DermGAN: Synthetic Generation of Clinical Skin Images with Pathology
arXiv:1911.08716
Abstract
Despite the recent success in applying supervised deep learning to medical imaging tasks, the problem of obtaining large and diverse expert-annotated datasets required for the development of high performant models remains particularly challenging. In this work, we explore the possibility of using Generative Adverserial Networks (GAN) to synthesize clinical images with skin condition. We propose DermGAN, an adaptation of the popular Pix2Pix architecture, to create synthetic images for a pre-specified skin condition while being able to vary its size, location and the underlying skin color. We demonstrate that the generated images are of high fidelity using objective GAN evaluation metrics. In a Human Turing test, we note that the synthetic images are not only visually similar to real images, but also embody the respective skin condition in dermatologists' eyes. Finally, when using the synthetic images as a data augmentation technique for training a skin condition classifier, we observe that the model performs comparably to the baseline model overall while improving on rare but malignant conditions.
In full proceedings of NeurIPS ML4H workshop, 2019
References in corpus (4)
Cited by in corpus (5)
- Vulnerabilities of Connectionist AI Applications: Evaluation and Defence
- A Model-Based Approach to Synthetic Data Set Generation for Patient-Ventilator Waveforms for Machine Learning and Educational Use
- Interpretable and synergistic deep learning for visual explanation and statistical estimations of segmentation of disease features from medical images
- Skin disease diagnosis with deep learning: a review
- Generative Adversarial Networks for anonymous Acneic face dataset generation