{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T16:59:12Z","timestamp":1792083552417,"version":"4.4.0"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T00:00:00Z","timestamp":1773273600000},"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>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Vulvovaginal candidiasis (VVC) is a common fungal infection that is frequently diagnosed through manual microscopic examination of vaginal discharge. Artificial Intelligence (AI)-assisted analysis of microscopic images enables rapid and accurate diagnosis, supporting timely and effective antifungal therapeutic interventions. However, conventional light microscopy often lacks cameras, limiting digital image analysis and AI applications. While mobile devices offer a practical alternative, no AI tools currently exist for the automated detection of fungal cellular morphology in microscopic images captured by smartphones and tablets. In this study, we developed deep learning models to segment fungal morphologies in microscopic images of vaginal discharge acquired with smartphones and tablets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      Three models were developed: ResNet18 for binary classification (\n                      <jats:italic>Candida<\/jats:italic>\n                      presence\/absence), YOLOv5 for detection, and YOLOv11 for segmentation. Models were trained using 1,259 microscopy images of Gram-stained vaginal discharge acquired with smartphones or tablets, along with 67 images obtained from conventional microscopes. These images were divided into training, validation, and test sets. Annotated microscopic images for fungal elements were used to train YOLO models in a two-stage approach: Stage 1 utilized 687 annotated images of yeast infections to learn general fungal morphology, comprising 266 bounding box\u2013annotated images sourced from Roboflow and 421 segmentation-labeled images manually annotated from the open-access dataset. Stage 2 fine-tuned the models on the annotated mobile device-acquired dataset. Metrics included F1-score, area under the curve (AUC), precision, recall, and mean average precision at 50% intersection over union (mAP50). Experts assessed segmentation outputs for diagnostic utility, providing explainability to the AI results.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>ResNet18 achieved F1-score=0.986, AUC = 0.99. YOLOv5 performed best at IoU=0.50 (precision=0.812, recall=0.622, mAP50 = 0.730); YOLOv11 at IoU=0.25 (precision=0.766, recall=0.700, mAP50 = 0.727). Expert ratings averaged 4.25\/5. Only 3.68% of images were rated as inappropriate due to false negative or false positive segmentations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>\n                      ResNet18 accurately classified microscopic images for fungal elements, while the YOLOv11 model effectively delineated\n                      <jats:italic>Candida<\/jats:italic>\n                      morphologies, including yeasts, budding yeasts, and filamentous forms from clinical specimens. The high accuracy and positive expert feedback demonstrate the feasibility of integrating AI-assisted mobile microscopy into routine workflows, thereby advancing digital analysis of microbial infections using conventional light microscopy. With further clinical validation and expansion to include other infections, this approach holds great potential to establish robust real-world utility.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fcimb.2026.1787545","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T06:48:05Z","timestamp":1773298085000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Fungal recognition in vaginal discharge using deep learning analysis of mobile device-acquired microscopic images"],"prefix":"10.3389","volume":"16","author":[{"given":"Monsicha","family":"Pongpom","sequence":"first","affiliation":[{"name":"Department of Microbiology, Faculty of Medicine, Chiang Mai University","place":["Chiang Mai, Thailand"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siriwoot","family":"Sookkhee","sequence":"additional","affiliation":[{"name":"Department of Microbiology, Faculty of Medicine, Chiang Mai University","place":["Chiang Mai, Thailand"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siriporn","family":"Chongkae","sequence":"additional","affiliation":[{"name":"Department of Microbiology, Faculty of Medicine, Chiang Mai University","place":["Chiang Mai, Thailand"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sara","family":"Wattanasombat","sequence":"additional","affiliation":[{"name":"Department of Microbiology, Faculty of Medicine, Chiang Mai University","place":["Chiang Mai, Thailand"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kornprom","family":"Pikulkaew","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Faculty of Science, Chiang Mai University","place":["Chiang Mai, Thailand"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Narin","family":"Lawan","sequence":"additional","affiliation":[{"name":"Department of Chemistry, Faculty of Science, Chiang Mai University","place":["Chiang Mai, Thailand"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Phit","family":"Upaphong","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Faculty of Medicine, Chiang Mai University","place":["Chiang Mai, Thailand"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tanaporn","family":"Wangsanut","sequence":"additional","affiliation":[{"name":"Department of Microbiology, Faculty of Medicine, Chiang Mai University","place":["Chiang Mai, Thailand"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,12]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1368","DOI":"10.1001\/jama.291.11.1368","article-title":"Evaluation of vaginal complaints","volume":"291","author":"Anderson","year":"2004","journal-title":"Jama"},{"key":"B2","doi-asserted-by":"publisher","first-page":"15","DOI":"10.3390\/parasitologia5020015","article-title":"Investigation of causative agents of vaginitis in symptomatic and asymptomatic women in Konya, Turkey","volume":"5","author":"Beder","year":"2025","journal-title":"Parasitologia"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1128\/spectrum.01472-22","article-title":"A Deep learning approach to capture the essence of Candida albicans morphologies","volume":"10","author":"Bettauer","year":"2022","journal-title":"Microbiol. Spectr."},{"key":"B4","first-page":"839","article-title":"Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks","author":"Chattopadhay","year":"2018"},{"key":"B5","doi-asserted-by":"publisher","first-page":"myaf097","DOI":"10.1093\/mmy\/myaf097","article-title":"Deep learning for the identification of Candida spp. directly from blood culture gram stains from candidemia patients","volume":"63","author":"Cuevas-Tello","year":"2025","journal-title":"Med. Mycol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pntd.0009677","article-title":"Mobile microscopy and telemedicine platform assisted by deep learning for the quantification of Trichuris trichiura infection","volume":"15","author":"Dacal","year":"2021","journal-title":"PLoS Negl. Trop. Dis."},{"key":"B7","doi-asserted-by":"publisher","first-page":"905","DOI":"10.3109\/1040841X.2015.1091805","article-title":"Vulvovaginal candidiasis: Epidemiology, microbiology and risk factors","volume":"42","author":"Gon\u00e7alves","year":"2016","journal-title":"Crit. Rev. Microbiol."},{"key":"B8","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"B9","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1038\/s41746-025-01539-9","article-title":"Deep learning-based mobile application for efficient eyelid tumor recognition in clinical images","volume":"8","author":"Hui","year":"2025","journal-title":"NPJ Digit Med."},{"key":"B10","doi-asserted-by":"publisher","first-page":"85","DOI":"10.17966\/JMI.2024.29.3.85","article-title":"Artificial intelligence applications in medical mycology: Current and Future","volume":"29","author":"Kim","year":"2024","journal-title":"J. Mycology Infection"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0256290","article-title":"Automated detection of superficial fungal infections from microscopic images through a regional convolutional neural network","volume":"16","author":"Koo","year":"2021","journal-title":"PLoS One"},{"key":"B12","doi-asserted-by":"publisher","first-page":"908","DOI":"10.1049\/iet-ipr.2015.0150","article-title":"Combination of contrast limited adaptive histogram equalisation and discrete wavelet transform for image enhancement","volume":"9","author":"Lidong","year":"2015","journal-title":"IET image Process."},{"key":"B13","first-page":"8693","article-title":"Microsoft COCO: Common objects in context","author":"Lin","year":"2014"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1967699","DOI":"10.1080\/20002297.2021.1967699","article-title":"Mycotic infections - mucormycosis and oral candidiasis associated with Covid-19: a significant and challenging association","volume":"13","author":"Nambiar","year":"2021","journal-title":"J. Oral. Microbiol."},{"key":"B15","doi-asserted-by":"publisher","first-page":"19171","DOI":"10.1038\/s41598-025-04626-9","article-title":"Applying machine learning with MobileNetV2 model for rapid screening of vaginal discharge samples in vaginitis diagnosis","volume":"15","author":"Nguyen","year":"2025","journal-title":"Sci. Rep."},{"key":"B16","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1038\/nrmicro.2016.157","article-title":"Candida albicans cell-type switching and functional plasticity in the mammalian host","volume":"15","author":"Noble","year":"2017","journal-title":"Nat. Rev. Microbiol."},{"key":"B17","first-page":"321","article-title":"Vaginitis: diagnosis and treatment","volume":"97","author":"Paladine","year":"2018","journal-title":"Am. Fam Physician"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.3389\/fcimb.2021.759795","article-title":"Recent advances in presentation, diagnosis and treatment for mixed vaginitis","volume":"11","author":"Qi","year":"2021","journal-title":"Front. Cell Infect. Microbiol."},{"key":"B19","doi-asserted-by":"publisher","first-page":"27222","DOI":"10.1038\/s41598-025-11228-y","article-title":"Deep learning application to hyphae and spores identification in fungal fluorescence images","volume":"15","author":"Ren","year":"2025","journal-title":"Sci. Rep."},{"key":"B20","doi-asserted-by":"publisher","first-page":"1645","DOI":"10.1093\/infdis\/jiz365","article-title":"Vaginal epithelial cells discriminate between yeast and hyphae of Candida albicans in women who are colonized or have vaginal candidiasis","volume":"220","author":"Roselletti","year":"2019","journal-title":"J. Infect. Dis."},{"key":"B21","first-page":"4510","article-title":"Mobilenetv2: Inverted residuals and linear bottlenecks","author":"Sandler","year":"2018"},{"key":"B22","first-page":"618","article-title":"Grad-cam: Visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"},{"key":"B23","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1016\/j.mcna.2022.10.009","article-title":"Infectious vaginitis, cervicitis, and pelvic inflammatory disease","volume":"107","author":"Shroff","year":"2023","journal-title":"Med. Clin. North Am."},{"key":"B24","doi-asserted-by":"publisher","first-page":"1896","DOI":"10.1056\/NEJM199712253372607","article-title":"Vaginitis","volume":"337","author":"Sobel","year":"1997","journal-title":"N Engl. J. Med."},{"key":"B25","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1038\/s43856-025-01144-7","article-title":"Using deep learning systems for diagnosing common skin lesions in sexual health","volume":"5","author":"Soe","year":"2025","journal-title":"Commun. Med. (Lond)"},{"key":"B26","article-title":"Image capture: AI-assisted sexually transmitted infection diagnosis tool for clinicians in a clinical setting","author":"Soe","year":"2023"},{"key":"B27","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/s12348-025-00465-x","article-title":"Diagnosis of microbial keratitis using smartphone-captured images; a deep-learning model","volume":"15","author":"Soleimani","year":"2025","journal-title":"J. Ophthalmic Inflammation Infect."},{"key":"B28","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1038\/nrmicro2636","article-title":"Growth of Candida albicans hyphae","volume":"9","author":"Sudbery","year":"2011","journal-title":"Nat. Rev. Microbiol."},{"key":"B29","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1016\/j.tim.2004.05.008","article-title":"The distinct morphogenic states of Candida albicans","volume":"12","author":"Sudbery","year":"2004","journal-title":"Trends Microbiol."},{"key":"B30","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1128\/spectrum.01691-24","article-title":"AI-assisted diagnosis of vulvovaginal candidiasis using cascaded neural networks","volume":"13","author":"Wang","year":"2025","journal-title":"Microbiol. Spectr."},{"key":"B32","volume-title":"YOLOv5 Model for Fungal Element Detection (bestYeast701.pt). Hugging Face","author":"Wangsanut","year":"2025"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.15585\/mmwr.rr7004a1","article-title":"Sexually transmitted infections treatment guidelines 2021","volume":"70","author":"Workowski","year":"2021","journal-title":"MMWR Recomm Rep."},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.2196\/70256","article-title":"Effectiveness of a 5G local area network-based digital microscopy interactive system: Quasi-experimental design","volume":"11","author":"Xu","year":"2025","journal-title":"JMIR Med. Educ."},{"key":"B35","first-page":"2392","volume-title":"Contrast limited adaptive histogram equalization based enhancement for real time video system. 2014 international conference on advances in computing, communications and informatics (ICACCI)","author":"Yadav","year":"2014"}],"container-title":["Frontiers in Cellular and Infection Microbiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcimb.2026.1787545\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T06:48:06Z","timestamp":1773298086000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcimb.2026.1787545\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,12]]},"references-count":35,"alternative-id":["10.3389\/fcimb.2026.1787545"],"URL":"https:\/\/doi.org\/10.3389\/fcimb.2026.1787545","relation":{},"ISSN":["2235-2988"],"issn-type":[{"value":"2235-2988","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,12]]},"article-number":"1787545"}}