GAN-Based Data Augmentation and Anonymization for Skin-Lesion Analysis: A Critical Review

Autor(es)

Bissoto, Alceu ; Valle, Eduardo ; Avila, Sandra ; IEEE Comp Soc

• Tipo de documento: Artigo Científico
• Fonte: 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGITION WORKSHOPS (CVPRW 2021); v. N/A, p. 10-pg., 2021-01-01.

Resumo

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. (AU)

• Processo FAPESP: 19/19619-7 - Geração ilimitada de imagens de lesões de pele usando redes generativas adversariais
• Beneficiário: Alceu Emanuel Bissoto
• Modalidade de apoio: Bolsas no Brasil - Doutorado
• Processo FAPESP: 13/08293-7 - CECC - Centro de Engenharia e Ciências Computacionais
• Beneficiário: Munir Salomao Skaf
• Modalidade de apoio: Auxílio à Pesquisa - Centros de Pesquisa, Inovação e Difusão - CEPIDs