Assessing GAN-Based Generative Modeling on Skin Lesions Images
Open Access
- 25 July 2023
- book chapter
- Published by Springer Nature
- p. 93-102
Abstract
We explored unconditional and conditional Generative Adversarial Networks (GANs) in centralized and decentralized settings. The centralized setting imitates studies on large but highly unbalanced skin lesion dataset, while the decentralized one simulates a more realistic hospital scenario with three institutions. We evaluated models’ performance in terms of fidelity, diversity, speed of training, and predictive ability of classifiers trained on the generated synthetic data. In addition, we provided explainability focused on both global and local features. Calculated distance between real images and their projections in the latent space proved the authenticity of generated samples, which is one of the main concerns in this type of applications. The code for studies is publicly available (https://github.com/aidotse/stylegan2-ada-pytorch).Keywords
This publication has 10 references indexed in Scilit:
- Discrimination between invasive and in situ melanomas using a convolutional neural networkJournal of the American Academy of Dermatology, 2022
- Analysis of the ISIC image datasets: Usage, benchmarks and recommendationsMedical Image Analysis, 2022
- Reducing bias and increasing utility by federated generative modeling of medical images using a centralized adversary2021
- Closed-Form Factorization of Latent Semantics in GANs2021
- GAN-Based Data Augmentation and Anonymization for Skin-Lesion Analysis: A Critical Review2021
- A patient-centric dataset of images and metadata for identifying melanomas using clinical contextScientific Data, 2021
- Detect and correct bias in multi-site neuroimaging datasetsMedical Image Analysis, 2021
- Analyzing and Improving the Image Quality of StyleGAN2020
- XRAI: Better Attributions Through Regions2019
- Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?2019