{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T13:52:48Z","timestamp":1779889968273,"version":"3.53.1"},"reference-count":21,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2021,8,17]],"date-time":"2021-08-17T00:00:00Z","timestamp":1629158400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Direct microscopic examination with potassium hydroxide is generally used as a screening method for diagnosing superficial fungal infections. Although this type of examination is faster than other diagnostic methods, it can still be time-consuming to evaluate a complete sample; additionally, it possesses the disadvantage of inconsistent reliability as the accuracy of the reading may differ depending on the performer\u2019s skill. This study aims at detecting hyphae more quickly, conveniently, and consistently through deep learning using images obtained from microscopy used in real-world practice. An object detection convolutional neural network, YOLO v4, was trained on microscopy images with magnifications of 100\u00d7, 40\u00d7, and (100+40)\u00d7. The study was conducted at the Department of Dermatology at Veterans Health Service Medical Center, Seoul, Korea between January 1, 2019 and December 31, 2019, using 3,707 images (1,255 images for training, 1,645 images for testing). The average precision was used to evaluate the accuracy of object detection. Precision recall curve analysis was performed for the hyphal location determination, and receiver operating characteristic curve analysis was performed on the image classification. The F1 score, sensitivity, and specificity values were used as measures of the overall performance. The sensitivity and specificity were, respectively, 95.2% and 100% in the 100\u00d7 data model, and 99% and 86.6% in the 40\u00d7 data model; the sensitivity and specificity in the combined (100+40)\u00d7 data model were 93.2% and 89%, respectively. The performance of our model had high sensitivity and specificity, indicating that hyphae can be detected with reliable accuracy. Thus, our deep learning-based autodetection model can detect hyphae in microscopic images obtained from real-world practice. We aim to develop an automatic hyphae detection system that can be utilized in real-world practice through continuous research.<\/jats:p>","DOI":"10.1371\/journal.pone.0256290","type":"journal-article","created":{"date-parts":[[2021,8,17]],"date-time":"2021-08-17T14:17:06Z","timestamp":1629209826000},"page":"e0256290","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":44,"title":["Automated detection of superficial fungal infections from microscopic images through a regional convolutional neural network"],"prefix":"10.1371","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1053-9387","authenticated-orcid":true,"given":"Taehan","family":"Koo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1504-5258","authenticated-orcid":true,"given":"Moon Hwan","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8253-6188","authenticated-orcid":true,"given":"Mihn-Sook","family":"Jue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2021,8,17]]},"reference":[{"issue":"Suppl 4","key":"pone.0256290.ref001","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1111\/j.1439-0507.2008.01606.x","article-title":"Epidemiological trends in skin mycoses worldwide","volume":"51","author":"B Havlickova","year":"2008","journal-title":"Mycoses"},{"issue":"5","key":"pone.0256290.ref002","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1111\/ced.12593","article-title":"Comparison of diagnostic methods for onychomycosis, and proposal of a diagnostic algorithm","volume":"40","author":"MY Jung","year":"2015","journal-title":"Clin Exp Dermatol"},{"issue":"11","key":"pone.0256290.ref003","doi-asserted-by":"crossref","first-page":"706","DOI":"10.21037\/atm.2020.03.134","article-title":"Deep learning-based automated diagnosis of fungal keratitis with in vivo confocal microscopy images","volume":"8","author":"J Lv","journal-title":"Ann Transl Med. 2020"},{"issue":"9","key":"pone.0256290.ref004","doi-asserted-by":"crossref","first-page":"945","DOI":"10.1002\/bit.260390909","article-title":"Classification and measurement of fungal pellets by automated image analysis","volume":"39","author":"PW Cox","year":"1992","journal-title":"Biotechnol Bioeng"},{"issue":"7","key":"pone.0256290.ref005","doi-asserted-by":"crossref","first-page":"1529","DOI":"10.1016\/j.jid.2018.01.028","article-title":"Classification of the clinical images for benign and malignant cutaneous tumors using a deep learning algorithm","volume":"138","author":"SS Han","year":"2018","journal-title":"J Invest Dermatol"},{"key":"pone.0256290.ref006","doi-asserted-by":"crossref","first-page":"851014","DOI":"10.1155\/2015\/851014","article-title":"Image-processing scheme to detect superficial fungal infections of the skin","volume":"2015","author":"U Mader","year":"2015","journal-title":"Comput Math Methods Med"},{"issue":"04","key":"pone.0256290.ref007","doi-asserted-by":"crossref","DOI":"10.4172\/1948-5948.1000142","article-title":"Characterization of fungal morphology using digital image analysis techniques","volume":"06","author":"M Papagianni","year":"2014","journal-title":"J Microb Biochem Technol"},{"issue":"1","key":"pone.0256290.ref008","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1111\/j.1574-6968.1990.tb13864.x","article-title":"An improved method for measuring the inter septal spacing in hyphae of Streptomyces tendae by fluorescence microscopy coupled with image processing","volume":"67","author":"U Reichl","year":"1990","journal-title":"FEMS Microbiology Letters"},{"key":"pone.0256290.ref009","doi-asserted-by":"crossref","first-page":"13449","DOI":"10.1109\/ACCESS.2018.2808941","article-title":"Hyphae detection in fungal keratitis images with adaptive robust binary pattern","volume":"6","author":"X Wu","year":"2018","journal-title":"IEEE Access"},{"issue":"7639","key":"pone.0256290.ref010","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"A Esteva","year":"2017","journal-title":"Nature"},{"issue":"1","key":"pone.0256290.ref011","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1001\/jamadermatol.2019.3807","article-title":"Keratinocytic skin cancer detection on the face using region-based convolutional neural network","volume":"156","author":"SS Han","journal-title":"JAMA Dermatol. 2020"},{"issue":"1","key":"pone.0256290.ref012","doi-asserted-by":"crossref","first-page":"e0191493","DOI":"10.1371\/journal.pone.0191493","article-title":"Deep neural networks show an equivalent and often superior performance to dermatologists in onychomycosis diagnosis: Automatic construction of onychomycosis datasets by region-based convolutional deep neural network","volume":"13","author":"SS Han","year":"2018","journal-title":"PLoS One"},{"issue":"1","key":"pone.0256290.ref013","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1001\/jamadermatol.2018.4378","article-title":"Expert-level diagnosis of nonpigmented skin cancer by combined convolutional neural networks","volume":"155","author":"P Tschandl","year":"2019","journal-title":"JAMA Dermatol"},{"key":"pone.0256290.ref014","first-page":"cite arXiv:2004.10934","article-title":"YOLOv3: An Incremental Improvement","author":"Joseph Redmon","year":"2018","journal-title":"arXiv"},{"key":"pone.0256290.ref015","doi-asserted-by":"crossref","unstructured":"Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, et al. SSD: Single shot multibox detector. In Proceedings of the European Conference on Computer Vision (ECCV), pages 21\u201337, 2016.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"pone.0256290.ref016","unstructured":"Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Doll ar. Focal loss for dense object detection. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), pages 2980\u20132988, 2017."},{"key":"pone.0256290.ref017","first-page":"379","article-title":"R","volume-title":"-FCN: Object detection via region-based fully convolutional networks","author":"Jifeng Dai","year":"2016"},{"key":"pone.0256290.ref018","unstructured":"Kaiming He, Georgia Gkioxari, Piotr Doll ar, and Ross Gir-shic. Mask R-CNN In Proceedings of the IEEE International Conference on Computer Vision (ICCV), pages 2961\u20132969, 2017."},{"key":"pone.0256290.ref019","first-page":"91","volume-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"Shaoqing Ren","year":"2015"},{"key":"pone.0256290.ref020","doi-asserted-by":"crossref","first-page":"764843","DOI":"10.1155\/2010\/764843","article-title":"The sensitivity and specificity of potassium hydroxide smear and fungal culture relative to clinical assessment in the evaluation of tinea pedis: a pooled analysis","volume":"2010","author":"JO Levitt","year":"2010","journal-title":"Dermatol Res Pract"},{"key":"pone.0256290.ref021","doi-asserted-by":"crossref","first-page":"965","DOI":"10.3390\/rs13050965","article-title":"Autonomous, Onborad Vision-Based Trash and Litter Detection in Low Altitude Aerial Images Collected by an Ummaned Aeiral Vehicle","volume":"13","author":"M Kraft","year":"2021","journal-title":"Remote Sens"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0256290","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,17]],"date-time":"2021-08-17T14:17:23Z","timestamp":1629209843000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0256290"}},"subtitle":[],"editor":[{"given":"Mohd Nadhir","family":"Ab Wahab","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2021,8,17]]},"references-count":21,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2021,8,17]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0256290","relation":{"has-review":[{"id-type":"doi","id":"10.32388\/R2PJWZ","asserted-by":"object"}]},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,17]]}}}