GAN-Based Data Augmentation and Anonymization for Skin-Lesion Analysis: A Critical Review
This review highlights limitations in GAN applications for medical imaging, potentially affecting researchers and practitioners in dermatology and AI.
The paper critically reviews the use of Generative Adversarial Networks (GANs) for data augmentation and anonymization in skin-lesion analysis, finding that favorable results only occur on out-of-distribution test sets, suggesting caution in adoption due to costs and risks.
Despite the growing availability of high-quality public datasets, the lack of training samples is still one of the main challenges of deep-learning for skin lesion analysis. Generative Adversarial Networks (GANs) appear as an enticing alternative to alleviate the issue, by synthesizing samples indistinguishable from real images, with a plethora of works employing them for medical applications. Nevertheless, carefully designed experiments for skin-lesion diagnosis with GAN-based data augmentation show favorable results only on out-of-distribution test sets. For GAN-based data anonymization $-$ where the synthetic images replace the real ones $-$ favorable results also only appear for out-of-distribution test sets. Because of the costs and risks associated with GAN usage, those results suggest caution in their adoption for medical applications.