1. Deep Learning-Based Synthetic Skin Lesion Image Classification.
- Author
-
Abbasi SF, Bilal M, Mukherjee T, Churm J, Pournik O, Epiphaniou G, and Arvanitis TN
- Subjects
- Datasets as Topic, Internet, Neural Networks, Computer, Humans, Deception, Deep Learning ethics, Deep Learning standards, Diagnostic Imaging ethics, Diagnostic Imaging standards, Skin Diseases classification, Skin Diseases diagnostic imaging, Skin Diseases pathology, Image Interpretation, Computer-Assisted methods, Image Interpretation, Computer-Assisted standards
- Abstract
Advances in general-purpose computers have enabled the generation of high-quality synthetic medical images that human eyes cannot differ between real and AI-generated images. To analyse the efficacy of the generated medical images, this study proposed a modified VGG16-based algorithm to recognise AI-generated medical images. Initially, 10,000 synthetic medical skin lesion images were generated using a Generative Adversarial Network (GAN), providing a set of images for comparison to real images. Then, an enhanced VGG16-based algorithm has been developed to classify real images vs AI-generated images. Following hyperparameters tuning and training, the optimal approach can classify the images with 99.82% accuracy. Multiple other evaluations have been used to evaluate the efficacy of the proposed network. The complete dataset used in this study is available online to the research community for future research.
- Published
- 2024
- Full Text
- View/download PDF