Deep learning application to hyphae and spores identification in fungal fluorescence images

Abstract This study explores the application of deep learning to fungal disease diagnosis, focusing on an automated detection system for hyphae and spores in clinical samples. This study employs a combination of the YOLOX and MobileNet V2 models to analyze fungal fluorescence images. The YOLOX model...

Full description

Saved in:
Bibliographic Details
Main Authors: Ruisong Ren, Wenyu Tan, Shiting Chen, Xiaoya Xu, Dadong Zhang, Peilin Chen, Min Zhu
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-11228-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849343299370876928
author Ruisong Ren
Wenyu Tan
Shiting Chen
Xiaoya Xu
Dadong Zhang
Peilin Chen
Min Zhu
author_facet Ruisong Ren
Wenyu Tan
Shiting Chen
Xiaoya Xu
Dadong Zhang
Peilin Chen
Min Zhu
author_sort Ruisong Ren
collection DOAJ
description Abstract This study explores the application of deep learning to fungal disease diagnosis, focusing on an automated detection system for hyphae and spores in clinical samples. This study employs a combination of the YOLOX and MobileNet V2 models to analyze fungal fluorescence images. The YOLOX model is used to identify individual fungal spores and hyphae, and the MobileNet V2 model is employed to identify fungal mycelium. Finally, their combination yields the results of the two analysis processes, providing positive or negative results for the entire sample set. The proposed dual-model framework is evaluated in terms of the precision, recall, F1-score, and Kappa metrics. For the YOLOX model, the precision is 85% for hyphae and 77% for spores, and for the MobileNet V2 model, the precision is 83%. The recall value of the YOLOX model is 90% for hyphae and 85% for spores, and that of the MobileNet V2 model is 100%. The agreement of the proposed dual-model framework with the doctors’ evaluations in terms of precision, recall, and Kappa values is 92.5%, 99.3%, and 0.857, respectively. The high agreement value suggests the proposed dual-model framework’s ability to identify fungal hyphae and spores in fluorescence images can reach the level of clinicians. With the help of the proposed framework, the time and labor of fungal diagnosis can be significantly saved.
format Article
id doaj-art-233a004b20ea44e9aade429a1e6174d5
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-233a004b20ea44e9aade429a1e6174d52025-08-20T03:43:02ZengNature PortfolioScientific Reports2045-23222025-07-011511910.1038/s41598-025-11228-yDeep learning application to hyphae and spores identification in fungal fluorescence imagesRuisong Ren0Wenyu Tan1Shiting Chen2Xiaoya Xu3Dadong Zhang4Peilin Chen5Min Zhu6Department of Dermatology, Huashan Hospital, Fudan UniversitySODA Data Technology IncSODA Data Technology IncDepartment of Clinical and Translational Medicine, 3D Medicines IncDepartment of Clinical and Translational Medicine, 3D Medicines IncSODA Data Technology IncDepartment of Dermatology, Huashan Hospital, Fudan UniversityAbstract This study explores the application of deep learning to fungal disease diagnosis, focusing on an automated detection system for hyphae and spores in clinical samples. This study employs a combination of the YOLOX and MobileNet V2 models to analyze fungal fluorescence images. The YOLOX model is used to identify individual fungal spores and hyphae, and the MobileNet V2 model is employed to identify fungal mycelium. Finally, their combination yields the results of the two analysis processes, providing positive or negative results for the entire sample set. The proposed dual-model framework is evaluated in terms of the precision, recall, F1-score, and Kappa metrics. For the YOLOX model, the precision is 85% for hyphae and 77% for spores, and for the MobileNet V2 model, the precision is 83%. The recall value of the YOLOX model is 90% for hyphae and 85% for spores, and that of the MobileNet V2 model is 100%. The agreement of the proposed dual-model framework with the doctors’ evaluations in terms of precision, recall, and Kappa values is 92.5%, 99.3%, and 0.857, respectively. The high agreement value suggests the proposed dual-model framework’s ability to identify fungal hyphae and spores in fluorescence images can reach the level of clinicians. With the help of the proposed framework, the time and labor of fungal diagnosis can be significantly saved.https://doi.org/10.1038/s41598-025-11228-yFungal disease diagnosisDeep learningYOLOX modelMobileNet V2 modelImage analysisAI application in medicine
spellingShingle Ruisong Ren
Wenyu Tan
Shiting Chen
Xiaoya Xu
Dadong Zhang
Peilin Chen
Min Zhu
Deep learning application to hyphae and spores identification in fungal fluorescence images
Scientific Reports
Fungal disease diagnosis
Deep learning
YOLOX model
MobileNet V2 model
Image analysis
AI application in medicine
title Deep learning application to hyphae and spores identification in fungal fluorescence images
title_full Deep learning application to hyphae and spores identification in fungal fluorescence images
title_fullStr Deep learning application to hyphae and spores identification in fungal fluorescence images
title_full_unstemmed Deep learning application to hyphae and spores identification in fungal fluorescence images
title_short Deep learning application to hyphae and spores identification in fungal fluorescence images
title_sort deep learning application to hyphae and spores identification in fungal fluorescence images
topic Fungal disease diagnosis
Deep learning
YOLOX model
MobileNet V2 model
Image analysis
AI application in medicine
url https://doi.org/10.1038/s41598-025-11228-y
work_keys_str_mv AT ruisongren deeplearningapplicationtohyphaeandsporesidentificationinfungalfluorescenceimages
AT wenyutan deeplearningapplicationtohyphaeandsporesidentificationinfungalfluorescenceimages
AT shitingchen deeplearningapplicationtohyphaeandsporesidentificationinfungalfluorescenceimages
AT xiaoyaxu deeplearningapplicationtohyphaeandsporesidentificationinfungalfluorescenceimages
AT dadongzhang deeplearningapplicationtohyphaeandsporesidentificationinfungalfluorescenceimages
AT peilinchen deeplearningapplicationtohyphaeandsporesidentificationinfungalfluorescenceimages
AT minzhu deeplearningapplicationtohyphaeandsporesidentificationinfungalfluorescenceimages