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.
Cite
Text
Bissoto et al. "GAN-Based Data Augmentation and Anonymization for Skin-Lesion Analysis: A Critical Review." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021. doi:10.1109/CVPRW53098.2021.00204Markdown
[Bissoto et al. "GAN-Based Data Augmentation and Anonymization for Skin-Lesion Analysis: A Critical Review." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021.](https://mlanthology.org/cvprw/2021/bissoto2021cvprw-ganbased/) doi:10.1109/CVPRW53098.2021.00204BibTeX
@inproceedings{bissoto2021cvprw-ganbased,
title = {{GAN-Based Data Augmentation and Anonymization for Skin-Lesion Analysis: A Critical Review}},
author = {Bissoto, Alceu and Valle, Eduardo and Avila, Sandra},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2021},
pages = {1847-1856},
doi = {10.1109/CVPRW53098.2021.00204},
url = {https://mlanthology.org/cvprw/2021/bissoto2021cvprw-ganbased/}
}