Title | ||
---|---|---|
GAN-Based Data Augmentation and Anonymization for Skin-Lesion Analysis: A Critical Review |
Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/CVPRW53098.2021.00204 | 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGITION WORKSHOPS (CVPRW 2021) |
DocType | ISSN | Citations |
Conference | 2160-7508 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Alceu Bissoto | 1 | 3 | 1.75 |
Eduardo Valle | 2 | 25 | 2.48 |
Sandra Avila | 3 | 22 | 4.18 |