Can deep learning technology really recognize Mpox? A positive response from the EfficientNet model

On July 23, 2022, the World Health Organization (WHO) officially declared the Mpox outbreak a “Public Health Emergency of International Concern” (PHEIC), highlighting the urgent need for effective prevention and control measures worldwide. To assist healthcare managers and medical professionals in e...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaoqian Zhao, Long Lyu, Li Zhang
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Microbiology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmicb.2025.1627311/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849392648000897024
author Xiaoqian Zhao
Xiaoqian Zhao
Long Lyu
Li Zhang
Li Zhang
author_facet Xiaoqian Zhao
Xiaoqian Zhao
Long Lyu
Li Zhang
Li Zhang
author_sort Xiaoqian Zhao
collection DOAJ
description On July 23, 2022, the World Health Organization (WHO) officially declared the Mpox outbreak a “Public Health Emergency of International Concern” (PHEIC), highlighting the urgent need for effective prevention and control measures worldwide. To assist healthcare managers and medical professionals in efficiently and accurately identifying Mpox cases from similar conditions, this study proposes a lightweight deep learning model. The model uses EfficientNet as the backbone network and employs transfer learning techniques to transfer the pre-trained EfficientNet parameters, originally trained on the ImageNet dataset, into this model. This approach allows the model to have strong generalization capabilities while controlling the number of parameters and computational complexity. Experimental results show that, compared to existing advanced methods, the proposed method not only has a lower number of parameters (only 4.14 M), but also achieves optimal values in most performance metrics, including precision (95.92%), recall (95.69%), F1 score (95.80%), ROC AUC (0.998), and PR AUC (0.999). Furthermore, statistical analysis shows that the cross-validation results of this model have no significant differences (p > 0.05), which verifies the robustness of the method in Mpox identification task. Additionally, ablation experiments demonstrate that as the version of EfficientNet’s expanded network increases, the model complexity rises, with performance showing a trend of initially increasing before decreasing. In conclusion, the model proposed in this study effectively balances model’s complexity and inference accuracy. In practical applications, model selection should be based on the specific needs of decision-makers.
format Article
id doaj-art-77c9d937b79d4ce0a2fdade8147451c1
institution Kabale University
issn 1664-302X
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Microbiology
spelling doaj-art-77c9d937b79d4ce0a2fdade8147451c12025-08-20T03:40:44ZengFrontiers Media S.A.Frontiers in Microbiology1664-302X2025-08-011610.3389/fmicb.2025.16273111627311Can deep learning technology really recognize Mpox? A positive response from the EfficientNet modelXiaoqian Zhao0Xiaoqian Zhao1Long Lyu2Li Zhang3Li Zhang4Department of Dermatology, The First Hospital of China Medical University, Shenyang, ChinaKey Laboratory of Immunodermatology, Ministry of Education, and National Health Commission, National Joint Engineering Research Center for Theranostics of Immunological Skin Diseases, Shen Yang, ChinaSchool of Business, Central South University, Changsha, ChinaDepartment of Dermatology, The First Hospital of China Medical University, Shenyang, ChinaKey Laboratory of Immunodermatology, Ministry of Education, and National Health Commission, National Joint Engineering Research Center for Theranostics of Immunological Skin Diseases, Shen Yang, ChinaOn July 23, 2022, the World Health Organization (WHO) officially declared the Mpox outbreak a “Public Health Emergency of International Concern” (PHEIC), highlighting the urgent need for effective prevention and control measures worldwide. To assist healthcare managers and medical professionals in efficiently and accurately identifying Mpox cases from similar conditions, this study proposes a lightweight deep learning model. The model uses EfficientNet as the backbone network and employs transfer learning techniques to transfer the pre-trained EfficientNet parameters, originally trained on the ImageNet dataset, into this model. This approach allows the model to have strong generalization capabilities while controlling the number of parameters and computational complexity. Experimental results show that, compared to existing advanced methods, the proposed method not only has a lower number of parameters (only 4.14 M), but also achieves optimal values in most performance metrics, including precision (95.92%), recall (95.69%), F1 score (95.80%), ROC AUC (0.998), and PR AUC (0.999). Furthermore, statistical analysis shows that the cross-validation results of this model have no significant differences (p > 0.05), which verifies the robustness of the method in Mpox identification task. Additionally, ablation experiments demonstrate that as the version of EfficientNet’s expanded network increases, the model complexity rises, with performance showing a trend of initially increasing before decreasing. In conclusion, the model proposed in this study effectively balances model’s complexity and inference accuracy. In practical applications, model selection should be based on the specific needs of decision-makers.https://www.frontiersin.org/articles/10.3389/fmicb.2025.1627311/fullauxiliary diagnosisdeep learningEfficientNetimage recognitionMpox
spellingShingle Xiaoqian Zhao
Xiaoqian Zhao
Long Lyu
Li Zhang
Li Zhang
Can deep learning technology really recognize Mpox? A positive response from the EfficientNet model
Frontiers in Microbiology
auxiliary diagnosis
deep learning
EfficientNet
image recognition
Mpox
title Can deep learning technology really recognize Mpox? A positive response from the EfficientNet model
title_full Can deep learning technology really recognize Mpox? A positive response from the EfficientNet model
title_fullStr Can deep learning technology really recognize Mpox? A positive response from the EfficientNet model
title_full_unstemmed Can deep learning technology really recognize Mpox? A positive response from the EfficientNet model
title_short Can deep learning technology really recognize Mpox? A positive response from the EfficientNet model
title_sort can deep learning technology really recognize mpox a positive response from the efficientnet model
topic auxiliary diagnosis
deep learning
EfficientNet
image recognition
Mpox
url https://www.frontiersin.org/articles/10.3389/fmicb.2025.1627311/full
work_keys_str_mv AT xiaoqianzhao candeeplearningtechnologyreallyrecognizempoxapositiveresponsefromtheefficientnetmodel
AT xiaoqianzhao candeeplearningtechnologyreallyrecognizempoxapositiveresponsefromtheefficientnetmodel
AT longlyu candeeplearningtechnologyreallyrecognizempoxapositiveresponsefromtheefficientnetmodel
AT lizhang candeeplearningtechnologyreallyrecognizempoxapositiveresponsefromtheefficientnetmodel
AT lizhang candeeplearningtechnologyreallyrecognizempoxapositiveresponsefromtheefficientnetmodel