GAN-Based Data Augmentation and Anonymization for Skin-Lesion Analysis: A Critical Review
Authors:
- 1 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1847-1856
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.Keywords
All Related Versions
Funding Information
- Universal
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
This publication has 35 references indexed in Scilit:
- GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classificationNeurocomputing, 2018
- Medical Image Synthesis for Data Augmentation and Anonymization Using Generative Adversarial Networks2018
- Conditional Infilling GANs for Data Augmentation in Mammogram Classification2018
- The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesionsScientific Data, 2018
- Seven-Point Checklist and Skin Lesion Classification Using Multitask Multimodal Neural NetsIEEE Journal of Biomedical and Health Informatics, 2018
- Revisiting Unreasonable Effectiveness of Data in Deep Learning Era2017
- Image-to-Image Translation with Conditional Adversarial Networks2017
- Knowledge transfer for melanoma screening with deep learning2017
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- A Color and Texture Based Hierarchical K-NN Approach to the Classification of Non-melanoma Skin Lesions2013