abs\/2014arXiv1406.4729H","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"e_1_2_10_28_1","unstructured":"RenS HeK GirshickR SunJ.Faster R\u2010CNN: Towards Real\u2010Time Object Detection with Region Proposal Networks. 2015 June 01 2015:[arXiv:1506.01497 p.]. Available from:https:\/\/ui.adsabs.harvard.edu\/abs\/2015arXiv150601497R"},{"key":"e_1_2_10_29_1","first-page":"1097","volume-title":"Proceedings of the 25th International Conference on Neural Information Processing Systems \u2010 Volume 1","author":"Krizhevsky A","year":"2012"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-132-10-200005160-00009"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-019-0539-7"}],"container-title":["Cancer Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cam4.4460","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/cam4.4460","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cam4.4460","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T07:46:26Z","timestamp":1693208786000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/cam4.4460"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,28]]},"references-count":30,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["10.1002\/cam4.4460"],"URL":"https:\/\/doi.org\/10.1002\/cam4.4460","archive":["Portico"],"relation":{},"ISSN":["2045-7634","2045-7634"],"issn-type":[{"value":"2045-7634","type":"print"},{"value":"2045-7634","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,28]]},"assertion":[{"value":"2021-10-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-11-18","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-11-28","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}