Robustly detecting mpox and non-mpox using a deep learning framework based on image inpainting
Abstract Due to the lack of efficient mpox diagnostic technology, mpox cases continue to increase. Recently, the great potential of deep learning models in detecting mpox and non-mpox has been proven. However, existing methods are susceptible to interference from various noises in real-world setting...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-85771-z |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544753122902016 |
|---|---|
| author | Yujun Cao Yubiao Yue Xiaoming Ma Di Liu Rongkai Ni Haihua Liang Zhenzhang Li |
| author_facet | Yujun Cao Yubiao Yue Xiaoming Ma Di Liu Rongkai Ni Haihua Liang Zhenzhang Li |
| author_sort | Yujun Cao |
| collection | DOAJ |
| description | Abstract Due to the lack of efficient mpox diagnostic technology, mpox cases continue to increase. Recently, the great potential of deep learning models in detecting mpox and non-mpox has been proven. However, existing methods are susceptible to interference from various noises in real-world settings, require diverse non-mpox images, and fail to detect abnormal input, which makes them unsuitable for practical deployment and application. To address these challenges, we proposed a novel strategy based on image inpainting called “Mask, Inpainting, and Measure” (MIM). In MIM’s pipeline, a generative adversarial network learns feature representations of mpox images by inpainting the masked mpox images. On this basis, MIM measure the similarity between the inpainted image and the original image to detect mpox and non-mpox. Compared with multi-class classification models, MIM can handle unknown categories and abnormal inputs more effectively. We used the recognized mpox dataset (MSLD) and a dataset containing 18 categories of non-mpox skin diseases to verify the effectiveness and robustness of MIM. Experimental results show that the average AUROC of MIM achieves 0.8237. In addition, external clinical testing further demonstrates the robustness of MIM. Importantly, we developed a free smartphone app to help the public and healthcare professionals detect mpox more conveniently. |
| format | Article |
| id | doaj-art-7a64f1c008a04256939a02bdba1160d8 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-7a64f1c008a04256939a02bdba1160d82025-01-12T12:17:33ZengNature PortfolioScientific Reports2045-23222025-01-0115111510.1038/s41598-025-85771-zRobustly detecting mpox and non-mpox using a deep learning framework based on image inpaintingYujun Cao0Yubiao Yue1Xiaoming Ma2Di Liu3Rongkai Ni4Haihua Liang5Zhenzhang Li6Department of Basic Courses, Guangzhou Maritime UniversitySchool of Biomedical Engineering, The Second Affiliated Hospital of Guangzhou Medical University, Guangzhou Medical UniversityDepartment of Basic Courses, Guangzhou Maritime UniversityDepartment of Basic Courses, Guangzhou Maritime UniversitySchool of Biomedical Engineering, The Second Affiliated Hospital of Guangzhou Medical University, Guangzhou Medical UniversitySchool of Mathematics and Systems Science, Guangdong Polytechnic Normal UniversitySchool of Mathematics and Systems Science, Guangdong Polytechnic Normal UniversityAbstract Due to the lack of efficient mpox diagnostic technology, mpox cases continue to increase. Recently, the great potential of deep learning models in detecting mpox and non-mpox has been proven. However, existing methods are susceptible to interference from various noises in real-world settings, require diverse non-mpox images, and fail to detect abnormal input, which makes them unsuitable for practical deployment and application. To address these challenges, we proposed a novel strategy based on image inpainting called “Mask, Inpainting, and Measure” (MIM). In MIM’s pipeline, a generative adversarial network learns feature representations of mpox images by inpainting the masked mpox images. On this basis, MIM measure the similarity between the inpainted image and the original image to detect mpox and non-mpox. Compared with multi-class classification models, MIM can handle unknown categories and abnormal inputs more effectively. We used the recognized mpox dataset (MSLD) and a dataset containing 18 categories of non-mpox skin diseases to verify the effectiveness and robustness of MIM. Experimental results show that the average AUROC of MIM achieves 0.8237. In addition, external clinical testing further demonstrates the robustness of MIM. Importantly, we developed a free smartphone app to help the public and healthcare professionals detect mpox more conveniently.https://doi.org/10.1038/s41598-025-85771-zMpox DetectionDeep learningNovelty detectionImage InpaintingGenerative model |
| spellingShingle | Yujun Cao Yubiao Yue Xiaoming Ma Di Liu Rongkai Ni Haihua Liang Zhenzhang Li Robustly detecting mpox and non-mpox using a deep learning framework based on image inpainting Scientific Reports Mpox Detection Deep learning Novelty detection Image Inpainting Generative model |
| title | Robustly detecting mpox and non-mpox using a deep learning framework based on image inpainting |
| title_full | Robustly detecting mpox and non-mpox using a deep learning framework based on image inpainting |
| title_fullStr | Robustly detecting mpox and non-mpox using a deep learning framework based on image inpainting |
| title_full_unstemmed | Robustly detecting mpox and non-mpox using a deep learning framework based on image inpainting |
| title_short | Robustly detecting mpox and non-mpox using a deep learning framework based on image inpainting |
| title_sort | robustly detecting mpox and non mpox using a deep learning framework based on image inpainting |
| topic | Mpox Detection Deep learning Novelty detection Image Inpainting Generative model |
| url | https://doi.org/10.1038/s41598-025-85771-z |
| work_keys_str_mv | AT yujuncao robustlydetectingmpoxandnonmpoxusingadeeplearningframeworkbasedonimageinpainting AT yubiaoyue robustlydetectingmpoxandnonmpoxusingadeeplearningframeworkbasedonimageinpainting AT xiaomingma robustlydetectingmpoxandnonmpoxusingadeeplearningframeworkbasedonimageinpainting AT diliu robustlydetectingmpoxandnonmpoxusingadeeplearningframeworkbasedonimageinpainting AT rongkaini robustlydetectingmpoxandnonmpoxusingadeeplearningframeworkbasedonimageinpainting AT haihualiang robustlydetectingmpoxandnonmpoxusingadeeplearningframeworkbasedonimageinpainting AT zhenzhangli robustlydetectingmpoxandnonmpoxusingadeeplearningframeworkbasedonimageinpainting |