Leveraging Vision Attention Transformers for Detection of Artificially Synthesized Dermoscopic Lesion Deepfakes Using Derm-CGAN
Synthesized multimedia is an open concern that has received much too little attention in the scientific community. In recent years, generative models have been utilized in maneuvering deepfakes in medical imaging modalities. We investigate the synthesized generation and detection of dermoscopic skin...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/5/825 |
| _version_ | 1797615612117123072 |
|---|---|
| author | Misaj Sharafudeen Andrew J. Vinod Chandra S. S. |
| author_facet | Misaj Sharafudeen Andrew J. Vinod Chandra S. S. |
| author_sort | Misaj Sharafudeen |
| collection | DOAJ |
| description | Synthesized multimedia is an open concern that has received much too little attention in the scientific community. In recent years, generative models have been utilized in maneuvering deepfakes in medical imaging modalities. We investigate the synthesized generation and detection of dermoscopic skin lesion images by leveraging the conceptual aspects of Conditional Generative Adversarial Networks and state-of-the-art Vision Transformers (ViT). The Derm-CGAN is architectured for the realistic generation of six different dermoscopic skin lesions. Analysis of the similarity between real and synthesized fakes revealed a high correlation. Further, several ViT variations were investigated to distinguish between actual and fake lesions. The best-performing model achieved an accuracy of 97.18% which has over 7% marginal gain over the second best-performing network. The trade-off of the proposed model compared to other networks, as well as a benchmark face dataset, was critically analyzed in terms of computational complexity. This technology is capable of harming laymen through medical misdiagnosis or insurance scams. Further research in this domain would be able to assist physicians and the general public in countering and resisting deepfake threats. |
| first_indexed | 2024-03-11T07:29:09Z |
| format | Article |
| id | doaj.art-cd1eedbd19f94873993998edef5485bf |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-11T07:29:09Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-cd1eedbd19f94873993998edef5485bf2023-11-17T07:28:44ZengMDPI AGDiagnostics2075-44182023-02-0113582510.3390/diagnostics13050825Leveraging Vision Attention Transformers for Detection of Artificially Synthesized Dermoscopic Lesion Deepfakes Using Derm-CGANMisaj Sharafudeen0Andrew J.1Vinod Chandra S. S.2Department of Computer Science, University of Kerala, Kerala 695581, IndiaDepartment of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal 576104, IndiaDepartment of Computer Science, University of Kerala, Kerala 695581, IndiaSynthesized multimedia is an open concern that has received much too little attention in the scientific community. In recent years, generative models have been utilized in maneuvering deepfakes in medical imaging modalities. We investigate the synthesized generation and detection of dermoscopic skin lesion images by leveraging the conceptual aspects of Conditional Generative Adversarial Networks and state-of-the-art Vision Transformers (ViT). The Derm-CGAN is architectured for the realistic generation of six different dermoscopic skin lesions. Analysis of the similarity between real and synthesized fakes revealed a high correlation. Further, several ViT variations were investigated to distinguish between actual and fake lesions. The best-performing model achieved an accuracy of 97.18% which has over 7% marginal gain over the second best-performing network. The trade-off of the proposed model compared to other networks, as well as a benchmark face dataset, was critically analyzed in terms of computational complexity. This technology is capable of harming laymen through medical misdiagnosis or insurance scams. Further research in this domain would be able to assist physicians and the general public in countering and resisting deepfake threats.https://www.mdpi.com/2075-4418/13/5/825artificial synthesismedical deepfakesdermoscopic skin lesionsgenerative adversarial networksattention vision transformers |
| spellingShingle | Misaj Sharafudeen Andrew J. Vinod Chandra S. S. Leveraging Vision Attention Transformers for Detection of Artificially Synthesized Dermoscopic Lesion Deepfakes Using Derm-CGAN Diagnostics artificial synthesis medical deepfakes dermoscopic skin lesions generative adversarial networks attention vision transformers |
| title | Leveraging Vision Attention Transformers for Detection of Artificially Synthesized Dermoscopic Lesion Deepfakes Using Derm-CGAN |
| title_full | Leveraging Vision Attention Transformers for Detection of Artificially Synthesized Dermoscopic Lesion Deepfakes Using Derm-CGAN |
| title_fullStr | Leveraging Vision Attention Transformers for Detection of Artificially Synthesized Dermoscopic Lesion Deepfakes Using Derm-CGAN |
| title_full_unstemmed | Leveraging Vision Attention Transformers for Detection of Artificially Synthesized Dermoscopic Lesion Deepfakes Using Derm-CGAN |
| title_short | Leveraging Vision Attention Transformers for Detection of Artificially Synthesized Dermoscopic Lesion Deepfakes Using Derm-CGAN |
| title_sort | leveraging vision attention transformers for detection of artificially synthesized dermoscopic lesion deepfakes using derm cgan |
| topic | artificial synthesis medical deepfakes dermoscopic skin lesions generative adversarial networks attention vision transformers |
| url | https://www.mdpi.com/2075-4418/13/5/825 |
| work_keys_str_mv | AT misajsharafudeen leveragingvisionattentiontransformersfordetectionofartificiallysynthesizeddermoscopiclesiondeepfakesusingdermcgan AT andrewj leveragingvisionattentiontransformersfordetectionofartificiallysynthesizeddermoscopiclesiondeepfakesusingdermcgan AT vinodchandrass leveragingvisionattentiontransformersfordetectionofartificiallysynthesizeddermoscopiclesiondeepfakesusingdermcgan |